View All Items
(1 - 13 of 13)
- Title
- TAMING CROWDED VISUAL SCENES.
- Creator
-
Ali, Saad, Shah, Mubarak, University of Central Florida
- Abstract / Description
-
Computer vision algorithms have played a pivotal role in commercial video surveillance systems for a number of years. However, a common weakness among these systems is their inability to handle crowded scenes. In this thesis, we have developed algorithms that overcome some of the challenges encountered in videos of crowded environments such as sporting events, religious festivals, parades, concerts, train stations, airports, and malls. We adopt a top-down approach by first performing a global...
Show moreComputer vision algorithms have played a pivotal role in commercial video surveillance systems for a number of years. However, a common weakness among these systems is their inability to handle crowded scenes. In this thesis, we have developed algorithms that overcome some of the challenges encountered in videos of crowded environments such as sporting events, religious festivals, parades, concerts, train stations, airports, and malls. We adopt a top-down approach by first performing a global-level analysis that locates dynamically distinct crowd regions within the video. This knowledge is then employed in the detection of abnormal behaviors and tracking of individual targets within crowds. In addition, the thesis explores the utility of contextual information necessary for persistent tracking and re-acquisition of objects in crowded scenes. For the global-level analysis, a framework based on Lagrangian Particle Dynamics is proposed to segment the scene into dynamically distinct crowd regions or groupings. For this purpose, the spatial extent of the video is treated as a phase space of a time-dependent dynamical system in which transport from one region of the phase space to another is controlled by the optical flow. Next, a grid of particles is advected forward in time through the phase space using a numerical integration to generate a ``flow map''. The flow map relates the initial positions of particles to their final positions. The spatial gradients of the flow map are used to compute a Cauchy Green Deformation tensor that quantifies the amount by which the neighboring particles diverge over the length of the integration. The maximum eigenvalue of the tensor is used to construct a forward Finite Time Lyapunov Exponent (FTLE) field that reveals the Attracting Lagrangian Coherent Structures (LCS). The same process is repeated by advecting the particles backward in time to obtain a backward FTLE field that reveals the repelling LCS. The attracting and repelling LCS are the time dependent invariant manifolds of the phase space and correspond to the boundaries between dynamically distinct crowd flows. The forward and backward FTLE fields are combined to obtain one scalar field that is segmented using a watershed segmentation algorithm to obtain the labeling of distinct crowd-flow segments. Next, abnormal behaviors within the crowd are localized by detecting changes in the number of crowd-flow segments over time. Next, the global-level knowledge of the scene generated by the crowd-flow segmentation is used as an auxiliary source of information for tracking an individual target within a crowd. This is achieved by developing a scene structure-based force model. This force model captures the notion that an individual, when moving in a particular scene, is subjected to global and local forces that are functions of the layout of that scene and the locomotive behavior of other individuals in his or her vicinity. The key ingredients of the force model are three floor fields that are inspired by research in the field of evacuation dynamics; namely, Static Floor Field (SFF), Dynamic Floor Field (DFF), and Boundary Floor Field (BFF). These fields determine the probability of moving from one location to the next by converting the long-range forces into local forces. The SFF specifies regions of the scene that are attractive in nature, such as an exit location. The DFF, which is based on the idea of active walker models, corresponds to the virtual traces created by the movements of nearby individuals in the scene. The BFF specifies influences exhibited by the barriers within the scene, such as walls and no-entry areas. By combining influence from all three fields with the available appearance information, we are able to track individuals in high-density crowds. The results are reported on real-world sequences of marathons and railway stations that contain thousands of people. A comparative analysis with respect to an appearance-based mean shift tracker is also conducted by generating the ground truth. The result of this analysis demonstrates the benefit of using floor fields in crowded scenes. The occurrence of occlusion is very frequent in crowded scenes due to a high number of interacting objects. To overcome this challenge, we propose an algorithm that has been developed to augment a generic tracking algorithm to perform persistent tracking in crowded environments. The algorithm exploits the contextual knowledge, which is divided into two categories consisting of motion context (MC) and appearance context (AC). The MC is a collection of trajectories that are representative of the motion of the occluded or unobserved object. These trajectories belong to other moving individuals in a given environment. The MC is constructed using a clustering scheme based on the Lyapunov Characteristic Exponent (LCE), which measures the mean exponential rate of convergence or divergence of the nearby trajectories in a given state space. Next, the MC is used to predict the location of the occluded or unobserved object in a regression framework. It is important to note that the LCE is used for measuring divergence between a pair of particles while the FTLE field is obtained by computing the LCE for a grid of particles. The appearance context (AC) of a target object consists of its own appearance history and appearance information of the other objects that are occluded. The intent is to make the appearance descriptor of the target object more discriminative with respect to other unobserved objects, thereby reducing the possible confusion between the unobserved objects upon re-acquisition. This is achieved by learning the distribution of the intra-class variation of each occluded object using all of its previous observations. In addition, a distribution of inter-class variation for each target-unobservable object pair is constructed. Finally, the re-acquisition decision is made using both the MC and the AC.
Show less - Date Issued
- 2008
- Identifier
- CFE0002135, ucf:47507
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0002135
- Title
- Visual Analysis of Extremely Dense Crowded Scenes.
- Creator
-
Idrees, Haroon, Shah, Mubarak, Da Vitoria Lobo, Niels, Stanley, Kenneth, Atia, George, Saleh, Bahaa, University of Central Florida
- Abstract / Description
-
Visual analysis of dense crowds is particularly challenging due to large number of individuals, occlusions, clutter, and fewer pixels per person which rarely occur in ordinary surveillance scenarios. This dissertation aims to address these challenges in images and videos of extremely dense crowds containing hundreds to thousands of humans. The goal is to tackle the fundamental problems of counting, detecting and tracking people in such images and videos using visual and contextual cues that...
Show moreVisual analysis of dense crowds is particularly challenging due to large number of individuals, occlusions, clutter, and fewer pixels per person which rarely occur in ordinary surveillance scenarios. This dissertation aims to address these challenges in images and videos of extremely dense crowds containing hundreds to thousands of humans. The goal is to tackle the fundamental problems of counting, detecting and tracking people in such images and videos using visual and contextual cues that are automatically derived from the crowded scenes.For counting in an image of extremely dense crowd, we propose to leverage multiple sources of information to compute an estimate of the number of individuals present in the image. Our approach relies on sources such as low confidence head detections, repetition of texture elements (using SIFT), and frequency-domain analysis to estimate counts, along with confidence associated with observing individuals, in an image region. Furthermore, we employ a global consistency constraint on counts using Markov Random Field which caters for disparity in counts in local neighborhoods and across scales. We tested this approach on crowd images with the head counts ranging from 94 to 4543 and obtained encouraging results. Through this approach, we are able to count people in images of high-density crowds unlike previous methods which are only applicable to videos of low to medium density crowded scenes. However, the counting procedure just outputs a single number for a large patch or an entire image. With just the counts, it becomes difficult to measure the counting error for a query image with unknown number of people. For this, we propose to localize humans by finding repetitive patterns in the crowd image. Starting with detections from an underlying head detector, we correlate them within the image after their selection through several criteria: in a pre-defined grid, locally, or at multiple scales by automatically finding the patches that are most representative of recurring patterns in the crowd image. Finally, the set of generated hypotheses is selected using binary integer quadratic programming with Special Ordered Set (SOS) Type 1 constraints.Human Detection is another important problem in the analysis of crowded scenes where the goal is to place a bounding box on visible parts of individuals. Primarily applicable to images depicting medium to high density crowds containing several hundred humans, it is a crucial pre-requisite for many other visual tasks, such as tracking, action recognition or detection of anomalous behaviors, exhibited by individuals in a dense crowd. For detecting humans, we explore context in dense crowds in the form of locally-consistent scale prior which captures the similarity in scale in local neighborhoods with smooth variation over the image. Using the scale and confidence of detections obtained from an underlying human detector, we infer scale and confidence priors using Markov Random Field. In an iterative mechanism, the confidences of detections are modified to reflect consistency with the inferred priors, and the priors are updated based on the new detections. The final set of detections obtained are then reasoned for occlusion using Binary Integer Programming where overlaps and relations between parts of individuals are encoded as linear constraints. Both human detection and occlusion reasoning in this approach are solved with local neighbor-dependent constraints, thereby respecting the inter-dependence between individuals characteristic to dense crowd analysis. In addition, we propose a mechanism to detect different combinations of body parts without requiring annotations for individual combinations.Once human detection and localization is performed, we then use it for tracking people in dense crowds. Similar to the use of context as scale prior for human detection, we exploit it in the form of motion concurrence for tracking individuals in dense crowds. The proposed method for tracking provides an alternative and complementary approach to methods that require modeling of crowd flow. Simultaneously, it is less likely to fail in the case of dynamic crowd flows and anomalies by minimally relying on previous frames. The approach begins with the automatic identification of prominent individuals from the crowd that are easy to track. Then, we use Neighborhood Motion Concurrence to model the behavior of individuals in a dense crowd, this predicts the position of an individual based on the motion of its neighbors. When the individual moves with the crowd flow, we use Neighborhood Motion Concurrence to predict motion while leveraging five-frame instantaneous flow in case of dynamically changing flow and anomalies. All these aspects are then embedded in a framework which imposes hierarchy on the order in which positions of individuals are updated. The results are reported on eight sequences of medium to high density crowds and our approach performs on par with existing approaches without learning or modeling patterns of crowd flow.We experimentally demonstrate the efficacy and reliability of our algorithms by quantifying the performance of counting, localization, as well as human detection and tracking on new and challenging datasets containing hundreds to thousands of humans in a given scene.
Show less - Date Issued
- 2014
- Identifier
- CFE0005508, ucf:50367
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0005508
- Title
- MYSTERY SHOPPER MOTIVATIONS AND THE PRESENCE OF MOTIVATION CROWDING.
- Creator
-
Allison, Pamela, Severt, Denver, University of Central Florida
- Abstract / Description
-
Mystery shopping is used in a variety of service industries to measure service performance, as a training tool for employees, and to ensure the safety and security of the product offered. The persons performing this activity, mystery shoppers, experience various motivations, some of which are similar to employees and/or volunteers. These motivations can be intrinsic, where the performance of the activity is a reward itself, or extrinsic, meaning performance of the activity is a method for...
Show moreMystery shopping is used in a variety of service industries to measure service performance, as a training tool for employees, and to ensure the safety and security of the product offered. The persons performing this activity, mystery shoppers, experience various motivations, some of which are similar to employees and/or volunteers. These motivations can be intrinsic, where the performance of the activity is a reward itself, or extrinsic, meaning performance of the activity is a method for attaining a reward. The dominance of intrinsic or extrinsic motivation can shift within the individual, which is termed motivation crowding. Individuals can crowd in when intrinsic motivations are supplemented and supported by extrinsic motivations, or crowd out if extrinsic motivations become the dominant factor, devaluing the activity and reducing intrinsic motivation. This study examines the motivations of mystery shoppers and examines whether the tenets of motivation crowding are supported using a mixed methods research design. The objectives for the study were to identify, classify, and measure mystery shopping motivations using motivational theory to test for the presence of motivation crowding, as reflected in the initial two hypotheses: H1: There are salient dimensions of motivation influencing individual participation in mystery shopping activities. H2: Mystery shoppers experience motivation "crowding in" after initial performance of mystery shopping activities, with intrinsic motivations increasing. To address the first hypothesis, the study began with a qualitative research approach utilizing semi-structured interviews with current mystery shoppers. Through qualitative analysis, 14 constructs of mystery shopper motivations were identified. The constructs were then utilized to develop the Mystery Shopper Motivation Scale, following the eight-step scale development process defined by DeVellis (2003). The scale was then refined through pre-testing and pilot testing, and was used in a survey administration to 323 current mystery shoppers. Through factor analysis, the motivations identified were quantitatively supported, and then dependent t-tests indicated the presence of motivation crowding affecting mystery shoppers. However, unanticipated increases in extrinsic motivations prompted further analysis of motivations based on mystery shopping experience levels, resulting in the addition of a third hypothesis: H3: The direction of motivation crowding is dependent on the mystery shopper's level of experience. H3a: Mystery shoppers who have performed less than 10 mystery shops will crowd in, with an increase in intrinsic motivations and a decrease in extrinsic motivations. H3b: Mystery shoppers who have performed between 10-24 mystery shops will crowd in, with an increase in both intrinsic and extrinsic motivations, and intrinsic motivations remaining the dominant factor. H3c: Mystery shoppers who have performed 25 or more mystery shops will crowd in, with an increase in both intrinsic and extrinsic motivations, but extrinsic motivations becoming the dominant factor. Results supported motivation crowding as dependent on the experience level of the mystery shopper, prompting the categorization of three distinct mystery shopping phases of activity: the novelty phase, the exploratory phase, and the career phase. Empirical results of the survey were then compared to a subsequent round of qualitative analysis of mystery shopper online forums. Recommendations for future research include longitudinal studies of novelty phase mystery shoppers, examination of the effects motivation crowding may have on mystery shopper behavioral intentions, and incorporation of the perceived costs associated with mystery shopping.
Show less - Date Issued
- 2009
- Identifier
- CFE0002588, ucf:48290
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0002588
- Title
- ON THE INCORPORATION OF THE PERSONALITY FACTORS INTO CROWD SIMULATION.
- Creator
-
Jaganathan, Sivakumar, Kincaid, J. Peter, University of Central Florida
- Abstract / Description
-
Recently, a considerable amount of research has been performed on simulating the collective behavior of pedestrians in the street or people finding their way inside a building or a room. Comprehensive reviews of the state of the art can be found in Schreckenberg and Deo (2002) and Batty, M., DeSyllas, J. and Duxbury, E. (2003). In all these simulation studies, one area that is lacking is accounting for the effects of human personalities on the outcome. As a result, there is a growing emphasis...
Show moreRecently, a considerable amount of research has been performed on simulating the collective behavior of pedestrians in the street or people finding their way inside a building or a room. Comprehensive reviews of the state of the art can be found in Schreckenberg and Deo (2002) and Batty, M., DeSyllas, J. and Duxbury, E. (2003). In all these simulation studies, one area that is lacking is accounting for the effects of human personalities on the outcome. As a result, there is a growing emphasis on researching the effects of human personalities and adding the results to the simulations to make them more realistic. This research investigated the possibility of incorporating personality factors into the crowd simulation model. The first part of this study explored the extraction of quantitative crowd motion from videos and developed a method to compare real video with the simulation output video. Several open source programs were examined and modified to obtain optical flow measurements from real videos captured at sporting events. Optical flow measurements provide information such as crowd density, average velocity with which individuals move in the crowd, as well as other parameters. These quantifiable optical flow calculations provided a strong method for comparing simulation results with those obtained from video footage captured in real life situations. The second part of the research focused on the incorporation of the personality factors into the crowd simulation. Existing crowd models such as HelbingU-Molnár-Farkas-Vicsek (HMFV) do not take individual personality factors into account. The most common approach employed by psychologists for studying personality traits is the Big Five factors or dimensions of personality (NEO: Neuroticism, Extroversion, Openness, Agreeableness and Conscientiousness). iii In this research forces related to the personality factors were incorporated into the crowd simulation models. The NEO-based forces were incorporated into an existing HMFV simulated implemented in the MASON simulation framework. The simulation results were validated using the quantification procedures developed in the first phase. This research reports on a major expansion of a simulation of pedestrian motion based on the model (HMFV) by Helbing, D., I. J. Farkas, P. Molnár, and T. Vicsek (2002). Example of actual behavior such as a crowd exiting church after service were simulated using NEO-based forces and show a striking resemblance to actual behavior as rated by behavior scientists.
Show less - Date Issued
- 2007
- Identifier
- CFE0001771, ucf:47276
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0001771
- Title
- EXAMINING CROWD VIOLENCE CONNECTED TO SPORT APPLYINGTHE HOOLIGAN TEMPLATE.
- Creator
-
Worthen, Kelly, Donley, Amy, University of Central Florida
- Abstract / Description
-
ABSTRACT The aim of the research is to evaluate crowd violence as it pertains to sports and its spectators. In particular, the research examines sports riots. "A sports riot is defined as violence-vandalism, throwing/shooting missiles, rushing the field or court, committing arson, and/or fighting- committed by five or more individuals in a crowd of one hundred people associated with a formally organized sporting event" (Lewis, 2007). On a micro level, the most prevalent form of spectator...
Show moreABSTRACT The aim of the research is to evaluate crowd violence as it pertains to sports and its spectators. In particular, the research examines sports riots. "A sports riot is defined as violence-vandalism, throwing/shooting missiles, rushing the field or court, committing arson, and/or fighting- committed by five or more individuals in a crowd of one hundred people associated with a formally organized sporting event" (Lewis, 2007). On a micro level, the most prevalent form of spectator violence is the act of Hooliganism in relation to football (soccer). The research on this aggression has been primarily inherent in Europe and South and Central America in concert with soccer matches. One of the goals of the research is to see if this unique type violence has the potential to occur in North America when comparing it to Europe and more specifically the United Kingdom. Currently, the average Major League Soccer (MLS) teams are capturing slightly higher attendance numbers than the NBA and the NHL. In the 2010-11 season, the average MLS attendance was 17,869, compared to 17,319 and 17,126 respectively (ESPN.com, 2011). With the expansion and globalization of the sport when traveling groups from Europe and South/Central America play United States teams (municipalities or the National team) in a "friendly" (exhibition match) or a World Cup qualifiers stateside, it is understood that supporter firms (hooligan gangs) will travel to support their team. Are hooligans simply looking for a violent result under the guise of being football supporters? "It's a lot more widespread than the general public realize. They might hear of one or two big incidences a year. But this thing happens week in week out at different grounds around England" (Hooligans: No one likes us, 2002). Collective behavior is the most apparent theoretic way to view these outbursts. This research however will examine this social phenomenon through symbolic interaction perspective as well. The hooligan culture is embedded with symbols of social disorder and rebellion. Racism, xenophobia homophobia and even patriotism are the tent poles of this social phenomenon. Additionally, from firm (gang) to firm (gang), socially constructed deviance such as rival history, improper police conduct, the media and alcohol are overarching factors. The final facet of the research examines how to curb the violence. Since Hooliganism is surprisingly tactical in and of itself, how authorities can potentially identify trouble makers and anticipate violence will be assessed. Since the English have customarily been deemed by the international community as some of the worst cohort participants, the tactics that authorities abroad have utilized (successful and otherwise) will be evaluated. Recommendations to prevent and combat this problem will be made in the hopes that a proactive approach can be developed domestically.
Show less - Date Issued
- 2012
- Identifier
- CFH0004220, ucf:44936
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFH0004220
- Title
- DEMOGRAPHIC CONSEQUENCES OF MANAGING FOR FLORIDA SCRUB-JAYS (APHELOCOMA COERULESCENS) ON AN ISOLATED PRESERVE.
- Creator
-
Lyon, Casey, Stout, I. Jack, University of Central Florida
- Abstract / Description
-
Many species naturally occupy discrete habitat patches within a mosaic of habitats that vary in quality. The Florida scrub-jay (Aphelocoma coerulescens) is endemic to Florida scrub, a habitat that is naturally patchy and greatly reduced in area over recent decades owing to development and urbanization. Because of this habitat loss, future management of Florida scrub-jays will focus on smaller, fragmented tracts of land. My study examines such a tract, Lyonia Preserve, southwest Volusia County...
Show moreMany species naturally occupy discrete habitat patches within a mosaic of habitats that vary in quality. The Florida scrub-jay (Aphelocoma coerulescens) is endemic to Florida scrub, a habitat that is naturally patchy and greatly reduced in area over recent decades owing to development and urbanization. Because of this habitat loss, future management of Florida scrub-jays will focus on smaller, fragmented tracts of land. My study examines such a tract, Lyonia Preserve, southwest Volusia County, FL. This preserve was unoccupied by scrub-jays prior to habitat restoration. The preserve is now frequently managed exclusively for scrub-jays as a habitat island surrounded by development. Management of the preserve includes roller chopping, root raking, timbering, and "oak stripping" where islands of oak patches are left intact while the rest of the area is roller chopped. I investigate what, if any, demographic consequences may be associated with the habitat management and the spatial setting of the preserve. I used population data collected in this area since 1992 to examine population growth and responses to habitat restoration within the preserve and habitat destruction outside the preserve. I mapped territories and measured survival and recruitment of scrub-jays, and dispersal into and out of the study area, for two and a half years. Since restoration, the population has shown logistic growth, with the area supporting higher than average densities of scrub-jay family groups. Observed density of the population and territory size varied between study years. Breeder survival values were positively related to territory size and significantly lower during periods of highest observed density. However, recruitment (yearling production) showed no relationship to territory size. Dispersal to isolated habitat patches was observed; likewise, several failed dispersal events were noted. No immigration into the study area was observed; however these data may be underrepresented since not all scrub-jays in and outside of the preserve were banded, and data collection was limited during the initial colonization period. High densities inside the preserve may therefore be both a result of frequent habitat management in the form of mechanical treatment as well as crowding of individuals due to outside habitat destruction. The results indicate that carrying capacity of habitat for scrub-jays may be raised by frequent, mechanical management; however, if the area is isolated, management may result in high densities and negative demographic consequences, e.g., reduced breeder survival. Negative effects of management may be avoided by subjecting smaller areas to mechanical treatment with increased time between treatments. Land managed for Florida scrub-jays should be contiguous or connected with other scrub habitats so that surplus birds from the managed areas have a refuge and do not contribute to increased densities. Regulatory officials should use caution when allowing for "take" of scrub-jay habitat as the effects may extend beyond the local habitat being destroyed.
Show less - Date Issued
- 2007
- Identifier
- CFE0001769, ucf:47280
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0001769
- Title
- TOWARDS CALIBRATION OF OPTICAL FLOW OF CROWD VIDEOS USING OBSERVED TRAJECTORIES.
- Creator
-
Elbadramany, Iman, Kaup, David, University of Central Florida
- Abstract / Description
-
The need exists for finding a quantitative method for validating crowd simulations. One approach is to use optical flow of videos of real crowds to obtain velocities that can be used for comparison to simulations. Optical flow, in turn, needs to be calibrated to be useful. It is essential to show that optical flow velocities obtained from crowd videos can be mapped into the spatially averaged velocities of the observed trajectories of crowd members, and to quantify the extent of the...
Show moreThe need exists for finding a quantitative method for validating crowd simulations. One approach is to use optical flow of videos of real crowds to obtain velocities that can be used for comparison to simulations. Optical flow, in turn, needs to be calibrated to be useful. It is essential to show that optical flow velocities obtained from crowd videos can be mapped into the spatially averaged velocities of the observed trajectories of crowd members, and to quantify the extent of the correlation of the results. This research investigates methods to uncover the best conditions for a good correlation between optical flow and the average motion of individuals in crowd videos, with the aim that this will help in the quantitative validation of simulations. The first approach was to use a simple linear proportionality relation, with a single coefficient, alpha, between velocity vector of the optical flow and observed velocity of crowd members in a video or simulation. Since there are many variables that affect alpha, an attempt was made to find the best possible conditions for determining alpha, by varying experimental and optical flow settings. The measure of a good alpha was chosen to be that alpha does not vary excessively over a number of video frames. Best conditions of low coefficient of variation of alpha using the Lucas-Kanade optical flow algorithm were found to be when a larger aperture of 15x15 pixels was used, combined with a smaller threshold. Adequate results were found at cell size 40x40 pixels; the improvement in detecting details when smaller cells are used did not reduce the variability of alpha, and required much more computing power. Reduction in variability of alpha can be obtained by spreading the tracked location of a crowd member from a pixel into a rectangle. The Particle Image Velocimetry optical flow algorithm had better correspondence with the velocity vectors of manually tracked crowd members than results obtained using the Lukas-Kanade method. Here, also, it was found that 40x40 pixel cells were better than 15x15. A second attempt at quantifying the correlation between optical flow and actual crowd member velocities was studied using simulations. Two processes were researched, which utilized geometrical correction of the perspective distortion of the crowd videos. One process geometrically corrects the video, and then obtains optical flow data. The other obtains optical flow data from video, and then geometrically corrects the data. The results indicate that the first process worked better. Correlation was calculated between sets of data obtained from the average of twenty frames. This was found to be higher than calculating correlations between the velocities of cells in each pair of frames. An experiment was carried out to predict crowd tracks using optical flow and a calculated parameter, beta, seems to give promising results.
Show less - Date Issued
- 2011
- Identifier
- CFE0004024, ucf:49175
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0004024
- Title
- Holistic Representations for Activities and Crowd Behaviors.
- Creator
-
Solmaz, Berkan, Shah, Mubarak, Da Vitoria Lobo, Niels, Jha, Sumit, Ilie, Marcel, Moore, Brian, University of Central Florida
- Abstract / Description
-
In this dissertation, we address the problem of analyzing the activities of people in a variety of scenarios, this is commonly encountered in vision applications. The overarching goal is to devise new representations for the activities, in settings where individuals or a number of people may take a part in specific activities. Different types of activities can be performed by either an individual at the fine level or by several people constituting a crowd at the coarse level. We take into...
Show moreIn this dissertation, we address the problem of analyzing the activities of people in a variety of scenarios, this is commonly encountered in vision applications. The overarching goal is to devise new representations for the activities, in settings where individuals or a number of people may take a part in specific activities. Different types of activities can be performed by either an individual at the fine level or by several people constituting a crowd at the coarse level. We take into account the domain specific information for modeling these activities. The summary of the proposed solutions is presented in the following.The holistic description of videos is appealing for visual detection and classification tasks for several reasons including capturing the spatial relations between the scene components, simplicity, and performance [1, 2, 3]. First, we present a holistic (global) frequency spectrum based descriptor for representing the atomic actions performed by individuals such as: bench pressing, diving, hand waving, boxing, playing guitar, mixing, jumping, horse riding, hula hooping etc. We model and learn these individual actions for classifying complex user uploaded videos. Our method bypasses the detection of interest points, the extraction of local video descriptors and the quantization of local descriptors into a code book; it represents each video sequence as a single feature vector. This holistic feature vector is computed by applying a bank of 3-D spatio-temporal filters on the frequency spectrum of a video sequence; hence it integrates the information about the motion and scene structure. We tested our approach on two of the most challenging datasets, UCF50 [4] and HMDB51 [5], and obtained promising results which demonstrates the robustness and the discriminative power of our holistic video descriptor for classifying videos of various realistic actions.In the above approach, a holistic feature vector of a video clip is acquired by dividing the video into spatio-temporal blocks then concatenating the features of the individual blocks together. However, such a holistic representation blindly incorporates all the video regions regardless of their contribution in classification. Next, we present an approach which improves the performance of the holistic descriptors for activity recognition. In our novel method, we improve the holistic descriptors by discovering the discriminative video blocks. We measure the discriminativity of a block by examining its response to a pre-learned support vector machine model. In particular, a block is considered discriminative if it responds positively for positive training samples, and negatively for negative training samples. We pose the problem of finding the optimal blocks as a problem of selecting a sparse set of blocks, which maximizes the total classifier discriminativity. Through a detailed set of experiments on benchmark datasets [6, 7, 8, 9, 5, 10], we show that our method discovers the useful regions in the videos and eliminates the ones which are confusing for classification, which results in significant performance improvement over the state-of-the-art.In contrast to the scenes where an individual performs a primitive action, there may be scenes with several people, where crowd behaviors may take place. For these types of scenes the traditional approaches for recognition will not work due to severe occlusion and computational requirements. The number of videos is limited and the scenes are complicated, hence learning these behaviors is not feasible. For this problem, we present a novel approach, based on the optical flow in a video sequence, for identifying five specific and common crowd behaviors in visual scenes. In the algorithm, the scene is overlaid by a grid of particles, initializing a dynamical system which is derived from the optical flow. Numerical integration of the optical flow provides particle trajectories that represent the motion in the scene. Linearization of the dynamical system allows a simple and practical analysis and classification of the behavior through the Jacobian matrix. Essentially, the eigenvalues of this matrix are used to determine the dynamic stability of points in the flow and each type of stability corresponds to one of the five crowd behaviors. The identified crowd behaviors are (1) bottlenecks: where many pedestrians/vehicles from various points in the scene are entering through one narrow passage, (2) fountainheads: where many pedestrians/vehicles are emerging from a narrow passage only to separate in many directions, (3) lanes: where many pedestrians/vehicles are moving at the same speeds in the same direction, (4) arches or rings: where the collective motion is curved or circular, and (5) blocking: where there is a opposing motion and desired movement of groups of pedestrians is somehow prohibited. The implementation requires identifying a region of interest in the scene, and checking the eigenvalues of the Jacobian matrix in that region to determine the type of flow, that corresponds to various well-defined crowd behaviors. The eigenvalues are only considered in these regions of interest, consistent with the linear approximation and the implied behaviors. Since changes in eigenvalues can mean changes in stability, corresponding to changes in behavior, we can repeat the algorithm over clips of long video sequences to locate changes in behavior. This method was tested on over real videos representing crowd and traffic scenes.
Show less - Date Issued
- 2013
- Identifier
- CFE0004941, ucf:49638
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0004941
- Title
- Load Estimation, Structural Identification and Human Comfort Assessment of Flexible Structures.
- Creator
-
Celik, Ozan, Catbas, Necati, Yun, Hae-Bum, Makris, Nicos, Kauffman, Jeffrey L., University of Central Florida
- Abstract / Description
-
Stadiums, pedestrian bridges, dance floors, and concert halls are distinct from other civil engineering structures due to several challenges in their design and dynamic behavior. These challenges originate from the flexible inherent nature of these structures coupled with human interactions in the form of loading. The investigations in past literature on this topic clearly state that the design of flexible structures can be improved with better load modeling strategies acquired with reliable...
Show moreStadiums, pedestrian bridges, dance floors, and concert halls are distinct from other civil engineering structures due to several challenges in their design and dynamic behavior. These challenges originate from the flexible inherent nature of these structures coupled with human interactions in the form of loading. The investigations in past literature on this topic clearly state that the design of flexible structures can be improved with better load modeling strategies acquired with reliable load quantification, a deeper understanding of structural response, generation of simple and efficient human-structure interaction models and new measurement and assessment criteria for acceptable vibration levels. In contribution to these possible improvements, this dissertation taps into three specific areas: the load quantification of lively individuals or crowds, the structural identification under non-stationary and narrowband disturbances and the measurement of excessive vibration levels for human comfort. For load quantification, a computer vision based approach capable of tracking both individual and crowd motion is used. For structural identification, a noise-assisted Multivariate Empirical Mode Decomposition (MEMD) algorithm is incorporated into the operational modal analysis. The measurement of excessive vibration levels and the assessment of human comfort are accomplished through computer vision based human and object tracking, which provides a more convenient means for measurement and computation. All the proposed methods are tested in the laboratory environment utilizing a grandstand simulator and in the field on a pedestrian bridge and on a football stadium. Findings and interpretations from the experimental results are presented. The dissertation is concluded by highlighting the critical findings and the possible future work that may be conducted.
Show less - Date Issued
- 2017
- Identifier
- CFE0006863, ucf:51752
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0006863
- Title
- Towards Improving Human-Robot Interaction For Social Robots.
- Creator
-
Khan, Saad, Boloni, Ladislau, Behal, Aman, Sukthankar, Gita, Garibay, Ivan, Fiore, Stephen, University of Central Florida
- Abstract / Description
-
Autonomous robots interacting with humans in a social setting must consider the social-cultural environment when pursuing their objectives. Thus the social robot must perceive and understand the social cultural environment in order to be able to explain and predict the actions of its human interaction partners. This dissertation contributes to the emerging field of human-robot interaction for social robots in the following ways: 1. We used the social calculus technique based on culture...
Show moreAutonomous robots interacting with humans in a social setting must consider the social-cultural environment when pursuing their objectives. Thus the social robot must perceive and understand the social cultural environment in order to be able to explain and predict the actions of its human interaction partners. This dissertation contributes to the emerging field of human-robot interaction for social robots in the following ways: 1. We used the social calculus technique based on culture sanctioned social metrics (CSSMs) to quantify, analyze and predict the behavior of the robot, human soldiers and the public perception in the Market Patrol peacekeeping scenario. 2. We validated the results of the Market Patrol scenario by comparing the predicted values with the judgment of a large group of human observers cognizant of the modeled culture. 3. We modeled the movement of a socially aware mobile robot in a dense crowds, using the concept of a micro-conflict to represent the challenge of giving or not giving way to pedestrians. 4. We developed an approach for the robot behavior in micro-conflicts based on the psychological observation that human opponents will use a consistent strategy. For this, the mobile robot classifies the opponent strategy reflected by the personality and social status of the person and chooses an appropriate counter-strategy that takes into account the urgency of the robots' mission. 5. We developed an alternative approach for the resolution of micro-conflicts based on the imitation of the behavior of the human agent. This approach aims to make the behavior of an autonomous robot closely resemble that of a remotely operated one.
Show less - Date Issued
- 2015
- Identifier
- CFE0005965, ucf:50819
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0005965
- Title
- Analysis of Behaviors in Crowd Videos.
- Creator
-
Mehran, Ramin, Shah, Mubarak, Sukthankar, Gita, Behal, Aman, Tappen, Marshall, Moore, Brian, University of Central Florida
- Abstract / Description
-
In this dissertation, we address the problem of discovery and representation of group activity of humans and objects in a variety of scenarios, commonly encountered in vision applications. The overarching goal is to devise a discriminative representation of human motion in social settings, which captures a wide variety of human activities observable in video sequences. Such motion emerges from the collective behavior of individuals and their interactions and is a significant source of...
Show moreIn this dissertation, we address the problem of discovery and representation of group activity of humans and objects in a variety of scenarios, commonly encountered in vision applications. The overarching goal is to devise a discriminative representation of human motion in social settings, which captures a wide variety of human activities observable in video sequences. Such motion emerges from the collective behavior of individuals and their interactions and is a significant source of information typically employed for applications such as event detection, behavior recognition, and activity recognition. We present new representations of human group motion for static cameras, and propose algorithms for their application to variety of problems.We first propose a method to model and learn the scene activity of a crowd using Social Force Model for the first time in the computer vision community. We present a method to densely estimate the interaction forces between people in a crowd, observed by a static camera. Latent Dirichlet Allocation (LDA) is used to learn the model of the normal activities over extended periods of time. Randomly selected spatio-temporal volumes of interaction forces are used to learn the model of normal behavior of the scene. The model encodes the latent topics of social interaction forces in the scene for normal behaviors. We classify a short video sequence of $n$ frames as normal or abnormal by using the learnt model. Once a sequence of frames is classified as an abnormal, the regions of anomalies in the abnormal frames are localized using the magnitude of interaction forces.The representation and estimation framework proposed above, however, has a few limitations. This algorithm proposes to use a global estimation of the interaction forces within the crowd. It, therefore, is incapable of identifying different groups of objects based on motion or behavior in the scene. Although the algorithm is capable of learning the normal behavior and detects the abnormality, but it is incapable of capturing the dynamics of different behaviors.To overcome these limitations, we then propose a method based on the Lagrangian framework for fluid dynamics, by introducing a streakline representation of flow. Streaklines are traced in a fluid flow by injecting color material, such as smoke or dye, which is transported with the flow and used for visualization. In the context of computer vision, streaklines may be used in a similar way to transport information about a scene, and they are obtained by repeatedly initializing a fixed grid of particles at each frame, then moving both current and past particles using optical flow. Streaklines are the locus of points that connect particles which originated from the same initial position.This approach is advantageous over the previous representations in two aspects: first, its rich representation captures the dynamics of the crowd and changes in space and time in the scene where the optical flow representation is not enough, and second, this model is capable of discovering groups of similar behavior within a crowd scene by performing motion segmentation. We propose a method to distinguish different group behaviors such as divergent/convergent motion and lanes using this framework. Finally, we introduce flow potentials as a discriminative feature to recognize crowd behaviors in a scene. Results of extensive experiments are presented for multiple real life crowd sequences involving pedestrian and vehicular traffic.The proposed method exploits optical flow as the low level feature and performs integration and clustering to obtain coherent group motion patterns. However, we observe that in crowd video sequences, as well as a variety of other vision applications, the co-occurrence and inter-relation of motion patterns are the main characteristics of group behaviors. In other words, the group behavior of objects is a mixture of individual actions or behaviors in specific geometrical layout and temporal order.We, therefore, propose a new representation for group behaviors of humans using the inter-relation of motion patterns in a scene. The representation is based on bag of visual phrases of spatio-temporal visual words. We present a method to match the high-order spatial layout of visual words that preserve the geometry of the visual words under similarity transformations. To perform the experiments we collected a dataset of group choreography performances from the YouTube website. The dataset currently contains four categories of group dances.
Show less - Date Issued
- 2011
- Identifier
- CFE0004482, ucf:49317
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0004482
- Title
- Headquarters of Vincent Collyer, Superintendent of the poor at New Berne, N.C: Distribution of captured confederate clothing to the contrabands..
- Date Created
- 1861
- Identifier
- DP0012811
- Format
- Set of related objects
- PURL
- http://purl.flvc.org/ucf/fd/DP0012811
- Title
- BRAVE NEW WORLD RELOADED: ADVOCATING FOR BASIC CONSTITUTIONAL SEARCH PROTECTIONS TO APPLY TO CELL PHONES FROM EAVESDROPPING AND TRACKING BY THE GOVERNMENT AND CORPORATE ENTITIES.
- Creator
-
Berrios-Ayala, Mark, Milon, Abby, University of Central Florida
- Abstract / Description
-
Imagine a world where someone's personal information is constantly compromised, where federal government entities AKA Big Brother always knows what anyone is Googling, who an individual is texting, and their emoticons on Twitter. Government entities have been doing this for years; they never cared if they were breaking the law or their moral compass of human dignity. Every day the Federal government blatantly siphons data with programs from the original ECHELON to the new series like PRISM...
Show moreImagine a world where someone's personal information is constantly compromised, where federal government entities AKA Big Brother always knows what anyone is Googling, who an individual is texting, and their emoticons on Twitter. Government entities have been doing this for years; they never cared if they were breaking the law or their moral compass of human dignity. Every day the Federal government blatantly siphons data with programs from the original ECHELON to the new series like PRISM and Xkeyscore so they can keep their tabs on issues that are none of their business; namely, the personal lives of millions. Our allies are taking note; some are learning our bad habits, from Government Communications Headquarters' (GCHQ) mass shadowing sharing plan to America's Russian inspiration, SORM. Some countries are following the United States' poster child pose of a Brave New World like order of global events. Others like Germany are showing their resolve in their disdain for the rise of tyranny. Soon, these new found surveillance troubles will test the resolve of the American Constitution and its nation's strong love and tradition of liberty. Courts are currently at work to resolve how current concepts of liberty and privacy apply to the current conditions facing the privacy of society. It remains to be determined how liberty will be affected as well; liberty for the United States of America, for the European Union, the Russian Federation and for the people of the World in regards to the extent of privacy in today's blurred privacy expectations.
Show less - Date Issued
- 2014
- Identifier
- CFH0004537, ucf:45187
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFH0004537
