View All Items
(1 - 5 of 5)
- Title
- FEATURE PRUNING FOR ACTION RECOGNITION IN COMPLEX ENVIRONMENT.
- Creator
-
Nagaraja, Adarsh, Tappen, Marshall, University of Central Florida
- Abstract / Description
-
A significant number of action recognition research efforts use spatio-temporal interest point detectors for feature extraction. Although the extracted features provide useful information for recognizing actions, a significant number of them contain irrelevant motion and background clutter. In many cases, the extracted features are included as is in the classification pipeline, and sophisticated noise removal techniques are subsequently used to alleviate their effect on classification. We...
Show moreA significant number of action recognition research efforts use spatio-temporal interest point detectors for feature extraction. Although the extracted features provide useful information for recognizing actions, a significant number of them contain irrelevant motion and background clutter. In many cases, the extracted features are included as is in the classification pipeline, and sophisticated noise removal techniques are subsequently used to alleviate their effect on classification. We introduce a new action database, created from the Weizmann database, that reveals a significant weakness in systems based on popular cuboid descriptors. Experiments show that introducing complex backgrounds, stationary or dynamic, into the video causes a significant degradation in recognition performance. Moreover, this degradation cannot be fixed by fine-tuning the system or selecting better interest points. Instead, we show that the problem lies at the descriptor level and must be addressed by modifying descriptors.
Show less - Date Issued
- 2011
- Identifier
- CFE0003882, ucf:48721
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0003882
- Title
- DEGREE OF APROXIMATION OF HÖLDER CONTINUOUS FUNCTIONS.
- Creator
-
Landon, Benjamin, Mohapatra, Ram, University of Central Florida
- Abstract / Description
-
Pratima Sadangi in a Ph.D. thesis submitted to Utkal University proved results on degree of approximation of functions by operators associated with their Fourier series. In this dissertation, we consider degree of approximation of functions in H_(α,p) by different operators. In Chapter 1 we mention basic definitions needed for our work. In Chapter 2 we discuss different methods of summation. In Chapter 3 we define the H_(α,p) metric and present the degree of approximation problem...
Show morePratima Sadangi in a Ph.D. thesis submitted to Utkal University proved results on degree of approximation of functions by operators associated with their Fourier series. In this dissertation, we consider degree of approximation of functions in H_(α,p) by different operators. In Chapter 1 we mention basic definitions needed for our work. In Chapter 2 we discuss different methods of summation. In Chapter 3 we define the H_(α,p) metric and present the degree of approximation problem relating to Fourier series and conjugate series of functions in the H_(α,p) metric using Karamata (K^λ) means. In Chapter 4 we present the degree of approximation of an integral associated with the conjugate series by the Euler, Borel and (e,c) means of a series analogous to the Hardy-Littlewood series in the H_(α,p) metric. In Chapter 5 we propose problems to be solved in the future.
Show less - Date Issued
- 2008
- Identifier
- CFE0002414, ucf:47730
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0002414
- Title
- IDENTIFICATION OF SPATIOTEMPORAL NUTRIENT PATTERNS AND ASSOCIATED ECOHYDROLOGICAL TRENDS IN THE TAMPA BAY COASTAL REGION.
- Creator
-
Wimberly, Brent, Chang, Ni-Bin, University of Central Florida
- Abstract / Description
-
The comprehensive assessment techniques for monitoring of water quality of a coastal bay can be diversified via an extensive investigation of the spatiotemporal nutrient patterns and the associated eco-hydrological trends in a coastal urban region. With this work, it is intended to thoroughly investigate the spatiotemporal nutrient patterns and associated eco-hydrological trends via a two part inquiry of the watershed and its adjacent coastal bay. The findings show that the onset of drought...
Show moreThe comprehensive assessment techniques for monitoring of water quality of a coastal bay can be diversified via an extensive investigation of the spatiotemporal nutrient patterns and the associated eco-hydrological trends in a coastal urban region. With this work, it is intended to thoroughly investigate the spatiotemporal nutrient patterns and associated eco-hydrological trends via a two part inquiry of the watershed and its adjacent coastal bay. The findings show that the onset of drought lags the crest of the evapotranspiration and precipitation curve during each year of drought. During the transition year, ET and precipitation appears to start to shift back into the analogous temporal pattern as the 2005 wet year. NDVI shows a flat receding tail for the September crest in 2005 due to the hurricane impact signifying that the hurricane event in October dampening the severity of the winter dry season in which alludes to relative system memory. The k-means model with 8 clusters is the optimal choice, in which cluster 2 at Lower Tampa Bay had the minimum values of total nitrogen (TN) concentrations, chlorophyll a (Chl-a) concentrations, and ocean color values in every season as well as the minimum concentration of total phosphorus (TP) in three consecutive seasons in 2008. Cluster 5, located in Middle Tampa Bay, displayed elevated TN concentrations, ocean color values, and Chl-a concentrations, suggesting that high colored dissolved organic matter values are linked with some nutrient sources. The data presented by the gravity modeling analysis indicate that the Alafia River Basin is the major contributor of nutrients in terms of both TP and TN values in all seasons. Such ecohydrological evaluation can be applied for supporting the LULC management of climatic vulnerable regions as well as further enrich the comprehensive assessment techniques for estimating and examining the multi-temporal impacts and dynamic influence of urban land use and land cover. Improvements for environmental monitoring and assessment were achieved to advance our understanding of sea-land interactions and nutrient cycling in a coastal bay.
Show less - Date Issued
- 2012
- Identifier
- CFH0004132, ucf:44878
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFH0004132
- Title
- CONTEXTUALIZING OBSERVATIONAL DATA FOR MODELING HUMAN PERFORMANCE.
- Creator
-
Trinh, Viet, Gonzalez, Avelino, University of Central Florida
- Abstract / Description
-
This research focuses on the ability to contextualize observed human behaviors in efforts to automate the process of tactical human performance modeling through learning from observations. This effort to contextualize human behavior is aimed at minimizing the role and involvement of the knowledge engineers required in building intelligent Context-based Reasoning (CxBR) agents. More specifically, the goal is to automatically discover the context in which a human actor is situated when...
Show moreThis research focuses on the ability to contextualize observed human behaviors in efforts to automate the process of tactical human performance modeling through learning from observations. This effort to contextualize human behavior is aimed at minimizing the role and involvement of the knowledge engineers required in building intelligent Context-based Reasoning (CxBR) agents. More specifically, the goal is to automatically discover the context in which a human actor is situated when performing a mission to facilitate the learning of such CxBR models. This research is derived from the contextualization problem left behind in Fernlund's research on using the Genetic Context Learner (GenCL) to model CxBR agents from observed human performance [Fernlund, 2004]. To accomplish the process of context discovery, this research proposes two contextualization algorithms: Contextualized Fuzzy ART (CFA) and Context Partitioning and Clustering (COPAC). The former is a more naive approach utilizing the well known Fuzzy ART strategy while the latter is a robust algorithm developed on the principles of CxBR. Using Fernlund's original five drivers, the CFA and COPAC algorithms were tested and evaluated on their ability to effectively contextualize each driver's individualized set of behaviors into well-formed and meaningful context bases as well as generating high-fidelity agents through the integration with Fernlund's GenCL algorithm. The resultant set of agents was able to capture and generalized each driver's individualized behaviors.
Show less - Date Issued
- 2009
- Identifier
- CFE0002563, ucf:48253
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0002563
- Title
- PATTERNS OF MOTION: DISCOVERY AND GENERALIZED REPRESENTATION.
- Creator
-
Saleemi, Imran, Shah, Mubarak, University of Central Florida
- Abstract / Description
-
In this dissertation, we address the problem of discovery and representation of motion patterns in a variety of scenarios, commonly encountered in vision applications. The overarching goal is to devise a generic representation, that captures any kind of object motion observable in video sequences. Such motion is a significant source of information typically employed for diverse applications such as tracking, anomaly detection, and action and event recognition. We present statistical...
Show moreIn this dissertation, we address the problem of discovery and representation of motion patterns in a variety of scenarios, commonly encountered in vision applications. The overarching goal is to devise a generic representation, that captures any kind of object motion observable in video sequences. Such motion is a significant source of information typically employed for diverse applications such as tracking, anomaly detection, and action and event recognition. We present statistical frameworks for representation of motion characteristics of objects, learned from tracks or optical flow, for static as well as moving cameras, and propose algorithms for their application to a variety of problems. The proposed motion pattern models and learning methods are general enough to be employed in a variety of problems as we demonstrate experimentally. We first propose a novel method to model and learn the scene activity, observed by a static camera. The motion patterns of objects in the scene are modeled in the form of a multivariate non-parametric probability density function of spatiotemporal variables (object locations and transition times between them). Kernel Density Estimation (KDE) is used to learn this model in a completely unsupervised fashion. Learning is accomplished by observing the trajectories of objects by a static camera over extended periods of time. The model encodes the probabilistic nature of the behavior of moving objects in the scene and is useful for activity analysis applications, such as persistent tracking and anomalous motion detection. In addition, the model also captures salient scene features, such as, the areas of occlusion and most likely paths. Once the model is learned, we use a unified Markov Chain Monte-Carlo (MCMC) based framework for generating the most likely paths in the scene, improving foreground detection, persistent labelling of objects during tracking and deciding whether a given trajectory represents an anomaly to the observed motion patterns. Experiments with real world videos are reported which validate the proposed approach. The representation and estimation framework proposed above, however, has a few limitations. This algorithm proposes to use a single global statistical distribution to represent all kinds of motion observed in a particular scene. It therefore, does not find a separation between multiple semantically distinct motion patterns in the scene. Instead, the learned model is a joint distribution over all possible patterns followed by objects. To overcome this limitation, we then propose a superior method for the discovery and statistical representation of motion patterns in a scene. The advantages of this approach over the first one are two-fold: first, this model is applicable to scenes of dense crowded motion where tracking may not be feasible, and second, it distinguishes between motion patterns that are distinct at a semantic level of abstraction. We propose a mixture model representation of salient patterns of optical flow, and present an algorithm for learning these patterns from dense optical flow in a hierarchical, unsupervised fashion. Using low level cues of noisy optical flow, K-means is employed to initialize a Gaussian mixture model for temporally segmented clips of video. The components of this mixture are then filtered and instances of motion patterns are computed using a simple motion model, by linking components across space and time. Motion patterns are then initialized and membership of instances in different motion patterns is established by using KL divergence between mixture distributions of pattern instances. Finally, a pixel level representation of motion patterns is proposed by deriving conditional expectation of optical flow. Results of extensive experiments are presented for multiple surveillance sequences containing numerous patterns involving both pedestrian and vehicular traffic. The proposed method exploits optical flow as the low level feature and performs a hierarchical clustering to obtain motion patterns; and we observe that the use of optical flow is also an integral part of a variety of other vision applications, for example, as features based representation of human actions. We, therefore, propose a new representation for articulated human actions using the motion patterns. The representation is based on hierarchical clustering of observed optical flow in four dimensional, spatial and motion flow space. The automatically discovered motion patterns, are the primitive actions, representative of flow at salient regions on the human body, much like trajectories of body joints, which are notoriously difficult to obtain automatically. The proposed method works in a completely unsupervised fashion, and in sharp contrast to state of the art representations like bag of video words, provides a truly semantically meaningful representation. Each primitive action depicts the most atomic sub-action, like left arm moving upwards, or right leg moving downward and leftward, and is represented by a mixture of four dimensional Gaussian distributions. A sequence of primitive actions are discovered in the test video, and labelled by computing the KL divergence between mixtures. The entire video sequence containing the human action, is thus reduced to a simple string, which is matched against similar strings of training videos to classify the action. The string matching is performed by global alignment, using the well-known Needleman-Wunsch algorithm. Experiments reported on multiple human actions data sets, confirm the validity, simplicity, and semantically meaningful nature of the proposed representation. Results obtained are encouraging and comparable to the state of the art.
Show less - Date Issued
- 2011
- Identifier
- CFE0003646, ucf:48836
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0003646
