Current Search: object detection (x)
View All Items
(1 - 9 of 9)
- Title
- DETECTING CURVED OBJECTS AGAINST CLUTTERED BACKGROUNDS.
- Creator
-
Prokaj, Jan, Lobo, Niels, University of Central Florida
- Abstract / Description
-
Detecting curved objects against cluttered backgrounds is a hard problem in computer vision. We present new low-level and mid-level features to function in these environments. The low-level features are fast to compute, because they employ an integral image approach, which makes them especially useful in real-time applications. The mid-level features are built from low-level features, and are optimized for curved object detection. The usefulness of these features is tested by designing an...
Show moreDetecting curved objects against cluttered backgrounds is a hard problem in computer vision. We present new low-level and mid-level features to function in these environments. The low-level features are fast to compute, because they employ an integral image approach, which makes them especially useful in real-time applications. The mid-level features are built from low-level features, and are optimized for curved object detection. The usefulness of these features is tested by designing an object detection algorithm using these features. Object detection is accomplished by transforming the mid-level features into weak classifiers, which then produce a strong classifier using AdaBoost. The resulting strong classifier is then tested on the problem of detecting heads with shoulders. On a database of over 500 images of people, cropped to contain head and shoulders, and with a diverse set of backgrounds, the detection rate is 90% while the false positive rate on a database of 500 negative images is less than 2%.
Show less - Date Issued
- 2008
- Identifier
- CFE0002102, ucf:47535
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0002102
- Title
- Human Detection, Tracking and Segmentation in Surveillance Video.
- Creator
-
Shu, Guang, Shah, Mubarak, Boloni, Ladislau, Wang, Jun, Lin, Mingjie, Sugaya, Kiminobu, University of Central Florida
- Abstract / Description
-
This dissertation addresses the problem of human detection and tracking in surveillance videos. Even though this is a well-explored topic, many challenges remain when confronted with data from real world situations. These challenges include appearance variation, illumination changes, camera motion, cluttered scenes and occlusion. In this dissertation several novel methods for improving on the current state of human detection and tracking based on learning scene-specific information in video...
Show moreThis dissertation addresses the problem of human detection and tracking in surveillance videos. Even though this is a well-explored topic, many challenges remain when confronted with data from real world situations. These challenges include appearance variation, illumination changes, camera motion, cluttered scenes and occlusion. In this dissertation several novel methods for improving on the current state of human detection and tracking based on learning scene-specific information in video feeds are proposed.Firstly, we propose a novel method for human detection which employs unsupervised learning and superpixel segmentation. The performance of generic human detectors is usually degraded in unconstrained video environments due to varying lighting conditions, backgrounds and camera viewpoints. To handle this problem, we employ an unsupervised learning framework that improves the detection performance of a generic detector when it is applied to a particular video. In our approach, a generic DPM human detector is employed to collect initial detection examples. These examples are segmented into superpixels and then represented using Bag-of-Words (BoW) framework. The superpixel-based BoW feature encodes useful color features of the scene, which provides additional information. Finally a new scene-specific classifier is trained using the BoW features extracted from the new examples. Compared to previous work, our method learns scene-specific information through superpixel-based features, hence it can avoid many false detections typically obtained by a generic detector. We are able to demonstrate a significant improvement in the performance of the state-of-the-art detector.Given robust human detection, we propose a robust multiple-human tracking framework using a part-based model. Human detection using part models has become quite popular, yet its extension in tracking has not been fully explored. Single camera-based multiple-person tracking is often hindered by difficulties such as occlusion and changes in appearance. We address such problems by developing an online-learning tracking-by-detection method. Our approach learns part-based person-specific Support Vector Machine (SVM) classifiers which capture articulations of moving human bodies with dynamically changing backgrounds. With the part-based model, our approach is able to handle partial occlusions in both the detection and the tracking stages. In the detection stage, we select the subset of parts which maximizes the probability of detection. This leads to a significant improvement in detection performance in cluttered scenes. In the tracking stage, we dynamically handle occlusions by distributing the score of the learned person classifier among its corresponding parts, which allows us to detect and predict partial occlusions and prevent the performance of the classifiers from being degraded. Extensive experiments using the proposed method on several challenging sequences demonstrate state-of-the-art performance in multiple-people tracking.Next, in order to obtain precise boundaries of humans, we propose a novel method for multiple human segmentation in videos by incorporating human detection and part-based detection potential into a multi-frame optimization framework. In the first stage, after obtaining the superpixel segmentation for each detection window, we separate superpixels corresponding to a human and background by minimizing an energy function using Conditional Random Field (CRF). We use the part detection potentials from the DPM detector, which provides useful information for human shape. In the second stage, the spatio-temporal constraints of the video is leveraged to build a tracklet-based Gaussian Mixture Model for each person, and the boundaries are smoothed by multi-frame graph optimization. Compared to previous work, our method could automatically segment multiple people in videos with accurate boundaries, and it is robust to camera motion. Experimental results show that our method achieves better segmentation performance than previous methods in terms of segmentation accuracy on several challenging video sequences.Most of the work in Computer Vision deals with point solution; a specific algorithm for a specific problem. However, putting different algorithms into one real world integrated system is a big challenge. Finally, we introduce an efficient tracking system, NONA, for high-definition surveillance video. We implement the system using a multi-threaded architecture (Intel Threading Building Blocks (TBB)), which executes video ingestion, tracking, and video output in parallel. To improve tracking accuracy without sacrificing efficiency, we employ several useful techniques. Adaptive Template Scaling is used to handle the scale change due to objects moving towards a camera. Incremental Searching and Local Frame Differencing are used to resolve challenging issues such as scale change, occlusion and cluttered backgrounds. We tested our tracking system on a high-definition video dataset and achieved acceptable tracking accuracy while maintaining real-time performance.
Show less - Date Issued
- 2014
- Identifier
- CFE0005551, ucf:50278
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0005551
- Title
- MULTI-VIEW APPROACHES TO TRACKING, 3D RECONSTRUCTION AND OBJECT CLASS DETECTION.
- Creator
-
khan, saad, Shah, Mubarak, University of Central Florida
- Abstract / Description
-
Multi-camera systems are becoming ubiquitous and have found application in a variety of domains including surveillance, immersive visualization, sports entertainment and movie special effects amongst others. From a computer vision perspective, the challenging task is how to most efficiently fuse information from multiple views in the absence of detailed calibration information and a minimum of human intervention. This thesis presents a new approach to fuse foreground likelihood information...
Show moreMulti-camera systems are becoming ubiquitous and have found application in a variety of domains including surveillance, immersive visualization, sports entertainment and movie special effects amongst others. From a computer vision perspective, the challenging task is how to most efficiently fuse information from multiple views in the absence of detailed calibration information and a minimum of human intervention. This thesis presents a new approach to fuse foreground likelihood information from multiple views onto a reference view without explicit processing in 3D space, thereby circumventing the need for complete calibration. Our approach uses a homographic occupancy constraint (HOC), which states that if a foreground pixel has a piercing point that is occupied by foreground object, then the pixel warps to foreground regions in every view under homographies induced by the reference plane, in effect using cameras as occupancy detectors. Using the HOC we are able to resolve occlusions and robustly determine ground plane localizations of the people in the scene. To find tracks we obtain ground localizations over a window of frames and stack them creating a space time volume. Regions belonging to the same person form contiguous spatio-temporal tracks that are clustered using a graph cuts segmentation approach. Second, we demonstrate that the HOC is equivalent to performing visual hull intersection in the image-plane, resulting in a cross-sectional slice of the object. The process is extended to multiple planes parallel to the reference plane in the framework of plane to plane homologies. Slices from multiple planes are accumulated and the 3D structure of the object is segmented out. Unlike other visual hull based approaches that use 3D constructs like visual cones, voxels or polygonal meshes requiring calibrated views, ours is purely-image based and uses only 2D constructs i.e. planar homographies between views. This feature also renders it conducive to graphics hardware acceleration. The current GPU implementation of our approach is capable of fusing 60 views (480x720 pixels) at the rate of 50 slices/second. We then present an extension of this approach to reconstructing non-rigid articulated objects from monocular video sequences. The basic premise is that due to motion of the object, scene occupancies are blurred out with non-occupancies in a manner analogous to motion blurred imagery. Using our HOC and a novel construct: the temporal occupancy point (TOP), we are able to fuse multiple views of non-rigid objects obtained from a monocular video sequence. The result is a set of blurred scene occupancy images in the corresponding views, where the values at each pixel correspond to the fraction of total time duration that the pixel observed an occupied scene location. We then use a motion de-blurring approach to de-blur the occupancy images and obtain the 3D structure of the non-rigid object. In the final part of this thesis, we present an object class detection method employing 3D models of rigid objects constructed using the above 3D reconstruction approach. Instead of using a complicated mechanism for relating multiple 2D training views, our approach establishes spatial connections between these views by mapping them directly to the surface of a 3D model. To generalize the model for object class detection, features from supplemental views (obtained from Google Image search) are also considered. Given a 2D test image, correspondences between the 3D feature model and the testing view are identified by matching the detected features. Based on the 3D locations of the corresponding features, several hypotheses of viewing planes can be made. The one with the highest confidence is then used to detect the object using feature location matching. Performance of the proposed method has been evaluated by using the PASCAL VOC challenge dataset and promising results are demonstrated.
Show less - Date Issued
- 2008
- Identifier
- CFE0002073, ucf:47593
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0002073
- Title
- Human Action Detection, Tracking and Segmentation in Videos.
- Creator
-
Tian, Yicong, Shah, Mubarak, Bagci, Ulas, Liu, Fei, Walker, John, University of Central Florida
- Abstract / Description
-
This dissertation addresses the problem of human action detection, human tracking and segmentation in videos. They are fundamental tasks in computer vision and are extremely challenging to solve in realistic videos. We first propose a novel approach for action detection by exploring the generalization of deformable part models from 2D images to 3D spatiotemporal volumes. By focusing on the most distinctive parts of each action, our models adapt to intra-class variation and show robustness to...
Show moreThis dissertation addresses the problem of human action detection, human tracking and segmentation in videos. They are fundamental tasks in computer vision and are extremely challenging to solve in realistic videos. We first propose a novel approach for action detection by exploring the generalization of deformable part models from 2D images to 3D spatiotemporal volumes. By focusing on the most distinctive parts of each action, our models adapt to intra-class variation and show robustness to clutter. This approach deals with detecting action performed by a single person. When there are multiple humans in the scene, humans need to be segmented and tracked from frame to frame before action recognition can be performed. Next, we propose a novel approach for multiple object tracking (MOT) by formulating detection and data association in one framework. Our method allows us to overcome the confinements of data association based MOT approaches, where the performance is dependent on the object detection results provided at input level. We show that automatically detecting and tracking targets in a single framework can help resolve the ambiguities due to frequent occlusion and heavy articulation of targets. In this tracker, targets are represented by bounding boxes, which is a coarse representation. However, pixel-wise object segmentation provides fine level information, which is desirable for later tasks. Finally, we propose a tracker that simultaneously solves three main problems: detection, data association and segmentation. This is especially important because the output of each of those three problems are highly correlated and the solution of one can greatly help improve the others. The proposed approach achieves more accurate segmentation results and also helps better resolve typical difficulties in multiple target tracking, such as occlusion, ID-switch and track drifting.
Show less - Date Issued
- 2018
- Identifier
- CFE0007378, ucf:52069
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0007378
- Title
- Guided Autonomy for Quadcopter Photography.
- Creator
-
Alabachi, Saif, Sukthankar, Gita, Behal, Aman, Lin, Mingjie, Boloni, Ladislau, Laviola II, Joseph, University of Central Florida
- Abstract / Description
-
Photographing small objects with a quadcopter is non-trivial to perform with many common user interfaces, especially when it requires maneuvering an Unmanned Aerial Vehicle (C) to difficult angles in order to shoot high perspectives. The aim of this research is to employ machine learning to support better user interfaces for quadcopter photography. Human Robot Interaction (HRI) is supported by visual servoing, a specialized vision system for real-time object detection, and control policies...
Show morePhotographing small objects with a quadcopter is non-trivial to perform with many common user interfaces, especially when it requires maneuvering an Unmanned Aerial Vehicle (C) to difficult angles in order to shoot high perspectives. The aim of this research is to employ machine learning to support better user interfaces for quadcopter photography. Human Robot Interaction (HRI) is supported by visual servoing, a specialized vision system for real-time object detection, and control policies acquired through reinforcement learning (RL). Two investigations of guided autonomy were conducted. In the first, the user directed the quadcopter with a sketch based interface, and periods of user direction were interspersed with periods of autonomous flight. In the second, the user directs the quadcopter by taking a single photo with a handheld mobile device, and the quadcopter autonomously flies to the requested vantage point.This dissertation focuses on the following problems: 1) evaluating different user interface paradigms for dynamic photography in a GPS-denied environment; 2) learning better Convolutional Neural Network (CNN) object detection models to assure a higher precision in detecting human subjects than the currently available state-of-the-art fast models; 3) transferring learning from the Gazebo simulation into the real world; 4) learning robust control policies using deep reinforcement learning to maneuver the quadcopter to multiple shooting positions with minimal human interaction.
Show less - Date Issued
- 2019
- Identifier
- CFE0007774, ucf:52369
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0007774
- Title
- Learning Hierarchical Representations for Video Analysis Using Deep Learning.
- Creator
-
Yang, Yang, Shah, Mubarak, Sukthankar, Gita, Da Vitoria Lobo, Niels, Stanley, Kenneth, Sukthankar, Rahul, University of Central Florida
- Abstract / Description
-
With the exponential growth of the digital data, video content analysis (e.g., action, event recognition) has been drawing increasing attention from computer vision researchers. Effective modeling of the objects, scenes, and motions is critical for visual understanding. Recently there has been a growing interest in the bio-inspired deep learning models, which has shown impressive results in speech and object recognition. The deep learning models are formed by the composition of multiple non...
Show moreWith the exponential growth of the digital data, video content analysis (e.g., action, event recognition) has been drawing increasing attention from computer vision researchers. Effective modeling of the objects, scenes, and motions is critical for visual understanding. Recently there has been a growing interest in the bio-inspired deep learning models, which has shown impressive results in speech and object recognition. The deep learning models are formed by the composition of multiple non-linear transformations of the data, with the goal of yielding more abstract and ultimately more useful representations. The advantages of the deep models are three fold: 1) They learn the features directly from the raw signal in contrast to the hand-designed features. 2) The learning can be unsupervised, which is suitable for large data where labeling all the data is expensive and unpractical. 3) They learn a hierarchy of features one level at a time and the layerwise stacking of feature extraction, this often yields better representations.However, not many deep learning models have been proposed to solve the problems in video analysis, especially videos ``in a wild''. Most of them are either dealing with simple datasets, or limited to the low-level local spatial-temporal feature descriptors for action recognition. Moreover, as the learning algorithms are unsupervised, the learned features preserve generative properties rather than the discriminative ones which are more favorable in the classification tasks. In this context, the thesis makes two major contributions.First, we propose several formulations and extensions of deep learning methods which learn hierarchical representations for three challenging video analysis tasks, including complex event recognition, object detection in videos and measuring action similarity. The proposed methods are extensively demonstrated for each work on the state-of-the-art challenging datasets. Besides learning the low-level local features, higher level representations are further designed to be learned in the context of applications. The data-driven concept representations and sparse representation of the events are learned for complex event recognition; the representations for object body parts and structures are learned for object detection in videos; and the relational motion features and similarity metrics between video pairs are learned simultaneously for action verification.Second, in order to learn discriminative and compact features, we propose a new feature learning method using a deep neural network based on auto encoders. It differs from the existing unsupervised feature learning methods in two ways: first it optimizes both discriminative and generative properties of the features simultaneously, which gives our features a better discriminative ability. Second, our learned features are more compact, while the unsupervised feature learning methods usually learn a redundant set of over-complete features. Extensive experiments with quantitative and qualitative results on the tasks of human detection and action verification demonstrate the superiority of our proposed models.
Show less - Date Issued
- 2013
- Identifier
- CFE0004964, ucf:49593
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0004964
- Title
- SCENE MONITORING WITH A FOREST OF COOPERATIVE SENSORS.
- Creator
-
Javed, Omar, Shah, Mubarak, University of Central Florida
- Abstract / Description
-
In this dissertation, we present vision based scene interpretation methods for monitoring of people and vehicles, in real-time, within a busy environment using a forest of co-operative electro-optical (EO) sensors. We have developed novel video understanding algorithms with learning capability, to detect and categorize people and vehicles, track them with in a camera and hand-off this information across multiple networked cameras for multi-camera tracking. The ability to learn prevents the...
Show moreIn this dissertation, we present vision based scene interpretation methods for monitoring of people and vehicles, in real-time, within a busy environment using a forest of co-operative electro-optical (EO) sensors. We have developed novel video understanding algorithms with learning capability, to detect and categorize people and vehicles, track them with in a camera and hand-off this information across multiple networked cameras for multi-camera tracking. The ability to learn prevents the need for extensive manual intervention, site models and camera calibration, and provides adaptability to changing environmental conditions. For object detection and categorization in the video stream, a two step detection procedure is used. First, regions of interest are determined using a novel hierarchical background subtraction algorithm that uses color and gradient information for interest region detection. Second, objects are located and classified from within these regions using a weakly supervised learning mechanism based on co-training that employs motion and appearance features. The main contribution of this approach is that it is an online procedure in which separate views (features) of the data are used for co-training, while the combined view (all features) is used to make classification decisions in a single boosted framework. The advantage of this approach is that it requires only a few initial training samples and can automatically adjust its parameters online to improve the detection and classification performance. Once objects are detected and classified they are tracked in individual cameras. Single camera tracking is performed using a voting based approach that utilizes color and shape cues to establish correspondence in individual cameras. The tracker has the capability to handle multiple occluded objects. Next, the objects are tracked across a forest of cameras with non-overlapping views. This is a hard problem because of two reasons. First, the observations of an object are often widely separated in time and space when viewed from non-overlapping cameras. Secondly, the appearance of an object in one camera view might be very different from its appearance in another camera view due to the differences in illumination, pose and camera properties. To deal with the first problem, the system learns the inter-camera relationships to constrain track correspondences. These relationships are learned in the form of multivariate probability density of space-time variables (object entry and exit locations, velocities, and inter-camera transition times) using Parzen windows. To handle the appearance change of an object as it moves from one camera to another, we show that all color transfer functions from a given camera to another camera lie in a low dimensional subspace. The tracking algorithm learns this subspace by using probabilistic principal component analysis and uses it for appearance matching. The proposed system learns the camera topology and subspace of inter-camera color transfer functions during a training phase. Once the training is complete, correspondences are assigned using the maximum a posteriori (MAP) estimation framework using both the location and appearance cues. Extensive experiments and deployment of this system in realistic scenarios has demonstrated the robustness of the proposed methods. The proposed system was able to detect and classify targets, and seamlessly tracked them across multiple cameras. It also generated a summary in terms of key frames and textual description of trajectories to a monitoring officer for final analysis and response decision. This level of interpretation was the goal of our research effort, and we believe that it is a significant step forward in the development of intelligent systems that can deal with the complexities of real world scenarios.
Show less - Date Issued
- 2005
- Identifier
- CFE0000497, ucf:46362
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0000497
- Title
- Understanding images and videos using context.
- Creator
-
Vaca Castano, Gonzalo, Da Vitoria Lobo, Niels, Shah, Mubarak, Mikhael, Wasfy, Jones, W Linwood, Wiegand, Rudolf, University of Central Florida
- Abstract / Description
-
In computer vision, context refers to any information that may influence how visual media are understood.(&)nbsp; Traditionally, researchers have studied the influence of several sources of context in relation to the object detection problem in images. In this dissertation, we present a multifaceted review of the problem of context.(&)nbsp; Context is analyzed as a source of improvement in the object detection problem, not only in images but also in videos. In the case of images, we also...
Show moreIn computer vision, context refers to any information that may influence how visual media are understood.(&)nbsp; Traditionally, researchers have studied the influence of several sources of context in relation to the object detection problem in images. In this dissertation, we present a multifaceted review of the problem of context.(&)nbsp; Context is analyzed as a source of improvement in the object detection problem, not only in images but also in videos. In the case of images, we also investigate the influence of the semantic context, determined by objects, relationships, locations, and global composition, to achieve a general understanding of the image content as a whole. In our research, we also attempt to solve the related problem of finding the context associated with visual media. Given a set of visual elements (images), we want to extract the context that can be commonly associated with these images in order to remove ambiguity. The first part of this dissertation concentrates on achieving image understanding using semantic context.(&)nbsp; In spite of the recent success in tasks such as image classi?cation, object detection, image segmentation, and the progress on scene understanding, researchers still lack clarity about computer comprehension of the content of the image as a whole. Hence, we propose a Top-Down Visual Tree (TDVT) image representation that allows the encoding of the content of the image as a hierarchy of objects capturing their importance, co-occurrences, and type of relations. A novel Top-Down Tree LSTM network is presented to learn about the image composition from the training images and their TDVT representations. Given a test image, our algorithm detects objects and determine the hierarchical structure that they form, encoded as a TDVT representation of the image.A single image could have multiple interpretations that may lead to ambiguity about the intentionality of an image.(&)nbsp; What if instead of having only a single image to be interpreted, we have multiple images that represent the same topic. The second part of this dissertation covers how to extract the context information shared by multiple images. We present a method to determine the topic that these images represent. We accomplish this task by transferring tags from an image retrieval database, and by performing operations in the textual space of these tags. As an application, we also present a new image retrieval method that uses multiple images as input. Unlike earlier works that focus either on using just a single query image or using multiple query images with views of the same instance, the new image search paradigm retrieves images based on the underlying concepts that the input images represent.Finally, in the third part of this dissertation, we analyze the influence of context in videos. In this case, the temporal context is utilized to improve scene identification and object detection. We focus on egocentric videos, where agents require some time to change from one location to another. Therefore, we propose a Conditional Random Field (CRF) formulation, which penalizes short-term changes of the scene identity to improve the scene identity accuracy.(&)nbsp; We also show how to improve the object detection outcome by re-scoring the results based on the scene identity of the tested frame. We present a Support Vector Regression (SVR) formulation in the case that explicit knowledge of the scene identity is available during training time. In the case that explicit scene labeling is not available, we propose an LSTM formulation that considers the general appearance of the frame to re-score the object detectors.
Show less - Date Issued
- 2017
- Identifier
- CFE0006922, ucf:51703
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0006922
- Title
- Robust Subspace Estimation Using Low-Rank Optimization. Theory and Applications in Scene Reconstruction, Video Denoising, and Activity Recognition.
- Creator
-
Oreifej, Omar, Shah, Mubarak, Da Vitoria Lobo, Niels, Stanley, Kenneth, Lin, Mingjie, Li, Xin, University of Central Florida
- Abstract / Description
-
In this dissertation, we discuss the problem of robust linear subspace estimation using low-rank optimization and propose three formulations of it. We demonstrate how these formulations can be used to solve fundamental computer vision problems, and provide superior performance in terms of accuracy and running time.Consider a set of observations extracted from images (such as pixel gray values, local features, trajectories...etc). If the assumption that these observations are drawn from a...
Show moreIn this dissertation, we discuss the problem of robust linear subspace estimation using low-rank optimization and propose three formulations of it. We demonstrate how these formulations can be used to solve fundamental computer vision problems, and provide superior performance in terms of accuracy and running time.Consider a set of observations extracted from images (such as pixel gray values, local features, trajectories...etc). If the assumption that these observations are drawn from a liner subspace (or can be linearly approximated) is valid, then the goal is to represent each observation as a linear combination of a compact basis, while maintaining a minimal reconstruction error. One of the earliest, yet most popular, approaches to achieve that is Principal Component Analysis (PCA). However, PCA can only handle Gaussian noise, and thus suffers when the observations are contaminated with gross and sparse outliers. To this end, in this dissertation, we focus on estimating the subspace robustly using low-rank optimization, where the sparse outliers are detected and separated through the `1 norm. The robust estimation has a two-fold advantage: First, the obtained basis better represents the actual subspace because it does not include contributions from the outliers. Second, the detected outliers are often of a specific interest in many applications, as we will show throughout this thesis. We demonstrate four different formulations and applications for low-rank optimization. First, we consider the problem of reconstructing an underwater sequence by removing the turbulence caused by the water waves. The main drawback of most previous attempts to tackle this problem is that they heavily depend on modelling the waves, which in fact is ill-posed since the actual behavior of the waves along with the imaging process are complicated and include several noise components; therefore, their results are not satisfactory. In contrast, we propose a novel approach which outperforms the state-of-the-art. The intuition behind our method is that in a sequence where the water is static, the frames would be linearly correlated. Therefore, in the presence of water waves, we may consider the frames as noisy observations drawn from a the subspace of linearly correlated frames. However, the noise introduced by the water waves is not sparse, and thus cannot directly be detected using low-rank optimization. Therefore, we propose a data-driven two-stage approach, where the first stage (")sparsifies(") the noise, and the second stage detects it. The first stage leverages the temporal mean of the sequence to overcome the structured turbulence of the waves through an iterative registration algorithm. The result of the first stage is a high quality mean and a better structured sequence; however, the sequence still contains unstructured sparse noise. Thus, we employ a second stage at which we extract the sparse errors from the sequence through rank minimization. Our method converges faster, and drastically outperforms state of the art on all testing sequences. Secondly, we consider a closely related situation where an independently moving object is also present in the turbulent video. More precisely, we consider video sequences acquired in a desert battlefields, where atmospheric turbulence is typically present, in addition to independently moving targets. Typical approaches for turbulence mitigation follow averaging or de-warping techniques. Although these methods can reduce the turbulence, they distort the independently moving objects which can often be of great interest. Therefore, we address the problem of simultaneous turbulence mitigation and moving object detection. We propose a novel three-term low-rank matrix decomposition approach in which we decompose the turbulence sequence into three components: the background, the turbulence, and the object. We simplify this extremely difficult problem into a minimization of nuclear norm, Frobenius norm, and L1 norm. Our method is based on two observations: First, the turbulence causes dense and Gaussian noise, and therefore can be captured by Frobenius norm, while the moving objects are sparse and thus can be captured by L1 norm. Second, since the object's motion is linear and intrinsically different than the Gaussian-like turbulence, a Gaussian-based turbulence model can be employed to enforce an additional constraint on the search space of the minimization. We demonstrate the robustness of our approach on challenging sequences which are significantly distorted with atmospheric turbulence and include extremely tiny moving objects. In addition to robustly detecting the subspace of the frames of a sequence, we consider using trajectories as observations in the low-rank optimization framework. In particular, in videos acquired by moving cameras, we track all the pixels in the video and use that to estimate the camera motion subspace. This is particularly useful in activity recognition, which typically requires standard preprocessing steps such as motion compensation, moving object detection, and object tracking. The errors from the motion compensation step propagate to the object detection stage, resulting in miss-detections, which further complicates the tracking stage, resulting in cluttered and incorrect tracks. In contrast, we propose a novel approach which does not follow the standard steps, and accordingly avoids the aforementioned difficulties. Our approach is based on Lagrangian particle trajectories which are a set of dense trajectories obtained by advecting optical flow over time, thus capturing the ensemble motions of a scene. This is done in frames of unaligned video, and no object detection is required. In order to handle the moving camera, we decompose the trajectories into their camera-induced and object-induced components. Having obtained the relevant object motion trajectories, we compute a compact set of chaotic invariant features, which captures the characteristics of the trajectories. Consequently, a SVM is employed to learn and recognize the human actions using the computed motion features. We performed intensive experiments on multiple benchmark datasets, and obtained promising results.Finally, we consider a more challenging problem referred to as complex event recognition, where the activities of interest are complex and unconstrained. This problem typically pose significant challenges because it involves videos of highly variable content, noise, length, frame size ... etc. In this extremely challenging task, high-level features have recently shown a promising direction as in [53, 129], where core low-level events referred to as concepts are annotated and modeled using a portion of the training data, then each event is described using its content of these concepts. However, because of the complex nature of the videos, both the concept models and the corresponding high-level features are significantly noisy. In order to address this problem, we propose a novel low-rank formulation, which combines the precisely annotated videos used to train the concepts, with the rich high-level features. Our approach finds a new representation for each event, which is not only low-rank, but also constrained to adhere to the concept annotation, thus suppressing the noise, and maintaining a consistent occurrence of the concepts in each event. Extensive experiments on large scale real world dataset TRECVID Multimedia Event Detection 2011 and 2012 demonstrate that our approach consistently improves the discriminativity of the high-level features by a significant margin.
Show less - Date Issued
- 2013
- Identifier
- CFE0004732, ucf:49835
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0004732
