Papers by Khurram Shafique
When viewed from a system of multiple cameras with nonoverlapping fields of view, the appearance ... more When viewed from a system of multiple cameras with nonoverlapping fields of view, the appearance of an object in one camera view is usually very different from its appearance in another camera view due to the differences in illumination, pose and camera parameters. In order to handle the change in observed colors of an object as it moves from one camera to another, we show that all brightness transfer functions from a given camera to another camera lie in a low dimensional subspace and demonstrate that this subspace can be used to compute appearance similarity. In the proposed approach, the system learns the subspace of intercamera brightness transfer functions in a training phase during which object correspondences are assumed to be known. Once the training is complete, correspondences are assigned using the maximum a posteriori (MAP) estimation framework using both location and appearance cues. We evaluate the proposed method under several real world scenarios obtaining encouraging results.
A defensive k−alliance in a graph G = (V, E) is a set of vertices A ⊆ V such that for every verte... more A defensive k−alliance in a graph G = (V, E) is a set of vertices A ⊆ V such that for every vertex v ∈ A, the number of neighbors v has in A is at least k more than the number of neighbors it has in V − A (where k is the strength of defensive k−alliance). An offensive k−alliance is a set of vertices A ⊆ V such that for every vertex v ∈ ∂A, the number of neighbors v has in A is at least k more than the number of neighbors it has in V − A (where ∂A is the boundary of set A and is defined as N [A] − A). In this paper, we deal with two types of sets associated with these k−alliances: maximum k−alliance free and minimum k−alliance cover sets. Define a set X ⊆ V to be maximum k−alliance free (for some type of k−alliance) if X does not contain any k−alliance (of that type) and is a largest such set. A set Y ⊆ V is called minimum k−alliance cover (for some type of k−alliance) if Y contains at least one vertex from each k−alliance (of that type) and is a set of minimum cardinality satisfying this property. We present bounds on the cardinalities of maximum k−alliance free and minimum k−alliance cover sets and explore their inter-relation. The existence of forbidden subgraphs for graphs induced by these sets is also explored.
Discrete Mathematics, 2009
A strong defensive alliance in a graph G = (V , E) is a set of vertices A ⊆ V , for which every v... more A strong defensive alliance in a graph G = (V , E) is a set of vertices A ⊆ V , for which every vertex v ∈ A has at least as many neighbors in A as in V − A. We call a partition A, B of vertices to be an alliance-free partition, if neither A nor B contains a strong defensive alliance as a subset. We prove that a connected graph G has an alliance-free partition exactly when G has a block that is other than an odd clique or an odd cycle.
A tight bound on the cardinalities of maximum alliance-free and minimum alliance-cover sets
A defensive k-alliance in a graph G = (V; E) is a set of vertices A μ V such that for every verte... more A defensive k-alliance in a graph G = (V; E) is a set of vertices A μ V such that for every vertex v 2 A, the number of neighbors v has in A is at least k more than the number of neighbors it has in V ? A (k is a measure of the strength of alliance). In this paper, we deal with two types of sets associated with defensive k-alliances; maximum defensive k-alliance free and minimum defensive k-alliance cover sets. Deˉne a set X μ V to be maximum defensive k-alliance free if X does not contain any defensive k-alliance and is a largest such set. A set Y μ V is called minimum defensive k-alliance cover if Y contains at least one vertex from each defensive k-alliance and is a set of minimum cardinality satisfying this property. We present bounds on the cardinalities of maximum defensive k-alliance free and minimum defensive k-alliance cover sets.
An Object-based Video Coding Framework for Video
KNIGHT: Object Detection and Tracking in Surveillance Videos
Abstract. In this paper, we present KNIGHT, a Windows-based stand-alone object detection and trac... more Abstract. In this paper, we present KNIGHT, a Windows-based stand-alone object detection and tracking software, which is built upon Mi-crosoft Windows technologies, including MFC and DirectShow SDK. The object detection module assumes stationary background settings ...
There are approximately 261,000 rail crossings in the United States according to the studies by t... more There are approximately 261,000 rail crossings in the United States according to the studies by the National Highway Traffic Safety Administration (NHTSA) and Federal Railroad Administration (FRA). From 1993 to 1998, there were over 25,000 highway-rail crossing incidents involving motor vehicles -averaging 4,167 incidents a year. In this paper, we present a real-time computer vision system for the monitoring of the movement of pedestrians, bikers, animals and vehicles at railroad intersections. The video is processed for the detection of uncharacteristic events, triggering an immediate warning system. In order to recognize the events, the system first performs robust object detection and tracking. Next, a classification algorithm is used to determine whether the detected object is a pedestrian, biker, group or a vehicle, allowing inferences on whether the behavior of the object is characteristic or not. Due to the ubiquity of low cost, low power, and high quality video cameras, increased computing power and memory capacity, the proposed approach provides a cost effective and scalable solution to this important problem. Furthermore, the system has the potential to significantly decrease the number of accidents and therefore the resulting deaths and injuries that occur at railroad crossings. We have field tested our system at two sites, a rail-highway grade crossing, and a trestle located in Central Florida, and we present results on six hours of collected data.
An Object-based Video Coding Framework for Video
Multiple Vehicle Tracking in Surveillance Videos
In this paper, we present KNIGHT, a Windows-based stand-alone object detection, tracking and clas... more In this paper, we present KNIGHT, a Windows-based stand-alone object detection, tracking and classification software, which is built upon Microsoft Windows technologies. The object detection component assumes stationary background settings and models background pixel values using Mixture of Gaussians. Gradient-based background subtraction is used to handle scenarios of sudden illumination change. Connected- component algorithm is applied to detected foreground pixels for finding object-level moving blobs. The foreground objects are further tracked based on a pixel-voting technique with the occlusion and entry/exit reasonings. Motion correspondences are established using the color, size, spatial and motion information of objects. We have proposed a texture-based descriptor to classify moving objects into two groups: vehicles and persons. In this component, feature descriptors are computed from image patches, which are partitioned by concentric squares. SVM is used to build the object classifier. The system has been used in the VACE-CLEAR evaluation forum for the vehicle tracking task. Corresponding system performance is presented in this paper.
KNIGHT: Object Detection and Tracking in Surveillance Videos
Abstract. In this paper, we present KNIGHT, a Windows-based stand-alone object detection and trac... more Abstract. In this paper, we present KNIGHT, a Windows-based stand-alone object detection and tracking software, which is built upon Mi-crosoft Windows technologies, including MFC and DirectShow SDK. The object detection module assumes stationary background settings ...
There are approximately 261,000 rail crossings in the United States according to the studies by t... more There are approximately 261,000 rail crossings in the United States according to the studies by the National Highway Traffic Safety Administration (NHTSA) and Federal Railroad Administration (FRA). From 1993 to 1998, there were over 25,000 highway-rail crossing incidents involving motor vehicles -averaging 4,167 incidents a year. In this paper, we present a real-time computer vision system for the monitoring of the movement of pedestrians, bikers, animals and vehicles at railroad intersections. The video is processed for the detection of uncharacteristic events, triggering an immediate warning system. In order to recognize the events, the system first performs robust object detection and tracking. Next, a classification algorithm is used to determine whether the detected object is a pedestrian, biker, group or a vehicle, allowing inferences on whether the behavior of the object is characteristic or not. Due to the ubiquity of low cost, low power, and high quality video cameras, increased computing power and memory capacity, the proposed approach provides a cost effective and scalable solution to this important problem. Furthermore, the system has the potential to significantly decrease the number of accidents and therefore the resulting deaths and injuries that occur at railroad crossings. We have field tested our system at two sites, a rail-highway grade crossing, and a trestle located in Central Florida, and we present results on six hours of collected data.
Multiple Vehicle Tracking in Surveillance Videos
In this paper, we present KNIGHT, a Windows-based stand-alone object detection, tracking and clas... more In this paper, we present KNIGHT, a Windows-based stand-alone object detection, tracking and classification software, which is built upon Microsoft Windows technologies. The object detection component assumes stationary background settings and models background pixel values using Mixture of Gaussians. Gradient-based background subtraction is used to handle scenarios of sudden illumination change. Connected- component algorithm is applied to detected foreground pixels for finding object-level moving blobs. The foreground objects are further tracked based on a pixel-voting technique with the occlusion and entry/exit reasonings. Motion correspondences are established using the color, size, spatial and motion information of objects. We have proposed a texture-based descriptor to classify moving objects into two groups: vehicles and persons. In this component, feature descriptors are computed from image patches, which are partitioned by concentric squares. SVM is used to build the object classifier. The system has been used in the VACE-CLEAR evaluation forum for the vehicle tracking task. Corresponding system performance is presented in this paper.
Conventional tracking approaches assume proximity in space, time and appearance of objects in suc... more Conventional tracking approaches assume proximity in space, time and appearance of objects in successive observations. However, observations of objects are often widely separated in time and space when viewed from multiple non-overlapping cameras. To address this problem, we present a novel approach for establishing object correspondence across non-overlapping cameras. Our multi-camera tracking algorithm exploits the redundance in paths that people and cars tend to follow, e.g. roads, walk-ways or corridors, by using motion trends and appearance of objects, to establish correspondence. Our system does not require any inter-camera calibration, instead the system learns the camera topology and path probabilities of objects using Parzen windows, during a training phase. Once the training is complete, correspondences are assigned using the maximum a posteriori (MAP) estimation framework. The learned parameters are updated with changing trajectory patterns. Experiments with real world videos are reported, which validate the proposed approach.
We present a background subtraction method that uses multiple cues to robustly detect objects in ... more We present a background subtraction method that uses multiple cues to robustly detect objects in adverse conditions. The algorithm consists of three distinct levels i.e pixel level, region level and frame level. At the pixel level, statistical models of gradients and color are separately used to classify each pixel as belonging to background or foreground. In region level, foreground pixels obtained from the color based subtraction are grouped into regions and gradient based subtraction is then used to make inferences about the validity of these regions. Pixel based models are updated based on decisions made at the region level. Finally frame level analysis is performed to detect global illumination changes. Our method provides the solution to some of the common problems that are not addressed by most background subtraction algorithms such as quick illumination changes, repositioning of static background objects, and initialization of background model with moving objects present in the scene.
Modern automated video analysis systems consist of large networks of heterogeneous sensors. These... more Modern automated video analysis systems consist of large networks of heterogeneous sensors. These systems must extract, integrate and present relevant information from the sensors in real-time. This paper addresses some of the major challenges such systems face: efficient video processing for high-resolution sensors; data fusion across multiple modalities; robustness to changing environmental conditions and video processing errors; and intuitive user interfaces for visualization and analysis. The paper discusses enabling technologies to overcome these challenges and presents a case study of a wide area video analysis system deployed at a port in the state of Florida, USA. The components of the system are also detailed and justified using quantitative and qualitative results.
Distributed Sensor Networks for Visual Surveillance
Automated video analysis systems consist of large networks of distributed heterogeneous sensors. ... more Automated video analysis systems consist of large networks of distributed heterogeneous sensors. Such systems require extraction, integration, and representation of relevant data from sensors in real time. This book chapter identifies some of those major challenges and proposes solutions to them. In particular, efficient video processing for high-resolution sensors, data fusion across multiple modalities, robustness to changing environmental conditions and video processing errors, and intuitive user interfaces for visualization and analysis are discussed. Enabling technologies to overcome these challenges are also discussed. The case study of a wide area video analysis system deployed at ports in the states of Florida and California, USA is also presented. The components of the system are also detailed and justified using quantitative and qualitative results.
Automatic Visual Analysis for Transportation Security
Page 1. Automatic Visual Analysis for Transportation Security Niels Haering and Khurram Shafique ... more Page 1. Automatic Visual Analysis for Transportation Security Niels Haering and Khurram Shafique ObjectVideo 11600 Sunrise Valley Drive, Reston, VA 20191 nhaering, kshafiquegobjectvideo.com ... transportation security. ObjectVideo's sinteliet ystem, ...
Self Calibrating Visual Sensor Networks
... It exploits the redundancy in ror of a pre-specified portion of the total data. Stauffer the ... more ... It exploits the redundancy in ror of a pre-specified portion of the total data. Stauffer the data to reduce the search space as well as susceptibil-and Tieu [16] employed tracking information in a simi-ity to noise. The method uses Parzen windows, also known ...
Multi-frame data association involves finding the most probable correspondences between target tr... more Multi-frame data association involves finding the most probable correspondences between target tracks and measurements (collected over multiple time instances) as well as handling the common tracking problems such as, track initiations and terminations, occlusions, and noisy detections. The problem is known to be NP-Hard for more than two frames. A rank constrained continuous formulation of the problem is presented that can be efficiently solved using nonlinear optimization methods. It is shown that the global and local extrema of the continuous problem respectively coincide with the maximum and the maximal solutions of the discrete counterpart. A scanning window based tracking algorithm is developed using the formulation that performs well under noisy conditions with frequent occlusions and multiple track initiations and terminations. The above claims are supported by experiments and quantitative evaluations using both synthetic and real data under different operating conditions. 1 978-1-4244-2243-2/08/$25.00 ©2008 IEEE
Uploads
Papers by Khurram Shafique