The Experts below are selected from a list of 35172 Experts worldwide ranked by ideXlab platform
Amit K Roychowdhury - One of the best experts on this subject based on the ideXlab platform.
-
tracking multiple interacting targets in a Camera Network
Computer Vision and Image Understanding, 2015Co-Authors: Shu Zhang, Yingying Zhu, Amit K RoychowdhuryAbstract:We propose a tracker for multiple interacting targets in a Camera Network.A model is developed to decide the group state of each trajectory.The tracking problem is converted to a Network flow problem. In this paper we propose a framework for tracking multiple interacting targets in a wide-area Camera Network consisting of both overlapping and non-overlapping Cameras. Our method is motivated from observations that both individuals and groups of targets interact with each other in natural scenes. We associate each raw target trajectory (i.e., a tracklet) with a group state, which indicates if the trajectory belongs to an individual or a group. Structural Support Vector Machine (SSVM) is applied to the group states to decide if merge or split events occur in the scene. Information fusion between multiple overlapping Cameras is handled using a homography-based voting scheme. The problem of tracking multiple interacting targets is then converted to a Network flow problem, for which the solution can be obtained by the K-shortest paths algorithm. We demonstrate the effectiveness of the proposed algorithm on the challenging VideoWeb dataset in which a large amount of multi-person interaction activities are present. Comparative analysis with state-of-the-art methods is also shown.
-
a Camera Network tracking camnet dataset and performance baseline
Workshop on Applications of Computer Vision, 2015Co-Authors: Shu Zhang, Elliot Staudt, Tim Faltemier, Amit K RoychowdhuryAbstract:In this paper, we propose a novel Non-Overlapping Camera Network Tracking Dataset (CamNeT) for evaluating multi-target tracking algorithms. The dataset is composed of five to eight Cameras covering both indoor and outdoor scenes at a university. This dataset consists of six scenarios. Within each scenario are challenges relevant to lighting changes, complex topographies, crowded scenes, and changing grouping dynamics. Persons with predefined trajectories are combined with persons with random trajectories. Ground truth data for predefined trajectories is provided for each Camera. Also, a baseline multi-target tracking system is presented. The tracking results using the baseline system are provided, which can be compared with future works. The work provides a comprehensive multiCamera dataset for performance evaluation in this challenging application domain, as well as an initial set of results.
-
consistent re identification in a Camera Network
European Conference on Computer Vision, 2014Co-Authors: Abir Das, Anirban Chakraborty, Amit K RoychowdhuryAbstract:Most existing person re-identification methods focus on finding similarities between persons between pairs of Cameras (Camera pairwise re-identification) without explicitly maintaining consistency of the results across the Network. This may lead to infeasible associations when results from different Camera pairs are combined. In this paper, we propose a Network consistent re-identification (NCR) framework, which is formulated as an optimization problem that not only maintains consistency in re-identification results across the Network, but also improves the Camera pairwise re-identification performance between all the individual Camera pairs. This can be solved as a binary integer programing problem, leading to a globally optimal solution. We also extend the proposed approach to the more general case where all persons may not be present in every Camera. Using two benchmark datasets, we validate our approach and compare against state-of-the-art methods.
-
collaborative sensing in a distributed ptz Camera Network
IEEE Transactions on Image Processing, 2012Co-Authors: Chong Ding, Bi Song, Akshay A Morye, Jay A Farrell, Amit K RoychowdhuryAbstract:The performance of dynamic scene algorithms often suffers because of the inability to effectively acquire features on the targets, particularly when they are distributed over a wide field of view. In this paper, we propose an integrated analysis and control framework for a pan, tilt, zoom (PTZ) Camera Network in order to maximize various scene understanding performance criteria (e.g., tracking accuracy, best shot, and image resolution) through dynamic Camera-to-target assignment and efficient feature acquisition. Moreover, we consider the situation where processing is distributed across the Network since it is often unrealistic to have all the image data at a central location. In such situations, the Cameras, although autonomous, must collaborate among themselves because each Camera's PTZ parameter entails constraints on the others. Motivated by recent work in cooperative control of sensor Networks, we propose a distributed optimization strategy, which can be modeled as a game involving the Cameras and targets. The Cameras gain by reducing the error covariance of the tracked targets or through higher resolution feature acquisition, which, however, comes at the risk of losing the dynamic target. Through the optimization of this reward-versus-risk tradeoff, we are able to control the PTZ parameters of the Cameras and assign them to targets dynamically. The tracks, upon which the control algorithm is dependent, are obtained through a consensus estimation algorithm whereby Cameras can arrive at a consensus on the state of each target through a negotiation strategy. We analyze the performance of this collaborative sensing strategy in active Camera Networks in a simulation environment, as well as a real-life Camera Network.
-
videoweb dataset for multi Camera activities and non verbal communication
dvsn, 2011Co-Authors: Giovanni Denina, Bir Bhanu, Amit K Roychowdhury, Chong Ding, Hoang Thanh Nguyen, Ahmed Tashrif Kamal, Chinya V Ravishankar, Allen Ivers, Brenda VardaAbstract:Human-activity recognition is one of the most challenging problems in computer vision. Researchers from around the world have tried to solve this problem and have come a long way in recognizing simple motions and atomic activities. As the computer vision community heads toward fully recognizing human activities, a challenging and labeled dataset is needed. To respond to that need, we collected a dataset of realistic scenarios in a multi-Camera Network environment (VideoWeb) involving multiple persons performing dozens of different repetitive and non-repetitive activities. This chapter describes the details of the dataset. We believe that this VideoWeb Activities dataset is unique and it is one of the most challenging datasets available today. The dataset is publicly available online at http://vwdata.ee.ucr.edu/ along with the data annotation.
Francesco Bullo - One of the best experts on this subject based on the ideXlab platform.
-
Continuous graph partitioning for Camera Network surveillance
Automatica, 2015Co-Authors: Domenica Borra, Fabio Pasqualetti, Francesco BulloAbstract:In this note we discuss a novel graph partitioning problem, namely continuous graph partitioning, and we discuss its application to the design of surveillance trajectories for Camera Networks. In continuous graph partitioning, each edge is partitioned in a continuous fashion between its endpoint vertices, and the objective is to minimize the largest load among the vertices. We show that the continuous graph partitioning problem is convex and non-differentiable, and we characterize a solution amenable to distributed computation. The continuous graph partitioning problem naturally arises in the context of Camera Networks, where intruders appear at arbitrary locations and times, and the objective is to design Camera trajectories for quickest detection of intruders. Finally, we propose a surveillance strategy for Networks of PTZ Cameras and we characterize its performance.
-
Camera Network coordination for intruder detection
IEEE Transactions on Control Systems and Technology, 2014Co-Authors: Fabio Pasqualetti, Filippo Zanella, Jeffrey R Peters, Markus Spindler, Ruggero Carli, Francesco BulloAbstract:This paper proposes surveillance trajectories for a Network of autonomous Cameras to detect intruders. We consider smart intruders, which appear at arbitrary times and locations, are aware of the Cameras configuration, and move to avoid detection for as long as possible. As performance criteria, we consider the worst case detection time (WDT) and the average detection time (ADT). We focus on the case of a chain of Cameras, and we obtain the following results. First, we characterize a lower bound on the WDT and on the ADT of smart intruders. Second, we propose a team trajectory for the Cameras, namely equal- waiting trajectory, with minimum WDT and with guarantees on the ADT. Third, we design a distributed algorithm to coordinate the Cameras along an equal-waiting trajectory. Fourth, we design a distributed algorithm for Cameras reconfiguration in the case of failure or Network change. Finally, we illustrate the effectiveness and robustness of our algorithms via numerical studies and experiments. development of distributed and autonomous surveillance strategies for the detection of moving intruders. We make combined assumptions on the environment to be monitored, the Cameras, and the intruders. We assume the environment to be 1-D, in the sense that it can be completely observed by a chain of Cameras using linear motion only (the perimeter surveillance problem is a special case of this framework). We assume the Cameras to be subjected to physical constraints, such as limited field of view (f.o.v.) and speed, and to be equipped with a low-level routine to detect intruders that fall within their f.o.v. We assume intruders to be smart, in the sense that they have access to the Cameras configuration at every time instant, and schedule their trajectory to avoid detection for as long as possible. Since the probability of success of an intrusion increases with the time an intruder remains unde- tected in the environment (5), we propose Cameras trajectories and control algorithms to minimize the worst case detection time (WDT) and the average detection time (ADT) of smart intruders.
-
continuous graph partitioning for Camera Network surveillance
IFAC Proceedings Volumes, 2012Co-Authors: Domenica Borra, Fabio Pasqualetti, Francesco BulloAbstract:Abstract This work focuses on the problem of designing surveillance trajectories for a Network of autonomous Cameras. As performance criterion we consider the worst-case detection time of static intruders. First, we represent the environment by means of a robotic roadmap. We show that optimal trajectories can be designed via a continuous graph partitioning problem. This minimization problem is convex and not differentiable. Second, we derive an auxiliary convex and differentiable minimization problem whose minimizer provides a solution to the original problem. Third and finally, we develop three distributed algorithms, for the Cameras to partition the roadmap, and, consequently, synchronize along a trajectory with minimum worst-case detection time. Different communication protocols are used for the three algorithms.
Demetri Terzopoulos - One of the best experts on this subject based on the ideXlab platform.
-
Smart Camera Networks in virtual reality
Proceedings of the IEEE, 2008Co-Authors: Faisal Qureshi, Demetri TerzopoulosAbstract:This paper presents our research towards smart Camera Networks capable of carrying out advanced surveillance tasks with little or no human supervision. A unique centerpiece of our work is the combination of computer graphics, artificial life, and computer vision simulation technologies to develop such Networks and experiment with them. Specifically, we demonstrate a smart Camera Network comprising static and active simulated video surveillance Cameras that provides extensive coverage of a large virtual public space, a train station populated by autonomously self-animating virtual pedestrians. The realistically simulated Network of smart Cameras performs persistent visual surveillance of individual pedestrians with minimal intervention. Our innovative Camera control strategy naturally addresses Camera aggregation and handoff, is robust against Camera and communication failures, and requires no Camera calibration, detailed world model, or central controller.
-
Smart Camera Networks in Virtual Reality Simulated smart Cameras track the movement of simulated pedestrians in a simulated train station, allowing development of improved control strategies for smart Camera Networks.
2008Co-Authors: Faisal Z. Qureshi, Demetri TerzopoulosAbstract:This paper presents our research towards smart Camera Networks capable of carrying out advanced surveil- lance tasks with little or no human supervision. A unique centerpiece of our work is the combination of computer graphics, artificial life, and computer vision simulation tech- nologies to develop such Networks and experiment with them. Specifically, we demonstrate a smart Camera Network com- prising static and active simulated video surveillance Cameras that provides extensive coverage of a large virtual public space, at rain station populated by autonomously self-animating virtual pedestrians. The realistically simulated Network of smart Cameras performs persistent visual surveillance of individual pedestrians with minimal intervention. Our innova- tive Camera control strategy naturally addresses Camera aggregation and handoff, is robust against Camera and communication failures, and requires no Camera calibration, detailed world model, or central controller.
-
smart Camera Networks in virtual reality
International Conference on Distributed Smart Cameras, 2007Co-Authors: Faisal Z. Qureshi, Demetri TerzopoulosAbstract:We present smart Camera Network research in the context of a unique new synthesis of advanced computer graphics and vision simulation technologies. We design and experiment with simulated Camera Networks within visually and behaviorally realistic virtual environments. Specifically, we demonstrate a smart Camera Network comprising static and active simulated video surveillance Cameras that provides perceptive coverage of a large virtual public space, a train station populated by autonomously self-animating virtual pedestrians. In the context of human surveillance, we propose a Camera Network control strategy that enables a collection of smart Cameras to provide perceptive scene coverage and perform persistent surveillance with minimal intervention. Our novel control strategy naturally addresses Camera aggregation and Camera handoff, it does not require Camera calibration, a detailed world model, or a central controller, and it is robust against Camera failures and communication.
Rudi Penne - One of the best experts on this subject based on the ideXlab platform.
-
interactive Camera Network design using a virtual reality interface
Sensors, 2019Co-Authors: Boris Bogaerts, Seppe Sels, Steve Vanlanduit, Rudi PenneAbstract:The traditional literature on Camera Network design focuses on constructing automated algorithms. These require problem-specific input from experts in order to produce their output. The nature of the required input is highly unintuitive, leading to an impractical workflow for human operators. In this work we focus on developing a virtual reality user interface allowing human operators to manually design Camera Networks in an intuitive manner. From real world practical examples we conclude that the Camera Networks designed using this interface are highly competitive with, or sometimes even superior to, those generated by automated algorithms, but the associated workflow is more intuitive and simple. The competitiveness of the human-generated Camera Networks is remarkable because the structure of the optimization problem is a well known combinatorial NP-hard problem. These results indicate that human operators can be used in challenging geometrical combinatorial optimization problems, given an intuitive visualization of the problem.
-
interactive Camera Network design using a virtual reality interface
arXiv: Human-Computer Interaction, 2018Co-Authors: Boris Bogaerts, Seppe Sels, Steve Vanlanduit, Rudi PenneAbstract:Traditional literature on Camera Network design focuses on constructing automated algorithms. These require problem specific input from experts in order to produce their output. The nature of the required input is highly unintuitive leading to an unpractical workflow for human operators. In this work we focus on developing a virtual reality user interface allowing human operators to manually design Camera Networks in an intuitive manner. From real world practical examples we conclude that the Camera Networks designed using this interface are highly competitive with, or superior to those generated by automated algorithms, but the associated workflow is much more intuitive and simple. The competitiveness of the human-generated Camera Networks is remarkable because the structure of the optimization problem is a well known combinatorial NP-hard problem. These results indicate that human operators can be used in challenging geometrical combinatorial optimization problems given an intuitive visualization of the problem.
Fabio Pasqualetti - One of the best experts on this subject based on the ideXlab platform.
-
Continuous graph partitioning for Camera Network surveillance
Automatica, 2015Co-Authors: Domenica Borra, Fabio Pasqualetti, Francesco BulloAbstract:In this note we discuss a novel graph partitioning problem, namely continuous graph partitioning, and we discuss its application to the design of surveillance trajectories for Camera Networks. In continuous graph partitioning, each edge is partitioned in a continuous fashion between its endpoint vertices, and the objective is to minimize the largest load among the vertices. We show that the continuous graph partitioning problem is convex and non-differentiable, and we characterize a solution amenable to distributed computation. The continuous graph partitioning problem naturally arises in the context of Camera Networks, where intruders appear at arbitrary locations and times, and the objective is to design Camera trajectories for quickest detection of intruders. Finally, we propose a surveillance strategy for Networks of PTZ Cameras and we characterize its performance.
-
Camera Network coordination for intruder detection
IEEE Transactions on Control Systems and Technology, 2014Co-Authors: Fabio Pasqualetti, Filippo Zanella, Jeffrey R Peters, Markus Spindler, Ruggero Carli, Francesco BulloAbstract:This paper proposes surveillance trajectories for a Network of autonomous Cameras to detect intruders. We consider smart intruders, which appear at arbitrary times and locations, are aware of the Cameras configuration, and move to avoid detection for as long as possible. As performance criteria, we consider the worst case detection time (WDT) and the average detection time (ADT). We focus on the case of a chain of Cameras, and we obtain the following results. First, we characterize a lower bound on the WDT and on the ADT of smart intruders. Second, we propose a team trajectory for the Cameras, namely equal- waiting trajectory, with minimum WDT and with guarantees on the ADT. Third, we design a distributed algorithm to coordinate the Cameras along an equal-waiting trajectory. Fourth, we design a distributed algorithm for Cameras reconfiguration in the case of failure or Network change. Finally, we illustrate the effectiveness and robustness of our algorithms via numerical studies and experiments. development of distributed and autonomous surveillance strategies for the detection of moving intruders. We make combined assumptions on the environment to be monitored, the Cameras, and the intruders. We assume the environment to be 1-D, in the sense that it can be completely observed by a chain of Cameras using linear motion only (the perimeter surveillance problem is a special case of this framework). We assume the Cameras to be subjected to physical constraints, such as limited field of view (f.o.v.) and speed, and to be equipped with a low-level routine to detect intruders that fall within their f.o.v. We assume intruders to be smart, in the sense that they have access to the Cameras configuration at every time instant, and schedule their trajectory to avoid detection for as long as possible. Since the probability of success of an intrusion increases with the time an intruder remains unde- tected in the environment (5), we propose Cameras trajectories and control algorithms to minimize the worst case detection time (WDT) and the average detection time (ADT) of smart intruders.
-
continuous graph partitioning for Camera Network surveillance
IFAC Proceedings Volumes, 2012Co-Authors: Domenica Borra, Fabio Pasqualetti, Francesco BulloAbstract:Abstract This work focuses on the problem of designing surveillance trajectories for a Network of autonomous Cameras. As performance criterion we consider the worst-case detection time of static intruders. First, we represent the environment by means of a robotic roadmap. We show that optimal trajectories can be designed via a continuous graph partitioning problem. This minimization problem is convex and not differentiable. Second, we derive an auxiliary convex and differentiable minimization problem whose minimizer provides a solution to the original problem. Third and finally, we develop three distributed algorithms, for the Cameras to partition the roadmap, and, consequently, synchronize along a trajectory with minimum worst-case detection time. Different communication protocols are used for the three algorithms.