The Experts below are selected from a list of 48 Experts worldwide ranked by ideXlab platform

Arun Hampapur - One of the best experts on this subject based on the ideXlab platform.

  • Machine Learning for Human Motion Analysis - Multi-Scale People Detection and Motion Analysis for Video Surveillance.
    Machine Learning for Human Motion Analysis, 2020
    Co-Authors: Yingli Tian, Rogerio S. Feris, Lisa M. Brown, Daniel Vaquero, Yun Zhai, Arun Hampapur
    Abstract:

    Visual processing of people, including detection, tracking, recognition, and behavior interpretation, is a key component of intelligent video surveillance systems. Computer vision algorithms with the capability of “looking at people” at multiple scales can be applied in different surveillance scenarios, such as farfield people detection for wide-area perimeter protection, mid-field people detection for Retail/banking applications or parking lot monitoring, and near-field people/face detection for facility security and access. In this chapter, we address the people detection problem in different scales as well as human tracking and motion analysis for real video surveillance applications including people search, Retail Loss Prevention, people counting, and display effectiveness.

  • Multi-Camera Networks - Composite Event Detection in Multi-Camera and Multi-Sensor Surveillance Networks
    Multi-Camera Networks, 2020
    Co-Authors: Yun Zhai, Yingli Tian, Rogerio S. Feris, Lisa M. Brown, Arun Hampapur, Russell P. Bobbitt, Sharath Pankanti, Akira Yanagawa, Senem Velipasalar
    Abstract:

    Given the rapid development of digital video technologies, large-scale multi-camera networks are now more prevalent than ever. There is an increasing demand for automated multi-camera/sensor event-modeling technologies that can efficiently and effectively extract events and activities occurring in the surveillance network. In this chapter, we present a composite event detection system for multicamera networks. The proposed framework is capable of handling relationships between primitive events generated from (1) a single camera view, (2) multiple camera views, and (3) nonvideo sensors with spatial and temporal variations. Composite events are represented in the form of full binary trees, where the leaf nodes represent primitive events, the root node represents the target composite event, and the middle nodes represent rule definitions. The multi-layer design of composite events provides great extensibility and flexibility in different applications. A standardized XML-style event language is designed to describe the composite events such that inter-agent communication and event detection module construction can be conveniently achieved. In our system, a set of graphical interfaces is also developed for users to easily define both primitive and high-level composite events. The proposed system is designed in distributed form, where the system components can be deployed on separate processors, communicating with each other over a network. The capabilities and effectiveness of our system have been demonstrated in several real-life applications, including Retail Loss Prevention, indoor tailgating detection, and false positive reduction.

Yun Zhai - One of the best experts on this subject based on the ideXlab platform.

  • Machine Learning for Human Motion Analysis - Multi-Scale People Detection and Motion Analysis for Video Surveillance.
    Machine Learning for Human Motion Analysis, 2020
    Co-Authors: Yingli Tian, Rogerio S. Feris, Lisa M. Brown, Daniel Vaquero, Yun Zhai, Arun Hampapur
    Abstract:

    Visual processing of people, including detection, tracking, recognition, and behavior interpretation, is a key component of intelligent video surveillance systems. Computer vision algorithms with the capability of “looking at people” at multiple scales can be applied in different surveillance scenarios, such as farfield people detection for wide-area perimeter protection, mid-field people detection for Retail/banking applications or parking lot monitoring, and near-field people/face detection for facility security and access. In this chapter, we address the people detection problem in different scales as well as human tracking and motion analysis for real video surveillance applications including people search, Retail Loss Prevention, people counting, and display effectiveness.

  • Multi-Camera Networks - Composite Event Detection in Multi-Camera and Multi-Sensor Surveillance Networks
    Multi-Camera Networks, 2020
    Co-Authors: Yun Zhai, Yingli Tian, Rogerio S. Feris, Lisa M. Brown, Arun Hampapur, Russell P. Bobbitt, Sharath Pankanti, Akira Yanagawa, Senem Velipasalar
    Abstract:

    Given the rapid development of digital video technologies, large-scale multi-camera networks are now more prevalent than ever. There is an increasing demand for automated multi-camera/sensor event-modeling technologies that can efficiently and effectively extract events and activities occurring in the surveillance network. In this chapter, we present a composite event detection system for multicamera networks. The proposed framework is capable of handling relationships between primitive events generated from (1) a single camera view, (2) multiple camera views, and (3) nonvideo sensors with spatial and temporal variations. Composite events are represented in the form of full binary trees, where the leaf nodes represent primitive events, the root node represents the target composite event, and the middle nodes represent rule definitions. The multi-layer design of composite events provides great extensibility and flexibility in different applications. A standardized XML-style event language is designed to describe the composite events such that inter-agent communication and event detection module construction can be conveniently achieved. In our system, a set of graphical interfaces is also developed for users to easily define both primitive and high-level composite events. The proposed system is designed in distributed form, where the system components can be deployed on separate processors, communicating with each other over a network. The capabilities and effectiveness of our system have been demonstrated in several real-life applications, including Retail Loss Prevention, indoor tailgating detection, and false positive reduction.

Yingli Tian - One of the best experts on this subject based on the ideXlab platform.

  • Machine Learning for Human Motion Analysis - Multi-Scale People Detection and Motion Analysis for Video Surveillance.
    Machine Learning for Human Motion Analysis, 2020
    Co-Authors: Yingli Tian, Rogerio S. Feris, Lisa M. Brown, Daniel Vaquero, Yun Zhai, Arun Hampapur
    Abstract:

    Visual processing of people, including detection, tracking, recognition, and behavior interpretation, is a key component of intelligent video surveillance systems. Computer vision algorithms with the capability of “looking at people” at multiple scales can be applied in different surveillance scenarios, such as farfield people detection for wide-area perimeter protection, mid-field people detection for Retail/banking applications or parking lot monitoring, and near-field people/face detection for facility security and access. In this chapter, we address the people detection problem in different scales as well as human tracking and motion analysis for real video surveillance applications including people search, Retail Loss Prevention, people counting, and display effectiveness.

  • Multi-Camera Networks - Composite Event Detection in Multi-Camera and Multi-Sensor Surveillance Networks
    Multi-Camera Networks, 2020
    Co-Authors: Yun Zhai, Yingli Tian, Rogerio S. Feris, Lisa M. Brown, Arun Hampapur, Russell P. Bobbitt, Sharath Pankanti, Akira Yanagawa, Senem Velipasalar
    Abstract:

    Given the rapid development of digital video technologies, large-scale multi-camera networks are now more prevalent than ever. There is an increasing demand for automated multi-camera/sensor event-modeling technologies that can efficiently and effectively extract events and activities occurring in the surveillance network. In this chapter, we present a composite event detection system for multicamera networks. The proposed framework is capable of handling relationships between primitive events generated from (1) a single camera view, (2) multiple camera views, and (3) nonvideo sensors with spatial and temporal variations. Composite events are represented in the form of full binary trees, where the leaf nodes represent primitive events, the root node represents the target composite event, and the middle nodes represent rule definitions. The multi-layer design of composite events provides great extensibility and flexibility in different applications. A standardized XML-style event language is designed to describe the composite events such that inter-agent communication and event detection module construction can be conveniently achieved. In our system, a set of graphical interfaces is also developed for users to easily define both primitive and high-level composite events. The proposed system is designed in distributed form, where the system components can be deployed on separate processors, communicating with each other over a network. The capabilities and effectiveness of our system have been demonstrated in several real-life applications, including Retail Loss Prevention, indoor tailgating detection, and false positive reduction.

Rogerio S. Feris - One of the best experts on this subject based on the ideXlab platform.

  • Machine Learning for Human Motion Analysis - Multi-Scale People Detection and Motion Analysis for Video Surveillance.
    Machine Learning for Human Motion Analysis, 2020
    Co-Authors: Yingli Tian, Rogerio S. Feris, Lisa M. Brown, Daniel Vaquero, Yun Zhai, Arun Hampapur
    Abstract:

    Visual processing of people, including detection, tracking, recognition, and behavior interpretation, is a key component of intelligent video surveillance systems. Computer vision algorithms with the capability of “looking at people” at multiple scales can be applied in different surveillance scenarios, such as farfield people detection for wide-area perimeter protection, mid-field people detection for Retail/banking applications or parking lot monitoring, and near-field people/face detection for facility security and access. In this chapter, we address the people detection problem in different scales as well as human tracking and motion analysis for real video surveillance applications including people search, Retail Loss Prevention, people counting, and display effectiveness.

  • Multi-Camera Networks - Composite Event Detection in Multi-Camera and Multi-Sensor Surveillance Networks
    Multi-Camera Networks, 2020
    Co-Authors: Yun Zhai, Yingli Tian, Rogerio S. Feris, Lisa M. Brown, Arun Hampapur, Russell P. Bobbitt, Sharath Pankanti, Akira Yanagawa, Senem Velipasalar
    Abstract:

    Given the rapid development of digital video technologies, large-scale multi-camera networks are now more prevalent than ever. There is an increasing demand for automated multi-camera/sensor event-modeling technologies that can efficiently and effectively extract events and activities occurring in the surveillance network. In this chapter, we present a composite event detection system for multicamera networks. The proposed framework is capable of handling relationships between primitive events generated from (1) a single camera view, (2) multiple camera views, and (3) nonvideo sensors with spatial and temporal variations. Composite events are represented in the form of full binary trees, where the leaf nodes represent primitive events, the root node represents the target composite event, and the middle nodes represent rule definitions. The multi-layer design of composite events provides great extensibility and flexibility in different applications. A standardized XML-style event language is designed to describe the composite events such that inter-agent communication and event detection module construction can be conveniently achieved. In our system, a set of graphical interfaces is also developed for users to easily define both primitive and high-level composite events. The proposed system is designed in distributed form, where the system components can be deployed on separate processors, communicating with each other over a network. The capabilities and effectiveness of our system have been demonstrated in several real-life applications, including Retail Loss Prevention, indoor tailgating detection, and false positive reduction.

Lisa M. Brown - One of the best experts on this subject based on the ideXlab platform.

  • Machine Learning for Human Motion Analysis - Multi-Scale People Detection and Motion Analysis for Video Surveillance.
    Machine Learning for Human Motion Analysis, 2020
    Co-Authors: Yingli Tian, Rogerio S. Feris, Lisa M. Brown, Daniel Vaquero, Yun Zhai, Arun Hampapur
    Abstract:

    Visual processing of people, including detection, tracking, recognition, and behavior interpretation, is a key component of intelligent video surveillance systems. Computer vision algorithms with the capability of “looking at people” at multiple scales can be applied in different surveillance scenarios, such as farfield people detection for wide-area perimeter protection, mid-field people detection for Retail/banking applications or parking lot monitoring, and near-field people/face detection for facility security and access. In this chapter, we address the people detection problem in different scales as well as human tracking and motion analysis for real video surveillance applications including people search, Retail Loss Prevention, people counting, and display effectiveness.

  • Multi-Camera Networks - Composite Event Detection in Multi-Camera and Multi-Sensor Surveillance Networks
    Multi-Camera Networks, 2020
    Co-Authors: Yun Zhai, Yingli Tian, Rogerio S. Feris, Lisa M. Brown, Arun Hampapur, Russell P. Bobbitt, Sharath Pankanti, Akira Yanagawa, Senem Velipasalar
    Abstract:

    Given the rapid development of digital video technologies, large-scale multi-camera networks are now more prevalent than ever. There is an increasing demand for automated multi-camera/sensor event-modeling technologies that can efficiently and effectively extract events and activities occurring in the surveillance network. In this chapter, we present a composite event detection system for multicamera networks. The proposed framework is capable of handling relationships between primitive events generated from (1) a single camera view, (2) multiple camera views, and (3) nonvideo sensors with spatial and temporal variations. Composite events are represented in the form of full binary trees, where the leaf nodes represent primitive events, the root node represents the target composite event, and the middle nodes represent rule definitions. The multi-layer design of composite events provides great extensibility and flexibility in different applications. A standardized XML-style event language is designed to describe the composite events such that inter-agent communication and event detection module construction can be conveniently achieved. In our system, a set of graphical interfaces is also developed for users to easily define both primitive and high-level composite events. The proposed system is designed in distributed form, where the system components can be deployed on separate processors, communicating with each other over a network. The capabilities and effectiveness of our system have been demonstrated in several real-life applications, including Retail Loss Prevention, indoor tailgating detection, and false positive reduction.