Monitoring of public and private sites has increasingly become a very sensitive issue resulting in a patchwork of privacy laws varying from country to country -though all aimed at protecting the privacy of the citizen. It is important to remember, however, that monitoring and vi sual surveillance capabilities can also be employed to aid the citizen. The focus of current development is primarily aimed at public and cor porate safety applications including the monitoring of railway stations, airports, and inaccessible or dangerous environments. Future research effort, however, has already targeted citizen-oriented applications such as monitoring assistants for the aged and infirm, route-planning and congestion-avoidance tools, and a range of environment al monitoring applications. The latest generation of surveillance systems has eagerly adopted re cent technological developments to produce a fully digital pipeline of digital image acquisition, digital data transmission and digital record ing. The resultant surveillance products are highly-fiexihle, capahle of generating forensic-quality imagery, and ahle to exploit existing Internet and wide area network services to provide remote monitoring capability.

"One ability of the human visual system is the ability to identify and track moving objects. Examples of this can easily be seen in any sporting event. Humans are able to find an object in motion and track its current path and even predict a trajectory based on its current motion. Computer vision systems exist that are able to track an object in video, but usually these systems need to be instructed what the object to track is. As a way to further the work done by these computer vision systems, I present two additions to the work in the form of Adaptive Thresholding, a way to dynamically discover a threshold value of difference images, and a new method of blob tracking to further improve the accuracy of tracking blobs in video."--Abstract.

Multiple cameras have been used to improve the coverage and accuracy of visual surveillance systems. Nowadays, there are estimated 30 million surveillance cameras deployed in the United States. The large amount of video data generated by cameras necessitate automatic activity analysis, and automatic object detection and tracking are essential steps before any activity/event analysis. Most work on automatic tracking of objects across multiple camera views has considered systems that rely on a back-end server to process video inputs from multiple cameras. In this dissertation, we propose distributed camera systems in peer-to-peer communication. Each camera in the proposed systems performs object detection and tracking individually and only exchanges a small amount of data for consistent labeling. With the lightweight and robust algorithms running in each camera, the systems are capable of tracking multiple objects in a real-time manner. The cameras in the system may have overlapping or non-overlapping views. With partially overlapping views, the object labels can be handed off between cameras based on geometric relations. Most camera systems with overlapping views attach cameras to PCs and communicate via Ethernet, which hinders the flexibility and scalability. With the advances in VLSI technology, smart cameras have been introduced. A smart camera not only captures images, but also includes a processor, memory and communication interface making it a stand-alone unit. We first present a wireless embedded smart camera system for cooperative object tracking and detection of composite events. Each camera is a CITRIC mote consisting of a camera board and a wireless mote. All the processing is performed on camera boards. Power consumption of the proposed system is analyzed based on the measurements of operating currents for different scenarios. On the other hand, in wide-area tracking applications, it is not always realistic to assume that all the cameras in the system have overlapping fields of view. Tracking across non-overlapping views present more challenges due to lack of spatial continuity. To address this problem, we present another distributed camera system based on a probabilistic Petri Net framework. We combine appearance features of objects as well as the travel-time evidence for target matching and consistent labeling across disjoint camera views. Multiple features are combined by adaptive weights, which are assigned based on the reliability of the features and updated online. We employ a probabilistic Petri Net to account for the uncertainties of the vision algorithms and to incorporate the available domain knowledge. Synchronization is another important problem for multi-camera systems, because it is essential to have the precise relevance between the video data captured by different cameras. We present a computationally efficient and robust method for temporally calibrating video sequences from unsynchronized cameras. As opposed to expensive hardware-based synchronization methods, our algorithm is solely based on video processing. This algorithm is to match and align the object trajectories using the Longest Consecutive Common Subsequence, and thus to recover the frame offset between video sequences. With the increasing number of cameras in the system, cost and flexibility are important factors to consider. The cost of each camera node increases with the increasing resolution of the image sensor. A possible way of employing low-cost low-resolution sensors to achieve higher resolution images is presented. In this system, four embedded cameras with low-resolution customized sensors are tiled in different arrangements. With the customized CMOS imager, we perform edge and motion detection on the focal plane, then stitch the four edge images together to get a higher-resolution edge map.

This volume contains the papers of the 9th International Conference on Computing and Information Technology (IC2IT 2013) held at King Mongkut's University of Technology North Bangkok (KMUTNB), Bangkok, Thailand, on May 9th-10th, 2013. Traditionally, the conference is organized in conjunction with the National Conference on Computing and Information Technology, one of the leading Thai national events in the area of Computer Science and Engineering. The conference as well as this volume is structured into 3 main tracks on Data Networks/Communication, Data Mining/Machine Learning, and Human Interfaces/Image processing.

Protecting Privacy in Video Surveillance offers the state of the art from leading researchers and experts in the field. This broad ranging volume discusses the topic from various technical points of view and also examines surveillance from a societal perspective. A comprehensive introduction carefully guides the reader through the collection of cutting-edge research and current thinking. The technical elements of the field feature topics from MERL blind vision, stealth vision and privacy by de-identifying face images, to using mobile communications to assert privacy from video surveillance, and using wearable computing devices for data collection in surveillance environments. Surveillance and society is approached with discussions of security versus privacy, the rise of surveillance, and focusing on social control. This rich array of the current research in the field will be an invaluable reference for researchers, as well as graduate students.

Visual object tracking (VOT) and face recognition (FR) are essential tasks in computer vision with various real-world applications including human-computer interaction, autonomous vehicles, robotics, motion-based recognition, video indexing, surveillance and security. This book presents the state-of-the-art and new algorithms, methods, and systems of these research fields by using deep learning. It is organized into nine chapters across three sections. Section I discusses object detection and tracking ideas and algorithms; Section II examines applications based on re-identification challenges; and Section III presents applications based on FR research.