A learning-based approach to detect abnormal audio information is presented, which can be applied to audio surveillance systems that work alone or as supplements to video surveillance systems. / An automatic surveillance system is also presented that can generate a density map with multi-resolution cells and calculate the density distribution of the image by using texture analysis technique. Hosed on the estimated density distribution, the SVM method is used to solve the classification problem of detecting abnormal situations caused by changes in density distribution. / Anti-terrorism has become a global issue, and surveillance has become increasingly popular in public places such as elevators, banks, airports, and casinos. With traditional surveillance systems, human observers inspect the monitor arrays. However, with screen arrays becoming larger as the number of cameras increases, human observers may feel burdened, lose concentration, and make mistakes, which may be significant in such crucial positions as security posts. To solve this problem, I have developed an intelligent surveillance system that can understand human actions in real-time. / I have built a low-cost PC-based real-time video surveillance system that can model and analyze human real-time actions based on learning by demonstration. By teaching the system the difference between normal and abnormal human actions, the computational action models built inside the trained machines can automatically identify whether newly observed behavior requires security interference. The video surveillance system can detect the following abnormal behavior in a crowded environment using learning algorithms: (1) running people in a crowded environment; (2) falling down movements when most people are walking or standing; and (3) a person carrying an abnormally long bar in a square. Even a person running and waving a hand in a very crowded environment can be detected using an optical flow algorithm. / I have developed a real-time face detection and classification system in which the classification problem is defined as differentiating and is used to classify the front of a face as Asian or non-Asian. I combine the selected principal component analysis (PCA) and independent component analysis (ICA) features into a support vector machine (SVM) classifier to achieved a good classification rate. The system can also be used for other binary classifications of face images, such as gender and age classification without much modification. / This thesis establishes a framework for video, audio, and crowd surveillance, and successfully implements it on a mobile surveillance robot. The work is of significance in understanding human behavior and the detection of abnormal events, and has potential applications in areas such as security monitoring in household and public spaces. / To test my algorithms, the video and audio surveillance technology are implemented on a mobile platform to develop a household surveillance robot. The robot can detect a moving target and track it across a large field of vision using a pan/tilt camera platform, and can detect abnormal behavior in a cluttered environment; such as a person suddenly running or falling down on the floor. When abnormal audio information is detected, a camera on the robot is triggered to further confirm the occurrence of the abnormal event. / Wu, Xinyu. / "May 2008." / Adviser: Yangsheng Xu. / Source: Dissertation Abstracts International, Volume: 70-03, Section: B, page: 1915. / Thesis (Ph.D.)--Chinese University of Hong Kong, 2008. / Includes bibliographical references (p. 101-109). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Electronic reproduction. [Ann Arbor, MI] : ProQuest Information and Learning, [200-] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Abstracts in English and Chinese. / School code: 1307.

Thesis (Ph. D.)--University of California, Riverside, 2009. / Includes abstract. Title from first page of PDF file (viewed March 12, 2010). Available via ProQuest Digital Dissertations. Includes bibliographical references (p. 138-144). Also issued in print.

The extraction and analysis of human gait characteristics using image sequences are an important area of research. Recently, the focus of this research area has turned to computer vision as an unobtrusive way to analyze human motions. The applications for such a system are wide ranging in many disciplines. For example, it has been shown that visual systems can be used to identify people by their gait, estimate a subject's kinematic configuration and identify abnormal motion. The focus of this thesis is a system that accurately classifies observed motions without the use of an explicit spatial or temporal model. The visual detection of hidden loads through passive visual analysis of gait is presented as a test of the system. The major contributions of this thesis are in two areas. The first is a neural network based scheme that classifies walking styles based on simple image metrics obtained from a single, monocular gray scale image sequence. The powerful neural network classifier utilized in this system provides an efficient, robust and highly accurate classification using these image metrics. This eliminates the need for more complex and difficult to obtain measures that are required by many of the currently human visual analysis systems. This system uses computer vision and pattern recognition techniques combined with physiological knowledge of human gait to estimate an observed subject's hip angle. The hip angle is then used to calculate a normality index of the gait. The hip angle estimate and normality index are then used as inputs to a neural network. It is shown through experiment that this system provides an accurate classification of four different walking styles observed by a single camera. Secondly, a computer vision based approach is presented that provides an accurate pose estimate without the use of an explicit spatial or temporal model. A hybrid fuzzy neural network is used to assign contour points of a silhouette to kinematically relevant groups. These labeled points are used to estimate the joint locations of the subject. The joint angles are shown to be good estimates as compared to ground truth angles provided by a motion capture system. The effectiveness of the system to distinguish between subtle gait differences is demonstrated by detecting the presence of hidden loads when carried by walking people. / Ph. D.

This project deals with monitoring cars approaching the crossroads. Describes various methods of detection and discussing their problems. Primary goal is surveillance during the day in different weather conditions, but method of detection cars during the night and low light is also introduced. The most widely used algorithms are implemented using the OpenCV library. Important part is testing different algorithms and also variety of lighting conditions, camera locations and settings.