http://hdl.handle.net/123456789/1374 2026-04-14T23:27:42Z http://hdl.handle.net/123456789/5923 Human detection using histogram of oriented gradients and human body ratio estimation Lee, Kelvin; Choo, Che Yon; See, Hui Qing; Tan, Zhuan Jiang; Lee, Yunli Recent research has been devoted to detecting people in images and videos. In this paper, a human detection method based on Histogram of Oriented Gradients (HoG) features and human body ratio estimation is presented. We utilized the discriminative power of HoG features for human detection, and implemented motion detection and local regions sliding window classifier, to obtain a rich descriptor set. Our human detection system consists of two stages. The initial stage involves image preprocessing and image segmentation, whereas the second stage classifies the integral image as human or non-human using human body ratio estimation, local region sliding window method and HoG Human Descriptor. Subsequently, it increases the detection rate and reduces the false alarm by deducting the overlapping window. In our experiments, DaimlerChrysler pedestrian benchmark data set is used to train a standard descriptor and the results showed an overall detection rate of 80% above 6p:, ill. 2010-01-01T00:00:00Z http://hdl.handle.net/123456789/5915 People detection enrichment for abnormal human activity detection Yussiff, Abdul-Lateef; Suet-Peng, Yong; Baharudin, Baharum B. A vibrant branch of research in computer vision that has attracted a lot of attention for decades is the human activity understanding from video. A means for accurately locating humans in image or a video is a prerequisite to the process of understanding human activities or action. This work’s focus is on investigating the use of people detectors for video surveillance in Financial Banks premises so that it can eventually be used for abnormal human activity detection. An integrated framework which is made up of histogram of oriented gradient descriptors and Haar integral features is proposed thus, it is a union of Full body detector and Upper body detector. The proposed framework gives an improvement over the state of the art when applied as a case study to bank security. The technique obtained an F-score of65.83 and precision of 73.83 and recall of 59.40 percentage points 9p:, ill. 2013-01-01T00:00:00Z http://hdl.handle.net/123456789/5912 Human tracking in video surveillance using particle filter Yussiff, Abdul-Lateef; Suet-Peng, Yong; Baharudin, Baharum B. Automated human tracking is a task that has a wide area of applications and has become more important nowadays. This research proposes to investigate the use of Bayesian inference technique specifically particle filter for tracking human in video surveillance. Kalman filter which has been the de facto technique for real world tracking performs poorly for most of the problems because, the real world applications are often non-linear and non Gaussian. The particle filter on the other hand is a tool for estimating the posterior probability density of state of a dynamic model that includes non-linear and non-Gaussian real world applications. The filter uses random sample to estimate the possible location of the tracked object in the next immediate frame even in the presence of occlusion. In order to initialize the tracking process, humans are first detected using a pretrained human detection model in video. The detector utilize model fusing method which is the combination of histogram of oriented gradient based human detector model and Haar feature based upper body detector to locate position of moving person in video. The technique performed excellently well when evaluated on the publicly available CAVIAR dataset and outperformed the Kalman flter algorithm 6p:, ill. 2015-01-01T00:00:00Z http://hdl.handle.net/123456789/5906 Human detection using histogram of oriented gradients and human body ratio estimation Lee, Kelvin; Choo, Che Yon; See, Hui Qing; Zhuan, Jiang Tan; Yunli, Lee Recent research has been devoted to detecting people in images and videos. In this paper, a human detection method based on Histogram of Oriented Gradients (HoG) features and human body ratio estimation is presented. We utilized the discriminative power of HoG features for human detection, and implemented motion detection and local regions sliding window classifier, to obtain a rich descriptor set. Our human detection system consists of two stages. The initial stage involves image preprocessing and image segmentation, whereas the second stage classifies the integral image as human or non-human using human body ratio estimation, local region sliding window method and HoG Human Descriptor. Subsequently, it increases the detection rate and reduces the false alarm by deducting the overlapping window. In our experiments, DaimlerChrysler pedestrian benchmark data set is used to train a standard descriptor and the results showed an overall detection rate of 80% above 6p:, ill. 2010-01-01T00:00:00Z