A method for detecting an abnormal object in video images is proposed. We define abnormal object as an object that does not appear in usual scenes. The detection system is trained with video images of usual scenes, and then detects abnormal objects in new input video images. The proposed method detects an abnormal object by assuming an object as a set of local features and ignoring the position...

This paper presents a compressed-domain fall incident detection scheme for intelligent homecare applications. For object extraction, global motion parameters are estimated to distinguish local object motions from camera motions so as to obtain a rough object mask. We then perform change detection and/or background subtraction on the DC+2AC images extracted from the incoming coded bitstream to r...

MPEG-4 video has been designed as a standard for video and audio compression, content-based functionalities, scalability of texture, images and video, shape coding, robustness in error-prone environment, and face and body animation. With all these functionalities, however, MPEG-4 still has limitations in practical software development. In this paper, we developed the frame preprocessing for rea...

Deep learning has been demonstrated to achieve excellent results for image classification and object detection. However, the impact of deep learning on video analysis (e.g. action detection and recognition) has not been that significant due to complexity of video data and lack of annotations. In addition, training deep neural networks on large scale video datasets is extremely computationally e...

There are many industrial products that use digital video image processing for orientation control or object detection. Often object shape is used for classification. However, if detection task has to be performed very fast and there are many different candidate shapes for an object, other characteristic features have to be used. One of the most relevant object features can be colour. For examp...

We propose an unsupervised video object segmentation algorithm that detects recurring objects and learns cohort object proposals over space-time. Our core contribution is a graph transduction process that learns object proposals densely over space-time, exploiting both appearance models learned from rudimentary detections of sparse objectlike regions, and their intrinsic structures. Our approac...

1077-3142/$ see front matter 2010 Elsevier Inc. A doi:10.1016/j.cviu.2010.10.008 ⇑ Corresponding author. Fax: +1 847 491 4455. E-mail addresses: [email protected]. edu.sg (J. Yuan), [email protected] (S.A. Ts ern.edu (A.K. Katsaggelos). Compared to other anomalous video event detection approaches that analyze object trajectories only, we propose a context-aware method to de...

Object detection and tracking is one of the critical areas of research due to routine change in motion of object and variation in scene size, occlusions, appearance variations, and ego-motion and illumination changes. Specifically, feature selection is the vital role in object tracking. It is related to many real time applications like vehicle perception, video surveillance and so on. In order ...

Moving object detection has been widely used in diverse discipline such as intelligent transportation systems, airport security systems, video monitoring systems, and so on. In this paper, we propose an efficient moving object detection method using enhanced edge localization mechanism and gradient directional masking for video surveillance system. In our proposed method, gradient map images ar...

Multi-object tracking has been recently approached with the min-cost network flow optimization techniques. Such methods simultaneously resolve multiple object tracks in a video and enable modeling of dependencies among tracks. Min-cost network flow methods also fit well within the “tracking-by-detection” paradigm where object trajectories are obtained by connecting per-frame outputs of an objec...