Shape Based Object Classification for Automated Video Surveillance with Feature Selection

Abstract

Object classification based on shape features for video surveillance has been a research problem for number of years. The object classification accuracy depends on the type of classifier and the extracted object features used for classification. Excellent classification accuracy can be obtained with an appropriate combination of the extracted features with a particular classifier. In this paper, we propose to use an online feature selection method which gives a good subset of features while the machine learns the classification task and use these selected features for object classification. This paper also explores the impact of different kinds of shape features on the object classification accuracy and the performance of different classifiers in a typical automated video surveillance application. 10th International Conference on Information Technology 0-7695-3068-0/07 $25.00 © 2007 IEEE DOI 97 10th International Conference on Information Technology 0-7695-3068-0/07 $25.00

Moving objects classification via category-wise two-dimensional principal component analysis

“…For example, Collins et al [3] adopted dispersedness, aspect ratio, area, and zoom factor to train a neural network (NN) classifier for categorizing moving objects. The effectiveness of various shape features in conjunction with NN, support vector machine (SVM), and support vector data description (SVDD) are investigated by Hota et al [9]. However, notwithstanding their simplicity and ease of implementation, shape-based methods unable to accommodate the diverse variabilities in object appearance.…”

Evaluation of Smart Video for Transit Event Detection

“…It should be noted that a real-time implementation of optical flow will often require specialized hardware, due to the complexity of the algorithm. A benefit of using optical flow is that it is robust to multiple and simultaneous camera and object motions, making it ideal for crowd analysis and conditions that contain properties, see [57 ]). Some of these properties are also used in post-object classification to keep track of the object in sequential frames or separate cameras.…”

Online Learning Classification for Video Monitor

“…Boosting methods have been researched extensively. Viola et al proposed a novel framework for feature selection by boosting [5] . However,these methods require a large number of heavy computation and human labor to handle on samples labeling.…”