PROJECT TITLE :

Moving Object Classification Using a Combination of Static Appearance Features and Spatial and Temporal Entropy Values of Optical Flows

ABSTRACT:

This paper proposes a brand new approach for classifying four varieties of moving objects in an intelligent transportation system. Pedestrians, cars, motorcycles, and bicycles are classified based mostly on their facet views from a mounted camera. A moving object is segmented and tracked using background subtraction, silhouette projection, an space ratio, a Kalman filter, and look correlation operations. For the classification of a segmented object, a mix of static and spatiotemporal options primarily based on the cooccurrence of its appearance and the movements of its native parts is proposed. To extract the static look options, adaptive block-primarily based gradient intensities and histograms of oriented gradients are proposed. For the spatiotemporal features, the optical-flow-based mostly entropy values of instantaneous and short-term movements are proposed. The former finds the spatial entropy values of the orientations and the amplitudes of optical flows during a block to extract the local movement info from 2 consecutive image frames. The latter finds the temporal entropy values of the tracked optical flows in numerous orientation bins to extract the short-term movement data from several consecutive frames. Linear support vector machines with batch incremental learning are proposed to classify the four categories of objects. Experimental results from 12 take a look at video sequences and comparisons with several feature descriptors show the effect of the proposed classification system and therefore the advantage of the proposed features in classification.