Object tracking system based on invariant features

Modern Tracking algorithms treat tracking as a binary classification problem between the object class and the background class. In this paper, we propose the use of Distance Metric Learning (DML) in combination with Nearest Neighbor (NN) classification for object tracking. Initially a video file is read and the frames in the video are accessed individually. The object in that video is first detected using canny edge detector. We assume that the previous appearances of the object and the background are clustered so that a nearest neighbor classifier can be used to distinguish between the new appearance of the object and the appearance of the background. Using Nearest Neighbor classifier it is able to distinguish the object from other objects. The process is repeated for all the frames. Then the object is tracked using the Distance Metric Learning algorithm using normalized correlation between the frames. The human appearance model is identified using the Blob detector which uses the skin color to identify the object. Then the bounding box is fixed for the object in that frame. Then the video is reconstructed with the processed frames. Feature extraction is done using Region Props which threshold the image and extract the features. Measure the gray level co-occurrence matrix and match the best similar one.

I. Introduction

OBJECT tracking, in general, is a difficult problem [1]. Difficulties in tracking objects can arise due to abrupt movement of object, changing appearance patterns of the object and the scene, structure-less object, object-to-object and object-to-scene occlusions and camera motion. Tracking is normally performed in the context of higher-level applications that require the location and/or shape of the object in every frame. There are three key steps in video analysis, first detection of moving objects, second is tracking of objects from frame to frame and third analyzing the object tracks to recognize their behavior.