OBJECT DETECTION AND TRACKING: EXPERIENCES WITH CONVENTIONAL IMAGE PROCESSING TECHNIQUES ON VEHICULAR TRAFFIC VIDEO
Singh Sukhmani, Prasun Kumar Gupta, Swapnil Jha · 2014
Abstract- Much work has been done in developing image processing techniques for data mining purposes; either by image enhancement or feature extraction. Seldom have these methods been applied to solve current day problems in transport management. This paper emphasis on the use of well established techniques (mountain gap & filters) in modified formats to achieve vehicle detection and tracking. Keywords- Image processing, Object Detection, Object Tracking, Filtering. I. INTRODUCTION Visual tracking has emerged as an important component of systems in several application areas including visual-based control surveillance medical imaging and visual reconstruction. The problem poses a challenge because of the multi-variate and multi-dimensional inputs in various application domains. The central challenge in visual tracking is to determine the image configuration of the target region of an object as it moves through a camera’s field of view. As object tracking has a lot of applications, many algorithms have been proposed to solve the problem. Changing illumination, scene changes and shadows are typical problems which make the problem challenging. A surveillance application usually consists of some sort of moving object detection, object tracking and higher order processing. A lot of existing methods first perform computationally expensive spatial segmentation based on gray scale values. This is not necessary in lots of applications, where only moving objects need to be tracked. This paper mainly concentrates on the two levels, moving object detection and object tracking. In this paper we propose an effective and efficient method for tracking moving objects in video sequences. In this paper we are not considering the camera motion, as our camera is stationary with small field of view.