Abstract Background/Objectives: Nowadays, object detection and tracking is an important issue in robotics and computer vision systems, especially in video surveillance, robot navigation and autonomous vehicle navigation. Methods: In this paper, we propose a fast method for object tracking and recognition within the context of a mobile robot acquiring real time images from a top mounted IP camera. The aim of the proposed method is to let the robot identify multi-targets within a scene, then move toward the desired object. The method is based on a new vectored contour to identify objects from HSV images. Findings: Experimental results have shown that our method best fitted the mobile platform and gave excellent competitive results in real time tracking. Our proposed method has shown better adaptation com-pared to SURF and other state of the art tracking methods, especially in terms of time and simplicity, specifically when the camera is not in front of the target object, i.e. at different inclination angles and distances. Application: The object detection and tracking proposed in this work can be implemented on many fields such as video surveillance robotic navigation or in industry in classification of objects depending on their forms or colors. *Author for correspondence Indian Journal of Science and Technology, Vol 8(32), DOI: 10.17485/ijst/2015/v8i32/92131, November 2015 ISSN (Print) : 0974-6846 ISSN (Online) : 0974-5645 Real Time Object Detection & Tracking over a Mobile Platform M. A. Mekhtiche, M. A. Bencherif*, M. Algabri, M. Alsulaiman, R. Hedjar, M. Faisal and K. AlMutib Center for Smart Robotics Research, CCIS, King Saud University, Riyadh, Saudi Arabia; mbencherif1@yahoo.com, mmekhtiche@ksu.edu.sa, malgabri@ksu.edu.sa, msuliman@ksu.edu.sa, he-djar@ksu.edu.sa, mfaisal@ksu.edu.sa, muteb@ksu.edu.sa. 1. Introduction In autonomous mobile navigation, tracking objects is crucial, mainly in the framework of detecting and mov- ing toward the desired objects. Diferent algorithms have been proposed in the literature. Te most popular method is the Scale Invariant Feature Transform (SIFT) 1-3 or its improved version Speeded-Up Robust Features (SURF) 4 . Unfortunately, both methods sufer from the zoom issue, especially when the object is at a far distance and require enormous computations. Moreover, their performance degrades when tracked objects have very few details. Te background subtraction as improved by 1-5 is mainly used for fxed cameras. Te frame diference 6-7 [6, 7] becomes useless, if the tracked object stops moving. Te mean shif algorithm 8-10 is mainly efective for a single object track- ing, while color tracking 11 is more related to the presence of that colored object within the image, the shape has to be identifed by a complementary method. In section 2, we describe the proposed method, in section 3, we present the results of the identifcation, in section 4, a time complexity study is developed, section 5 discusses the results, and we conclude at section 6. 2. Methodology Te goal of this work is to let the robot fnd difer- ent required objects within a real time video stream, then position itself autonomously and move toward the desired target. For a real time implementation, a fast tracking algorithm is required, we propose, in this context, the use of a color histogram and a normalized vectored contour. Te histogram is used to identify the regions of the image having the same color of the object. Keywords: Mobile Robot, Object Recognition and Tracking