IOSR Journal of VLSI and Signal Processing (IOSR-JVSP) Volume 7, Issue 5, Ver. I (Sep-Oct. 2017), PP 12-22 e-ISSN: 2319 – 4200, p-ISSN No. : 2319 – 4197 www.iosrjournals.org DOI: 10.9790/4200-0705011222 www.iosrjournals.org 12 | Page FPGA Based Moving Object Tracking For Indoor Robot Navigation T. D. Magdum * a , P. C. Bhaskar a a Department of Technology (Electronic), Shivaji University, Kolhapur -416 004, India Corresponding author: T. D. Magdum Abstract: Indoor environments such as houses, offices, hospitals, mobile robots have to be equipped with a capability to navigate in indoor environments to execute a given task while avoiding obstacles. A number of sensors are used widely in order to navigate while detecting obstacles in indoor environments. However, most of these sensors are too expensive to apply for low-cost service robots. Thus we can use low cost surveillance camera for indoor robot navigation using the visual navigation. This paper gives the state of the art the FPGA and indoor robot navigation concept with the focus on FPGA based moving object tracking. The paper starts with an overview of FPGA base image processing in order to get an idea about FPGA architecture, and followed by an explanation on Moving object tracking algorithm and virtual path calculation. Finally, we concluded FPGA is an ideal choice for implementation of visual navigation for real time moving object tracking algorithms. Keywords: FPGA implementation, Indoor navigation, Moving object tracking algorithm, Virtual path claculation --------------------------------------------------------------------------------------------------------------------------------------- Date of Submission: 28-09-2017 Date of acceptance: 12-10-2017 --------------------------------------------------------------------------------------------------------------------------------------- I. Introduction Moving object tracking is one of the fundamental components of computer vision; it can be very beneficial in applications such as unmanned aerial vehicle, surveillance, automated traffic control, biomedical image analysis, intelligent robots etc. The problem of object tracking is of considerable interest in the scientific community and it is still an open and active field of research [1] (Shashank Pujari; 2008). Most of the image processing algorithms are sequential in nature. These algorithms are most suited in applications, which do not have any time restrictions. In other words, where the response time is not so important. In real-time systems, sequential algorithm will not be a good choice due to time and resource constraints. Field Programmable Gate Arrays (FPGA) on the other hand gives a platform for parallel execution. In an FPGA based design, different hardware blocks execute the sequences of an algorithm in parallel, and thus provide quick response and high frame rate. Since the overall operations are performed in less number of clock cycles, the power consumption will be reduced considerably, compared to micro-controller/DSP-processor based designs. 1.1 Motivations In a typical micro-controller/DSP processor based design, executes algorithm sequences sequentially. This will involve storing the frames in a buffer, and then performing the operation. If multiple hardware circuits can be designed to carry out different algorithm sequences in parallel, there will be considerable increase in overall execution speed. In actual designs, algorithm will be divided in to parallel blocks and will be executed simultaneously. In a nutshell, the significant increase in processing speed is the major motivation behind hardware image processing for moving object tracking. If the processing time is less, the power consumption also will be reduced. Hence it can be concluded that hardware image processing for proposed systems give better performance in time critical applications. In the current scenario, most of the image processing algorithms are running in a sequential environment. Hence a research in FPGA based image processing algorithms has greater significance and scope in time critical applications. Nowadays, Robots are used as mobile service robots in indoor environments such as houses, offices, hospitals. A number of sensors are used widely in order to detect obstacles in natural environments. However, most of these sensors are too expensive to apply for low-cost service robots like vacuum cleaning robots or guide robots. Hence, visual navigation takes much attention after web cameras were introduced a few years ago since its cost is attractive comparing with the previous sensors [2] (Nguyen Xuan Dao). Thus we can use Visual