Real-Time FPGA-Based Object Tracker with Automatic Pan-Tilt Features for Smart Video Surveillance Systems

Abstract

Abstract:The design of smart video surveillance systems is an active research field among the computer vision community because of their ability to perform automatic scene analysis by selecting and tracking the objects of interest. In this paper, we present the design and implementation of an FPGA-based standalone working prototype system for real-time tracking of an object of interest in live video streams for such systems. In addition to real-time tracking of the object of interest, the implemented system is also capable of providing purposive automatic camera movement (pan-tilt) in the direction determined by movement of the tracked object. The complete system, including camera interface, DDR2 external memory interface controller, designed object tracking VLSI architecture, camera movement controller and display interface, has been implemented on the Xilinx ML510 (Virtex-5 FX130T) FPGA Board. Our proposed, designed and implemented system robustly tracks the target object present in the scene in real time for standard PAL (720 × 576) resolution color video and automatically controls camera movement in the direction determined by the movement of the tracked object.

UnCanny: Exploiting Reversed Edge Detection as a Basis for Object Tracking in Video

“…While the Canny technique has been improved many times over the years, including improving the blurring operator [ 8 ], using Otsu’s method for thresholding [ 9 ], and using advanced thinning techniques [ 10 ], most improvements on the Canny filter have focused on static images as opposed to video streams. Currently, many optical flow, object tracking, and motion detection algorithms are concerned with corner matching methods [ 11 ] that tend to require intensive computation [ 12 ], customized deep learning algorithms [ 13 ], and/or dedicated hardware [ 14 ]. As an alternative we offer a naive approach suitable for detecting moving objects that employs computationally inexpensive methods based on a reversal of classic edge detection techniques.…”

Vessel Detection and Tracking Method Based on Video Surveillance

“…Several researchers have proposed methods for object detection and tracking in video streams that did not assume a constant background, but were not specially dedicated for waterside systems. Their work was brought up and thoroughly compared in recent literature [8,9,10]. However, these solutions are usually too slow for use in real-time systems.…”