Abstract
The processing of a high-definition video stream in real-time is a challenging task for embedded systems. However, modern FPGA devices have both a high operating frequency and sufficient logic resources to be successfully used in these tasks. In this article, an advanced system that is able to generate and maintain a complex background model for a scene as well as segment the foreground for an HD colour video stream (1,920 × 1,080 @ 60 fps) in real-time is presented. The possible application ranges from video surveillance to machine vision systems. That is, in all cases, when information is needed about which objects are new or moving in the scene. Excellent results are obtained by using the CIE Lab colour space, advanced background representation as well as integrating information about lightness, colour and texture in the segmentation step. Finally, the complete system is implemented in a single high-end FPGA device.
Highlights
Nowadays megapixels and high-definition video sensors are installed almost everywhere from mobile phones and photo cameras to medical imaging and surveillance systems
There are two main approaches: methods based on optical flow (e.g. [5, 11, 25]) and background generation followed by background subtraction
A system for foreground object segmentation with shadow removal implemented in an FPGA device was described in this article
Summary
Nowadays megapixels and high-definition video sensors are installed almost everywhere from mobile phones and photo cameras to medical imaging and surveillance systems. The model used a histogram for each pixel and as the background, the central value of the largest bin was recognized This approach was implemented in an Xilinx XC2V1000 FPGA device and allowed to process a greyscale 640 9 480 video stream at 132 fps. In a recent work [35], a hardware implementation of a background generation system in Spartan 3 FPGA device which is using the Horprasert [12] method was presented Authors added their own shadow detection mechanism which allows to improve the segmentation results. An FPGA-based system which is able to generate the background and extract the foreground object mask for an HD colour video stream in real-time (1,920 9 1,080 @ 60 fps) is presented.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
