Abstract
During the process of moving object detection in an intelligent visual surveillance system, a scenario with complex background is sure to appear. The traditional methods, such as “frame difference” and “optical flow”, may not able to deal with the problem very well. In such scenarios, we use a modified algorithm to do the background modeling work. In this paper, we use edge detection to get an edge difference image just to enhance the ability of resistance illumination variation. Then we use a “multi-block temporal-analyzing LBP (Local Binary Pattern)” algorithm to do the segmentation. In the end, a connected component is used to locate the object. We also produce a hardware platform, the core of which consists of the DSP (Digital Signal Processor) and FPGA (Field Programmable Gate Array) platforms and the high-precision intelligent holder.
Highlights
Moving object detection is an important part of computer vision filed
In order to avoid the weakness and enhance its advantage, we use the edge detection method to do the same part of work, which can overcome the disadvantage of frame difference method
Canny operator edge detection can be divided into four steps: (1) Gaussian smoothing function for the purpose of smoothing to remove noise; (2) first difference convolution template, to achieve edge enhancement; (3) non-maxima suppression (NMS), intended to preserve the maximum gradient direction (The third one is the most important step in this process); and (4) bilinear threshold, to get the edge points in order to determine whether the second step of its 80 neighborhood is obtained, and make the connection
Summary
Moving object detection is an important part of computer vision filed. All of the identification and tracking parts afterwards depend on a precise and robust detection result, which makes the moving object detection step a really important portion [1,2,3,4,5]. A scanning moving object detection system is used with a scanning high definition camera as its video image sensor. We can get far more than one field of view since we made our video image sensor scan around with the support of the holder mentioned before This means we can gain richer scenes information than just using a high-definition camera. The main work we have done is detecting one or more moving objects from the video sequence gained by a high definition camera rotating around using an intelligent holder. Real-time surveillance systems, especially in the outdoor condition, have a high background complexity; that is, when the object detection method proceeds, we should consider the background complexity. The proposed method uses LBP operator and edge detection is processed to do the background modeling and moving object detection work.
Sign-in/Register to view highlights & summary 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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
