Abstract
With regard to the weakness and shortage of traditional moving object segmentation method, this paper presents an effective segmentation method for moving objects in video surveillance. The difference image of color distance which is between current image and the reference background image in RGB color space is first obtained. According to the mono-modal feature of histogram of the difference image, an adaptive clustering segmentation method based on histogram is proposed. The morphology filtering is employed to remove the noise existing in the segmented binary image. An updating scheme for background image is introduced to follow the variation of illumination conditions and changes in environmental conditions. In order to remove unwanted shadows of moving regions, an efficient multi-object shadows distinguishing and eliminating method for surveillance scene was presented in this paper. Experimental results show that the proposed method is simple and effective for moving object segmentation and eliminating shadows.
Highlights
Segmentation and extraction of moving objects are basic tasks in many applications such as video surveillance (Lipton A, 1998),video retrieval (N.Hoose, 1991), intelligent transportation, and so on
Experimental results indicate that the proposed method is simple and effective for moving object segmentation and eliminating shadows
The experimental results shows that the method can segment moving object accurately and remove 98% of the shadow of moving images, and the removing shadow method requires certain difference of gray value at the junction between the shadow and the object
Summary
Segmentation and extraction of moving objects are basic tasks in many applications such as video surveillance (Lipton A, 1998) ,video retrieval (N.Hoose, 1991), intelligent transportation, and so on. The impact of noise, many light source, shadows (Y.M.Wu, 2002), transparency and shelter reduces the reliability and accuracy of the algorithm which is based on optical flow technology for moving object detection methods. Despite these difficulties, computational complexity and time-consuming further complicate the moving object detection in real-time monitoring. Image difference method was divided into the background difference method and the inter-frame difference method The former algorithm is simple but it lacks a reasonable method for the background update, which changes with illumination and other factors. The current difference method, which didn’t make full use of rich color information, is generally limited to two images of the brightness, but color information is indispensable in practical application
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
