Voting-Based Motion Estimation for Real-Time Video Transmission in Networked Mobile Camera Systems

Abstract

In a video-based surveillance system, a mobile camera can provide dynamical and wider monitoring range and the video data transmitted from cooperative mobile cameras can be used to actively detect the objects of interest. However, it is a difficult task to accurately detect the moving objects from the image frames captured by the mobile cameras and the data flow of surveillance video from multiple cameras could be huge. The camera motion usually causes the shifting of static background as well as the moving objects in the captured image frames. In order to correctly estimate the motion of moving objects, a voting-based motion estimation algorithm is proposed to process the image frames captured by the mobile camera. Based on the estimation, a content-based video transmission mechanism is then implemented to further effectively decrease encoding cost and bandwidth utilization. The overall approach consists of voting-based motion estimation, moving object edges detection and content-based sampling coding at temporal and spatial scales. Without knowing the prior knowledge of camera motion, the motion estimation algorithm only utilizes the shifting information of edges of static background to estimate the camera movement. The shifting information is determined based on the voting decision of several representative regions of interest and the estimated motion is then used to compensate for the visual content obtained from the captured image frames. The proposed algorithms have been experimentally tested on several practical scenarios and it is demonstrated that, under limited network bandwidth, the transmitted image quality can be progressively achieved and the transmission bandwidth utilization can be effectively decreased.

Statistical Review of Various Object Detection Techniques

“…According to this sampling algorithm, information which is more important will be preserved prudently and also the redundant frames which are similar will be removed effectively [10].…”

“…Algorithm based on spatial coding is used to encrypt those regions having important information in frame with greater visual quality. The regions without any important information will have a very low visual quality [10]. It also includes two key parts namely (a) Set the priority to a region-based resulting in an edge detection of moving objects.…”

“…On a whole, the entire encoding process would upgrade the so called quality on those regions that are occupied at the moving objects edges but it degrades the other regions quality. Therefore, when the accessible bandwidth is under limit, the quality of those high-priority info can be maintained [10]. …”

Clausius Normalized Field-Based Shape-Independent Motion Segmentation

“…Many methods have been devised for accurate motion segmentation utilizing optical flow techniques [6], [7], motion discontinuities [8], [9], global parametric motion models [10], [11], or background removal techniques [1], [12], [13]. Although various approaches to motion segmentation have been reported, there is a wide consensus that an ideal and polished motion segmentation algorithm should do the following:…”

Data reduction based on keyframe with motion energy extraction rules

“…Motion perception is an important faculty of the brain for paying attention to and dealing with sudden events [9]. (b) In the image processing technique, moving objects are always the goal to find, and lots of mature algorithm could be used to compute motion estimation of the objects between two continuous frames in different real scene [10] [11]. Therefore, motion is a reasonable index for representing the information quantity in the frame and it also could stand for the dynamic of the monitored system or the objects.…”