Robust foreground modelling to segment and detect multiple moving objects in videos

Abstract

Last decade has witnessed an ever increasing number of video surveillance installations due to the rise of security concerns worldwide. With this comes the need for video analysis for fraud detection, crime investigation, traffic monitoring to name a few. For any kind of video analysis application, detection of moving objects in videos is a fundamental step. In this paper, an efficient foreground modelling method to segment multiple moving objects is implemented. Proposed method significantly reduces noise thereby accurately segmenting region of interest under dynamic conditions while handling occlusion to a large extent. Extensive performance analysis shows that the proposed method was found to give far better results when compared to the de facto standard as well as relatively new approaches used for
 moving object detection.

Threshold adaptation and XOR accumulation algorithm for objects detection

“…MaxValue is the highest grayscale value is (255). In ( 9), the pixel intensity threshold is determined, so that the pixel values that are less than 30 are considered as black (0); otherwise, they should be white (1). This is due to the saturation phenomena of human vision.…”

“…The measurement of precision (quality) is the pixels ratio of the retrieved pixels as (1). It was used to assess recently the preliminary extraction techniques objectively.…”

“…Changes in scene and motion detection are two basic steps that play an essential and guiding role in simple and complex environments, where most outdoor surveillance videos are recorded [1]- [6]. However, the variation of the static background in some unfamiliar designs still make the mission of correctly extracting the foreground from the background a widely occurring challenge in surveillance video analysis [7]- [11].…”