Locally Statistical Dual-Mode Background Subtraction Approach

Abstract

Due to the variety of background model in the real world, detecting changes in a video cannot be addressed exhaustively by a simple background subtraction method, especially with several motion detection challenges, such as dynamic background, camera jitter, intermittent object motion, and so on. In this paper, we propose an efficient background subtraction method, namely locally statistical dual-mode (LSD), for detecting moving objects in video-based surveillance systems. The method includes a local intensity pattern comparison algorithm for foreground segmentation by analyzing the homogeneity of intensity patterns of the input frame and the background model, in which the homogeneity is calculated by the mean and standard deviation of pixel intensity. Besides that, a dual-mode scheme is developed to temporally update the background model for the short-and long-term scenarios corresponding to sudden and gradual changes in the background. The advantage of this scheme is the allowance of updating the model in both pixel-and framewise manners simultaneously. The parameters used in both the local intensity pattern comparison algorithm and the dual-mode background model updating scheme are estimated for every input frame consecutively based on local and global statistical information of segmentation result. In experiments, the proposed LSD method is extensively evaluated on the Wallflower and CDnet2014 datasets; and remarkable performance demonstrates its preeminence to the many state-of-the-art background subtraction approaches in terms of segmentation accuracy and computational complexity. INDEX TERMS Motion detection, background subtraction, background modeling, moving object detection, video segmentation, locally statistical dual-mode updating. THIEN HUYNH-THE (S'15-M'19) received the B.S. degree in electronics and telecommunication engineering and the M.Sc. degree in electronics engineering from the

Highly efficient neoteric histogram–entropy‐based rapid and automatic thresholding method for moving vehicles and pedestrians detection

“…These include subsense‐based foreground detection (SuBSENSE [49]), improved foreground detection based on visual background extractor (ViBe++ [50]), motion‐based superpixel‐level‐based background estimation algorithm (STC [53]), foreground detection based on block‐based structure in dynamic scene (HVR [54]), foreground detection based on spatio‐temporal classification (SuperBE [51]), background subtraction based on the Gaussian mixture model (block‐based [52]), an efficient local binary pattern for background subtraction (ESILBP [55]), dual‐target non‐parametric background modelling method‐based foreground detection (DTNBM [56]), and background subtraction based on local intensity pattern comparison algorithm (SBS [57]). The performance parameters (recall, precision, and f‐measure) for the HEBT method are listed in Table 5 which also includes similar results published for the referred methods by the other authors [49–57]. According to the results in Table 5, it can be easily noticed that all the performance parameters are highest for the HEBT method recall ( 0.8942 ), precision ( 0.8854 ), f‐measure ( 0.8887 ) than all the differently combined threshold‐based segmentation methods [49–57].…”

“…In these comparison studies, all the thresholding methods including our own HEBT method, are implemented with the three‐frame differencing segmentation method (the one used in the work of [2]) for object detection from complex and coarse images. In another set of experimental analysis, the performance of the HEBT method (implemented with the three‐frame differencing segmentation method) is compared with several published works [49–58], which used the same datasets, i.e. CD‐2012, CD‐2014, and Wallflower, but employed different thresholding and object segmentation methods.…”

Moving Target Detection with Modified Logarithm Background Subtraction and Its Application to the GF-3 Spotlight Mode

“…In this section, the proposed method is described in detail. The background subtraction method is first developed and successfully applied in the optical video surveillance domain [18,19], a logarithm kind method can be found in [20], but such an idea is first introduced in SAR moving target detection by our team (to our knowledge) [11]. The main idea of the logarithm background subtraction method is simple.…”

Online Semantic Object Segmentation for Vision Robot Collected Video

“…For video object segmentation algorithms, how to define and discover the desired objects is the key problem. When the camera is static, foreground segmentation are defined as background subtraction problem [14], [50]. Papazoglou et al [30] defined the objects according to the motion cues and designed a fast strategy to estimate whether a pixel is inside the object, then the segmentation will be refined in whole video scope with appearance model and spatial constraint.…”