Moving object extraction based on saliency detection and adaptive background model

Abstract

For the ghost in visual background extractor (ViBe) algorithm and the influence of dynamic background, an improved ViBe algorithm is proposed to extract moving object in this paper. The way of background acquisition during modeling is improved to eliminate the ghost. Detect the saliency of the pre-M-frame, and synthetic relatively real background. Modeling with the background can avoid the generation of ghost. The selection of thresholds in the model is improved to reduce the impact of the dynamic background. Adjust the thresholds adaptively according to the background complexity. In addition, find the inner contour of extracted object to fill, which makes the detected targets more complete. Experimental results show that the presented algorithm effectively removes ghosts and enhances anti-interference ability. Compared with several existing methods, the presented algorithm has better performance.

References

[1] ChenB H, HuangS C, YenJ Y. Neurocomputing, 2018, 273: 481

[2] AngL L, HacerY K. Pattern Recognition Letters, 2018, 112: 256

[3] ZhaoL L, ChenY, ZouY, YeQ. IEEE Consumer Electronics Magazine, 2017, 6: 81

[4] YunX U, YongP, Min-TaoH U. Transducer & Microsystem Technologies, 2018, 37: 40(in Chinese)

[5] WangJ, HanJ P, LiuE Q, FanZ H, GuoD, TanD R. Journal of Guangxi University, 2017, 6: 2191(in Chinese)

[6] SuY Z, LiA H, JiangK, JinG Z. Journal of Computer-Aided Design & Computer Graphics, 2014, 2: 232(in Chinese)

[7] QuZ, HuangX L. The Imaging Science Journal, 2017, 65: 49

[8] OuyangZ B, NiuY X, XieP Y. Semiconductor optoelectronics, 2018, 2: 260(in Chinese)

[9] YangS, HaoK, DingY, LiuJ. Memetic Computing, 2018, 10: 53

[10] IshikuraK, KuritaN, ChandlerD M, OhashiG. IEEE Transactions on Image Processing, 2018, 27: 703

[11] AchantaR, HemamiS, EstradaF, SusstrunkS. Frequency-Tuned Salient Region Detection, 2009,

[12] GoyetteN, JodoinP M, PorikliF, KonradJ, IshwarP. Changedetection.net: A New Change Detection Benchmark Dataset, 2012,

[13] http://vcipl-okstate.org/pbvs/bench/Data/05/download.html

[14] http://cvrr.ucsd.edu/aton/shadow/