Title: Improved global optical flow estimation with mean shift algorithm for target detection

Authors: Zhonghua Wang; Chunyong Li; Qingping Liu

Addresses: Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition, Nanchang Hangkong University, Nanchang, Jiangxi Province, 330063, China; School of Information and Engineering, Nanchang Hangkong University, Nanchang, Jiangxi Province 330063, China ' Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition, Nanchang Hangkong University, Nanchang, Jiangxi Province, 330063, China; School of Information and Engineering, Nanchang Hangkong University, Nanchang, Jiangxi Province 330063, China ' Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition, Nanchang Hangkong University, Nanchang, Jiangxi Province, 330063, China; School of Information and Engineering, Nanchang Hangkong University, Nanchang, Jiangxi Province 330063, China

Abstract: In view of the problem that the global optical flow algorithm cannot acquire accurate motion parameter estimation at a low-gradient value, an improved method has been presented in order to enhance the self-adaptive ability. The proposed method is divided into three steps: firstly, the Gaussian filter is used to restrain the background noise; secondly, the optical basic constraint weighted function is modified to acquire targets area; finally, the morphological filtering and mean shift segmentation algorithm is adopted to reduce the false alarm rate. Compared with other algorithms, the experiment results show that the proposed method can improve the self-adaptive ability and the detection rate.

Keywords: target detection; optical flow constraints; mean shift; threshold; motion parameter estimation; Gaussian filter; morphological filtering; infrared images; moving objects; object detection; infrared imaging detection systems.

DOI: 10.1504/IJWMC.2015.070936

International Journal of Wireless and Mobile Computing, 2015 Vol.8 No.4, pp.323 - 328

Available online: 27 Jul 2015 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article