Infrared dim target detection based on visual attention |
| |
| Authors: | Xin Wang Guofang Lv Lizhong Xu |
| |
| Institution: | 1. College of Computer and Information Science, Fujian Agriculture and Forestry University, Fuzhou 350002, China;2. Electronic Information School, Wuhan University, Wuhan 430072, China;3. Basic Subject Department of Fujian Health College, Fuzhou 350101, China;4. Institute of Intelligent Vision and Image Information, College of Science, China Three Gorges University, Yichang 443002, China;1. Shanghai Jiao Tong University, Institute of Image Processing & Pattern Recognition, Department of Automation, 800 Dongchuan Road, Shanghai 200240, PR China;2. University of Technology, Sydney (UTS), School of Computing and Communications, NSW 2007, Australia;1. Intelligence Control, Institute for Pattern Recognition and Artificial Intelligence, Huazhong University of Science and Technology and Science and Technology on Multi-Spectral Information Processing Laboratory, Key Laboratory of Ministry of Education for Image Processing and Intelligent Control, Luoyu Road 1037, Wuhan 430074, China;2. National Key Laboratory of Science and Technology on Aerospace Intelligence Control, Beijing 100101, China;1. School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China;2. College of Computer Science, Shenyang Aerospace University, Shenyang 110136, China |
| |
| Abstract: | Accurate and fast detection of infrared (IR) dim target has very important meaning for infrared precise guidance, early warning, video surveillance, etc. Based on human visual attention mechanisms, an automatic detection algorithm for infrared dim target is presented. After analyzing the characteristics of infrared dim target images, the method firstly designs Difference of Gaussians (DoG) filters to compute the saliency map. Then the salient regions where the potential targets exist in are extracted by searching through the saliency map with a control mechanism of winner-take-all (WTA) competition and inhibition-of-return (IOR). At last, these regions are identified by the characteristics of the dim IR targets, so the true targets are detected, and the spurious objects are rejected. The experiments are performed for some real-life IR images, and the results prove that the proposed method has satisfying detection effectiveness and robustness. Meanwhile, it has high detection efficiency and can be used for real-time detection. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
