A fast-saliency method for real-time infrared small target detection |
| |
| Affiliation: | 1. College of Computer and Information, Hohai University, Nanjing, Jiangsu 211100, China;2. Jiangsu Key Laboratory of Image and Video Understanding for Social Safety, Nanjing University of Science and Technology, Nanjing, Jiangsu 210094, China;3. School of Physics and Technology, Nanjing Normal University, Nanjing, Jiangsu 210023, China;1. Institute of Aerospace Information Technology, Zhejiang University, Yuquan Campus, Hangzhou, Zhejiang 310027, PR China;2. Joint Laboratory of Flight Vehicle Ocean-based Measurement and Control, Zhejiang University, Yuquan Campus, Hangzhou, Zhejiang 310027, PR China;3. Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong;1. College of Communication Engineering, Chongqing University, Chongqing 400044, China;2. Key Laboratory of Beam Control, Chinese Academy of Sciences, Chengdu 610209, China;1. College of Computer and Information, Hohai University, Nanjing, Jiangsu 211100, China;2. Jiangsu Key Laboratory of Spectral Imaging and Intelligent Sense, Nanjing University of Science and Technology, Nanjing, Jiangsu 210094, China;3. School of Physics and Technology, Nanjing Normal University, Nanjing, Jiangsu 210023, China;1. Faculty of Engineering, Shahid Bahonar University of Kerman, Kerman, Iran;2. Department of Electrical Engineering, Faculty of Engineering, University of Isfahan, Isfahan, Iran;3. Department of Mechatronics Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran;1. School of Computer Science, Northeast Electric Power University, Jilin, PR China;2. School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, PR China;3. National Key Laboratory of Science and Technology on Multi-spectral Information Processing, Wuhan, PR China;4. Xi’an Modern Control Technology Research Institute, Xi’an, PR China |
| |
| Abstract: | Infrared small target detection plays an important role in applications including military reconnaissance, early warning and terminal guidance. In this paper, we present a fast method, called fast-saliency, with very low computational complexity, for real-time small target detection in single image frame under various complex backgrounds. Different from traditional algorithms, the proposed method is inspired by a recent research on visual saliency detection indicating that small salient signals could be well detected by a gradient enhancement operation combined with Gaussian smoothing, which is able to delineate regions of small targets in infrared images. Concisely, there are only four simple steps contained in fast-saliency. In order, they are gradient operation, square computation, Gaussian smoothing and automatic thresholding, representing the four procedures as highpass filtering, target enhancement, noise suppression and target segmentation, respectively. Especially, for the most crucial step, gradient operation, we innovatively propose a 5 × 5 facet kernel operator that holds the key for separating the small targets from backgrounds. To verify the effectiveness of our proposed method, a set of real infrared images covering typical backgrounds with sea, sky and ground clutters are tested in experiments. The results demonstrate that it outperforms the state-of-the-art methods not only in detection accuracy, but also in computation efficiency. |
| |
| Keywords: | Infrared image Small target Real-time detection Visual saliency Computation efficiency |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
