Dim Target Detection in Infrared Image Sequences Using Accumulated Information
The targets in infrared images are usually dim and small, buried under heavy clutter and noise. Recognition of such targets is a challenging task, especially in detecting in real-time and low false rate. In this paper, we present a new target detection scheme based on accumulated information, and a neural network structure to realize this method is also introduced. Computer simulation was carried out and the satisfactory result showed substantial reduction in computational complexity.
Unable to display preview. Download preview PDF.
- M. W. Roth, “Survey of Neural Network Technology for Automatic Target Recognition,” IEEE Trans. Neural Networks, vol. 1, no. 1, pp. 2843, March 1990.Google Scholar
- Patra, J.C., Widjaja, F., Das, A., and Ee Luang Ang, “A fast neural network-based detection and tracking of dim moving targets in FLIR imagery,” Neural Networks, 2005. IJCNN ‘05. Proceedings. 2005 IEEE International Joint Conference on, Vol.5, pp:3144 – 3149, 31 July-4 Aug. 2005CrossRefGoogle Scholar
- Haixin Chen, Zhenkang Shen, and Huihuang Chen, “Detecting dim point target in infrared image sequences using probalilistic neural network,” Aerospace and Electronics Conference, 1994. NAECON 1994., Proceedings of the IEEE 1994 National, vol.1, pp:137 – 141, 23-27 May 1994Google Scholar