A novel fast detection method of infrared LSS-Target in complex urban background

作者：Wu, Yanfeng^*; Sun, Haijiang; Liu, Peixun

来源：International Journal of Wavelets, Multiresolution and Information Processing, 2018, 16(1): 1850008.

DOI：10.1142/S021969131850008X

• Adaptive threshold segmentation
• region growth
• small target detection

LSS-Target (the Low altitude, Slow speed and Small Target) is likely to be a threat to the observation platform, thus infrared LSS-Target detection is an urgent task. LSS-Target is a challenging issue due to the low Signal-to-Noise Ratio (SNR) and sophisticated background. Motivated by the analysis of infrared imaging characteristics, this paper proposes a novel fusion method for IR LSS-Target detection with complex urban background, which is suitable for precise guidance and self defense. First, an adaptive threshold segmentation based on accumulative histogram and maximum likelihood estimation are utilized to eliminate the clutter and improve SNR of the initial image. Second, a template is set up to identify the seed points in the image. Third, a constrained four criteria region growth algorithm is performed to separate the entire regions. Finally, the confidence measure is constructed, which can eliminate false targets and the background edges. Experimental results show that the method in this paper can screen out the real LSS-Target in real time with high accuracy under sophisticated background.

• 出版日期2018-1
• 单位中国科学院; 中国科学院长春光学精密机械与物理研究所; 中国科学院大学