摘要
A fast object detection method based on object region dissimilarity and 1-D AGADM(one dimensional average gray absolute difference maximum) between object and background isproposed for real-time defection of small offshore targets. Then computational complexity, antinoiseperformance, the signal-to-noise ratio (SNR) gain between original images and their results as afunction of SNR of original images and receiver operating characteristic (ROC) curve are analyzed andcompared with those existing methods of small target detection such as two dimensional average grayabsolute difference maximum (2-D AGADM), median contrast filter algorithm and multi-level filteralgorithm. Experimental results and theoretical analysis have shown that the proposed method hasfaster speed and more adaptability to small object shape and also yields improved SNR performance.
A fast object detection method based on object region dissimilarity and 1-D AGADM (one dimensional average gray absolute difference maximum) between object and background is proposed for real-time defection of small offshore targets. Then computational complexity, antinoise performance, the signal-to-noise ratio (SNR) gain between original images and their results as a function of SNR of original images and receiver operating characteristic (ROC) curve are analyzed and compared with those existing methods of small target detection such as two dimensional average gray absolute difference maximum (2-D AGADM), median contrast filter algorithm and multi-level filter algorithm. Experimental results and theoretical analysis have shown that the proposed method has faster speed and more adaptability to small object shape and also yields improved SNR performance.
出处
《自动化学报》
EI
CSCD
北大核心
2005年第3期427-433,共7页
Acta Automatica Sinica
基金
National Defense Science Foundation of P.R.China
关键词
小目标检测
快速算法
区域特性
海面
Algorithms
Automatic target recognition
Computational complexity
Image analysis
One dimensional
Signal detection
Signal receivers
Signal to noise ratio
Two dimensional
