红外与激光工程, 2005, 34 (5): 587, 网络出版: 2006-05-25
新的红外图像小目标检测方法
Novel method of small target detection in infrared images
小目标检测与分割 LOG算子 背景粗糙度 区域生长 Small target detection and segmentation LOG operator Roughness of the background Region growing
摘要
在分析了海空背景下舰船目标红外图像特征的基础上,提出了一种基于背景粗糙度估计的红外图像小目标自适应检测算法,该算法利用LOG算子检测目标的大致轮廓,确定目标的中心点作为区域生长的种子点,可以看作是为后续处理压缩数据量的一种方法.它可以减少运算量,提高检测.速度,抑制对不必要的种子点的区域生长,提高目标的检测概率.
Abstract
Based on the characteris tic analysis of infrared naval vessel target under the sea-sky background, a new adaptive infrared small target detection method is developed, which uses the LOG operator to detect the outline of the target and then decides its center point as the seed point in the region growing procedure. In the proposed approach, the parameters of the LOG operator are adaptively determined using the roughness estimation of the background.This procedure is a preprocessing method of the detection and recognition of the small target, and it can reduce the computation requirement, improve the detection speed, restrain the unnecessary seed points in region growing process, and increase the possibility of target detection.
参考文献
[2] . Scattering from a 2D sea fractal surface:fractal analysis of the scattered signal[J]. IEEE Trans on Antennas and Propagation, 2002, 50(7): 912-925.
[3] . Enhanced detection of a target in a sea clutter environment using a stepped,ultra-wideband signal and E-pulse cancellation[J]. IEEE Trans on Antennas and Propagation, 2001, 49(8): 1166-1173.
[5] . Detection of intensity changes with subpixel accuracy using laplacian-gaussian masks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(5): 651-664.
崔玉平, 刘永才. 新的红外图像小目标检测方法[J]. 红外与激光工程, 2005, 34(5): 587. 崔玉平, 刘永才. Novel method of small target detection in infrared images[J]. Infrared and Laser Engineering, 2005, 34(5): 587.