复杂场景多传感器图像的多目标分割算法

马超杰; 杨华; 李晓霞; 凌永顺; 吴丹; 王静雯

光电工程, 2009, 36 (1): 47, 网络出版: 2009-10-09

复杂场景多传感器图像的多目标分割算法

Multi-target Segmentation in Multi-sensor Images in Complex Scenes

论文大纲

马超杰 ^*杨华李晓霞凌永顺吴丹王静雯

作者单位

电子工程学院安徽省红外与低温等离子体重点实验室，合肥 230037

多传感器多目标分割分形特征动态边缘演化复杂场景 multi-sensor multi-target segmentation fractal feature active contour evolution complex scenes

摘要

综合应用多传感器图像灰度分布特征和分形维数特征进行目标检测、应用动态边缘演化提取目标轮廓，有效解决了复杂场景多目标分割的难题。首先根据图像的内在属性应用指定直方图进行图像增强，随后分别对可见光图像应用分形维数特征、对红外图像应用最大熵法、对激光雷达图像应用局部阈值法进行兴趣区域提取；再将各传感器图像获得的兴趣区域进行交叉验证，进一步排除背景干扰；最后把经过综合处理的目标轮廓估计作为初始生长曲线应用动态边缘演化技术最终确定目标边缘。对大量的复杂场景多传感器图像测试表明，本文提出的方法较好地保留了目标的形状特征，是一种有效的多目标分割技术。

Abstract

The multi-target segmentation in complex background could be solved effectively by synthetically utilizing multi-sensor images’ gray level distribution, fractal dimension and active contour evolution technology. Firstly, according to image inherent attribution, the images were enhanced using the histogram specification. Then the regions of interest were selected in multi-sensor images by using fractal dimension features for visible images, maximum entropy method for infrared images and the local threshold for Lidar images. The regions-of-interest obtained in multi-sensor images were across verified, so background clutter could be further eliminated. Finally, the target contour estimation could be used as the initial growth curve for active contour evolution processing, and the better target contours were obtained on the true target boundaries. A large number of segmentation tests on multi-sensor images in complex scenes prove the validity and reliability of the scheme.

参考文献

[1] David A, Forsyth Jean Ponce. Computer vision：a modern approach [M]. Beijing：Publishing House of Electronics Industry，2004：256-278.

[2] ZHANG Yu-jin. Image engineering：image Analysis：2nd ed [M]. Beijing：Tsinghua University Press，2005：73-105.

[3] Ma Chaojie, Sun Xiaoquan，Li Xiaoxia. Simulation designing of imaging laser radar guidance system [J]. Infrared and Laser Engineering，2005，34(6)：655-659.

[4] Gozales R C, Woods R E. Digital Image Processing：2nd ed [M]. Beijing：Publishing House of Electronics Industry，2002：445-452，540-541.

[5] Pentland A P. Fractal-based description of nature scences [J]. IEEE Trans on Pattern Analysis and machine Intelligence(S0162-8828)，1984，6(6)：661-674.

[6] SU Ding，ZHANG Qi-hen，TAO Bin-jie，et al. Fractal segmentation for multi-target from multi-source in complex backgrounds [J]. Infrared and Laser Engineering，2007，36(3)：387-390.

[7] Chan T F, Vese L. Active contours with out edges [J]. IEEE Transactions on Image Processing (S1057-7149)，2001，10(2)：266-277.

[8] Mumford D，Shah J. Optimal approximation by piecewise smooth functions and associated variational problems [J]. Communication on Pure and Applied Mathematics(S0010-3640)，1989，42(5)：577-685.

[9] Schwickerath A. Simultaneous Refinement of Pose and Sensor Registration [R]. Technical Report CS-97-101 in Colorado State University，1997-01.

[10] Stevens M R, Beveridge J R. Precise matching of 3-D target models to multisensor data [J]. IEEE Transactions on Image Processing(S1057-7149)，1997，6(1)：126-142.

[11] CHEN Xiao-mei, NI Guo-qiang. Remote Sensing Image Segmentation Based on Local Fractal Dimension [J]. Opto-Electronic Engineering，2008，35(1)：136-139

马超杰, 杨华, 李晓霞, 凌永顺, 吴丹, 王静雯. 复杂场景多传感器图像的多目标分割算法[J]. 光电工程, 2009, 36(1): 47. MA Chao-jie, YANG Hua, LI Xiao-xia, LING Yong-shun, WU Dan, WANG Jing-wen. Multi-target Segmentation in Multi-sensor Images in Complex Scenes[J]. Opto-Electronic Engineering, 2009, 36(1): 47.

复杂场景多传感器图像的多目标分割算法

关于本站 Cookie 的使用提示

全站搜索

复杂场景多传感器图像的多目标分割算法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索