[1]韩 彤,曹铁勇,郑云飞,等.迷彩伪装目标检测的视觉特征偏好研究[J].计算机技术与发展,2023,33(12):193-199.[doi:10. 3969 / j. issn. 1673-629X. 2023. 12. 027]
　HAN Tong,CAO Tie-yong,ZHENG Yun-fei,et al.Research on Visual Feature Bias of Camouflaged Object Detection[J].,2023,33(12):193-199.[doi:10. 3969 / j. issn. 1673-629X. 2023. 12. 027]
点击复制

迷彩伪装目标检测的视觉特征偏好研究()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
33
期数:
2023年12期
页码:
193-199
栏目:
人工智能
出版日期:
2023-12-10

文章信息/Info

Title:
Research on Visual Feature Bias of Camouflaged Object Detection
文章编号:
1673-629X(2023)12-0193-07
作者:
韩 彤1; 2 ; 曹铁勇1 ; 郑云飞3 ; 王 杨1 ; 陈 雷1 ; 王烨奎4 ; 付炳阳1
1. 陆军工程大学 指挥控制工程学院,江苏 南京 210007;
2. 95911 部队,甘肃 酒泉 735000;
3. 陆军炮兵防空兵学院,江苏 南京 211100;
4. 31401 部队,吉林 长春 130000)
Author(s):
HAN Tong1; 2 ; CAO Tie-yong1 ; ZHENG Yun-fei3 ; WANG Yang1 ; CHEN Lei1 ; WANG Ye-kui4 ; FU Bing-yang1
1. School of Command & Control Engineering,Army Engineering University of PLA,Nanjing 210007,China;
2. Unit 95911,Jiuquan 735000,China;
3. The Army Artillery and Defense Academy of PLA,Nanjing 211100,China;
4. Unit 31401,Changchun 130000,China
关键词:
目标检测; 迷彩伪装; 特征解耦; 人类视觉系统; 卷积神经网络
Keywords:
object detection; camouflage; feature decoupling; human visual system; convolutional neural networks
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2023. 12. 027
摘要:
迷彩伪装通过设计颜色和纹理图案来破坏目标的固有形状,其检测依赖的视觉特征应与常规目标不同。 然而卷积神经网络的黑盒性质使得不同视觉特征对模型识别的贡献程度无法获知。 为解决上述问题,借鉴人类视觉系统设计了一种适用于伪装场景的视觉特征解耦方法,解耦并分析目标检测模型在颜色、纹理和形状特征上的偏好程度。 具体来说,使用消除单一特征并保留其余特征的解耦框架,以模型的性能下降情况作为偏向性的衡量标准,通过灰度化处理消除图像的颜色特征,使用区域置乱破坏目标的纹理特征,对目标轮廓取内接形状以改变目标的形状特征。 在公开的迷彩伪装人员数据集和常规人员检测数据集上分别进行实验,结果显示,迷彩伪装目标的检测主要依赖纹理,常规目标的检测主要依赖形状。
Abstract:
Camouflage uses designed color and texture patterns to disrupt the inherent shape of the target,so the visual features that its detection relies on should be different from those of conventional targets. However,the black box nature of convolutional neural networksmakes it impossible to know the contribution of different visual features to model recognition. To solve this problem,a new visual featuredecoupling method was designed based on the human visual system,which is suitable for camouflage scenes. This method decouples andanalyzes the preference degree of object detection models on color,texture,and shape features. Specifically,an analysis architecture wasused to eliminate a single feature while retaining the remaining features,and the performance degradation of the model was used as ameasure of bias. Grayscale processing was used to eliminate the color features of images, region scrambling was used to disrupt thetexture features of targets,and the inner shapes of targets were extracted to change their shape features. Experiments were conducted onpublicly available datasets of camouflaged personnel and conventional personnel detection,respectively,and the results showed that thedetection of camouflaged object mainly relies on texture,while the detection of conventional object mainly relies on shape.

相似文献/References:

[1]刘晓明 李毓蕙 高燕 郑华强.基于目标区域清晰显示的H.264编码策略[J].计算机技术与发展,2010,(06):29.
　LIU Xiao-ming,LI Yu-hui,GAO Yan,et al.A Coding Strategy of H.264 Based on High-definition Display of Target Region[J].,2010,(12):29.
[2]刘翔 吴谨 祝愿博 康晓晶.基于视频序列的目标检测与跟踪技术研究[J].计算机技术与发展,2009,(11):179.
　LIU Xiang,WU Jin,ZHU Yuan-bo,et al.A Study of Object Detecting and Tracking Based on Video Sequences[J].,2009,(12):179.
[3]曙光 张超 蔡则苏.基于改进的混合高斯模型的目标检测方法[J].计算机技术与发展,2012,(07):60.
　SHU Guang,ZHANG Chao,CAI Ze-su.Target Detection Method Based on Improved Gaussian Mixture Model[J].,2012,(12):60.
[4]刘洁,李目,周少武.一种混沌混合粒子群优化RBF神经网络算法[J].计算机技术与发展,2013,(08):181.
　LIU Jie[],LI Mu[],ZHOU Shao-wu[].An Algorithm of Chaotic Hybrid Particle Swarm Optimization Based on RBF Neural Network[J].,2013,(12):181.
[5]蒋翠清,孙富亮,吴艿芯. 基于相对欧氏距离的背景差值法视频目标检测[J].计算机技术与发展,2015,25(01):37.
　JIANG Cui-qing,SUN Fu-liang,WU Nai-xin. Video Object Detection of Background Subtraction Method Based on Relative Euclidean Distance[J].,2015,25(12):37.
[6]卢官明,衣美佳. 步态识别关键技术研究[J].计算机技术与发展,2015,25(07):100.
　LU Guan-ming,YI Mei-jia. Research on Critical Techniques in Gait Recognition[J].,2015,25(12):100.
[7]高翔,朱婷婷,刘洋. 多摄像头系统的目标检测与跟踪方法研究[J].计算机技术与发展,2015,25(07):221.
　GAO Xiang,ZHU Ting-ting,LIU Yang. Research of Target Detection and Tracking Method for Multi-camera System[J].,2015,25(12):221.
[8]章文洁[][],黄旻[],张桂峰[]. 滤光片多光谱成像中运动目标场景误配准修正[J].计算机技术与发展,2016,26(01):18.
　ZHANG Wen-jie[][],HUANG Min[],ZHANG Gui-feng[]. Misregistration Correction for Moving Object Scene in Filter-type Multispectral Imaging[J].,2016,26(12):18.
[9]施泽浩,赵启军.基于全卷积网络的目标检测算法[J].计算机技术与发展,2018,28(05):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
　SHI Ze-hao,ZHAO Qi-jun.Object Detection Algorithm Based on Fully Convolutional Neural Network[J].,2018,28(12):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
[10]张夏清,茅耀斌. 一种改进的ViBe背景提取算法[J].计算机技术与发展,2016,26(07):36.
　ZHANG Xia-qing,MAO Yao-bin. An Improved ViBe Background Generation Method[J].,2016,26(12):36.
[11]王烨奎,曹铁勇,王 杨,等.CAMOU-YOLO:一种迷彩伪装目标检测模型[J].计算机技术与发展,2022,32(12):29.[doi:10. 3969 / j. issn. 1673-629X. 2022. 12. 005]
　WANG Ye-kui,CAO Tie-yong,WANG Yang,et al.CAMOU-YOLO:A Camouflaged Object Detection Model[J].,2022,32(12):29.[doi:10. 3969 / j. issn. 1673-629X. 2022. 12. 005]

更新日期/Last Update: 2023-12-10