Camouflaged object detection based on Convnextv2 and texture-edge guidance

doi:10.3785/j.issn.1008-973X.2025.08.019

Journal of ZheJiang University (Engineering Science)

2025, Vol. 59

Issue (8): 1718-1726 DOI: 10.3785/j.issn.1008-973X.2025.08.019

Camouflaged object detection based on Convnextv2 and texture-edge guidance

Jiarui FU1(

),Zhaofei LI1,2,3,*(

),Hao ZHOU1,Wei HUANG1

1. College of Automation and Information Engineering, Sichuan University of Science and Engineering, Yibin 644000, China
2. Intelligent Perception and Control Key Laboratory of Sichuan Province, Yibin 644000, China
3. Key Laboratory of Higher Education of Sichuan Province for Enterprise Informationalization and Internet of Things, Yibin 644000, China

Download:

HTML

PDF(1894KB) HTML
Export: BibTeX | EndNote (RIS)

Abstract

A camouflaged object detection method based on Convnextv2 and texture-edge guidance was proposed in order to address the issue of insufficient expression and processing of edge features of targets and unique texture feature information in corresponding scenarios in camouflaged object detection. The texture encoding module was used to extract texture features from input images, which were fused with the edge features extracted by the backbone network to generate texture-edge features of the images. The texture-edge features were integrated into the backbone features to locate the true position of the target through the designed texture-edge guided attention module. A feature fusion module was employed for multi-level feature fusion, and a multi-level supervision approach was adopted to design the overall loss function. Experiments on three public datasets (CAMO, COD10K, NC4K) and the camouflage mixed dataset MICAI_TE showed that the algorithm achieved optimal comprehensive performance.

Key words： camouflage object detection texture-edge-guided feature fusion Convnextv2 feature extraction texture edge attention mechanism

Received: 08 August 2024 Published: 28 July 2025

CLC:

TP 391

Fund: 企业信息化与物联测控技术四川省重点实验室资助项目（2022WZJ02）；自贡市重点科技计划资助项目（2019YYJC15）；四川轻化工大学科研基金资助项目（2020RC32）；四川轻化工大学研究生课程建设项目（AL202213，SZ202310）；四川轻化工大学教学改革项目（2024KCSZ-ZY03，2024KCSZ-KC09，JG-24064）.

Corresponding Authors: Zhaofei LI E-mail: izayoisakur_ray@163.com;lizhaofei825@163.com

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Jiarui FU
	Zhaofei LI
	Hao ZHOU
	Wei HUANG

Cite this article:

Jiarui FU,Zhaofei LI,Hao ZHOU,Wei HUANG. Camouflaged object detection based on Convnextv2 and texture-edge guidance. Journal of ZheJiang University (Engineering Science), 2025, 59(8): 1718-1726.

URL:

https://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2025.08.019 OR https://www.zjujournals.com/eng/Y2025/V59/I8/1718

基于Convnextv2与纹理边缘引导的伪装目标检测

为了解决伪装目标检测中目标的边缘特征及对应场景下独特纹理特征信息表达处理不足的问题，提出基于Convnextv2与纹理边缘引导的伪装目标检测算法. 通过纹理编码模块在输入图片上提取纹理特征，与主干网络提取的边缘特征进行融合，生成图片的纹理-边缘特征. 通过设计的纹理边缘引导的注意力模块，将纹理-边缘特征融入主干特征以定位目标的真实位置. 利用特征融合模块进行多层次特征融合，采用多级监督的方式，设计总的损失函数. 在3个公开数据集CAMO、COD10K、NC4K和迷彩伪装混合数据集MICAI_TE上的实验表明，该算法的综合性能最优.

关键词： 伪装目标检测, 纹理边缘引导特征融合, Convnextv2, 特征提取, 纹理边缘注意力机制

Fig.1 Network structure of CTEGAFNet

Fig.2 Structure of texture encode module

Fig.3 Structure of edge encode module

Fig.4 Structure of texture-edge guided attention module

Fig.5 Structure of fusion module

Tab.1 Comparison result of CTEGAFNet and other 11 methods in CAMO and COD10K

Tab.2 Comparison result of CTEGAFNet and other 11 methods in NC4K and MICAI_TE

Fig.6 Visual comparison of detection result obtained by other 10 different COD methods

Fig.7 4-Octopus original image

Fig.8 Structure of Att (Without T-Edge) module

Tab.3 Result of ablation study conducted on CAMO dataset

Fig.9 Comparison of visual result of different models in ablation study

Fig.10 Structure of Base+Fus


[1]	张冬冬, 王春平, 付强伪装目标检测研究进展[J]. 激光杂志, 2024, 45 (3): 1- 13 ZHANG Dongdong, WANG Chunping, FU Qiang Research developments in camouflage object detection[J]. Laser Journal, 2024, 45 (3): 1- 13

[2]	SUN Y, CHEN G, ZHOU T, et al. Context-aware cross-level fusion network for camouflaged object detection [EB/OL]. [2025-05-29]. https://arxiv.org/abs/2105.12555.

[3]	REN J, HU X, ZHU L, et al Deep texture-aware features for camouflaged object detection[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2021, 33 (3): 1157- 1167

[4]	JI G P, FAN D P, CHOU Y C, et al Deep gradient learning for efficient camouflaged object detection[J]. Machine Intelligence Research, 2023, 20 (1): 92- 108 doi: 10.1007/s11633-022-1365-9

[5]	SUN Y, WANG S, CHEN C, et al. Boundary-guided camouflaged object detection [C]// International Joint Conference on Artificial Intelligence. Shenzhen: Morgan Kaufmann, 2022: 335-1341.

[6]	CHEN Tianrun, ZHU Lanyun, DENG Chaotao, et al. SAM2-Adapter: evaluating and adapting segment anything 2 in downstream tasks: camouflage, shadow, medical image segmentation, and more [EB/OL]. [2024-10-19]. https://arxiv.org/abs/2408.04579.

[7]	NIKHILA R, VALENTIN G, HU Y, et al. SAM 2: segment anything in images and videos [EB/OL]. [2024-10-19]. https://arxiv.org/abs/2408.00714.

[8]	CHEN G, WANG H, CHEN K, et al A survey of the four pillars for small object detection: multiscale representation, contextual information, super-resolution, and region proposal[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2020, 52 (2): 936- 953

[9]	LIU Y, LI H, CHENG J, et al MSCAF-net: a general framework for camouflaged object detection via learning multi-scale context-aware features[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2023, 33 (9): 4934- 4947 doi: 10.1109/TCSVT.2023.3245883

[10]	WOO S, DEBNATH S, HU R, et al. Convnext v2: co-designing and scaling convnets with masked autoencoders [C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver: IEEE, 2023: 16133-16142.

[11]	HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition [C]// IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778.

[12]	DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16x16 words: Transformers for image recognition at scale [EB/OL]. [2025-05-29]. https://arxiv.org/abs/2010.11929.

[13]	WU Z, SU L, HUANG Q. Cascaded partial decoder for fast and accurate salient object detection [C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 3907-3916.

[14]	ZHAO J X, LIU J J, FAN D P, et al. EGNet: edge guidance network for salient object detection [C]// IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2019: 8779-8788.

[15]	WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module [C]// European Conference on Computer Vision. Munich: Springer, 2018: 3-19.

[16]	MILLETARI F, NAVAB N, AHMADI S A. V-net: fully convolutional neural networks for volumetric medical image segmentation [C]// International Conference on 3D Vision. California: IEEE, 2016: 565-571.

[17]	LE T N, NGUYEN T V, NIE Z, et al Anabranch network for camouflaged object segmentation[J]. Computer Vision and Image Understanding, 2019, 184: 45- 56 doi: 10.1016/j.cviu.2019.04.006

[18]	FAN D P, JI G P, SUN G, et al. Camouflaged object detection [C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 2777-2787.

[19]	LV Y, ZHANG J, DAI Y, et al. Simultaneously localize, segment and rank the camouflaged objects [C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 11591-11601.

[20]	FAN D P, JI G P, CHENG M M, et al Concealed object detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 44 (10): 6024- 6042

[21]	XING H, GAO S, WANG Y, et al Go closer to see better: camouflaged object detection via object area amplification and figure-ground conversion[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2023, 33 (10): 5444- 5457 doi: 10.1109/TCSVT.2023.3255304

[22]	JIA Q, YAO S, LIU Y, et al. Segment, magnify and reiterate: detecting camouflaged objects the hard way [C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 4713-4722.

[23]	SONG Z, KANG X, WEI X, et al Fsnet: focus scanning network for camouflaged object detection[J]. IEEE Transactions on Image Processing, 2023, 32: 2267- 2278 doi: 10.1109/TIP.2023.3266659

[24]	HU X, WANG S, QIN X, et al. High-resolution iterative feedback network for camouflaged object detection [C]// AAAI Conference on Artificial Intelligence. Washington: AAAI, 2023, 37(1): 881-889.

[1]	Zhuguo ZHOU,Yujun LU,Liye LV. Improved YOLOv5s-based algorithm for printed circuit board defect detection[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(8): 1608-1616.

[2]	Liming LIANG,Pengwei LONG,Jiaxin JIN,Renjie LI,Lu ZENG. Steel surface defect detection algorithm based on improved YOLOv8s[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(3): 512-522.

[3]	Youping FU,Hang ZHANG,Menghan LI,Jun MENG. Identity recognition based on multi-dimensional features of pulse wave signals[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(3): 566-576.

[4]	Junjie LIN,Yaguang ZHU,Chunchao LIU,Haoyang LIU. Digital twin system of legged robot for mobile operation[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(9): 1956-1969.

[5]	Haijun WANG,Tao WANG,Cijun YU. CFRP ultrasonic detection defect identification method based on recursive quantitative analysis[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(8): 1604-1617.

[6]	Kang HAN,Hongfei ZHAN,Junhe YU,Rui WANG. Rolling bearing fault diagnosis based on dilated convolution and enhanced multi-scale feature adaptive fusion[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(6): 1285-1295.

[7]	Bo ZHONG,Pengfei WANG,Yiqiao WANG,Xiaoling WANG. Survey of deep learning based EEG data analysis technology[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(5): 879-890.

[8]	Fanrui LUO,Zhenyu LIU,Jiahui REN,Xiaoyu LI,Yang CHENG. Lightweight LiDAR-IMU odometry based on improved Kalman filter[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(11): 2280-2289.

[9]	Lin JIANG,Lin-rui LIU,An-na ZHOU,Lu HAN,Ping-yuan LI. Improved ORB-SLAM algorithm based on motion prediction[J]. Journal of ZheJiang University (Engineering Science), 2023, 57(1): 170-177.

[10]	Yan BIAN,Yu-sheng GONG,Guo-peng MA,Chang WANG. Water extraction from unmanned aerial vehicle remote sensing images[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(4): 764-774.

[11]	Ze-xin XU,Li-juan DUAN,Wen-jian WANG,Qing EN. Code vulnerability detection method based on contextual feature fusion[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(11): 2260-2270.

[12]	Fang LIU,Zhen WANG,Rui-di LIU,Kai WANG. Short-term forecasting method of wind power generation based on BP neural network with combined loss function[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(3): 594-600.

[13]	Yi-xiong FENG,Kang-jie LI,Yi-cong GAO,Hao ZHEN,Jian-rong TAN. Shaft surface defect detection method based on feature and morphology reconstruction[J]. Journal of ZheJiang University (Engineering Science), 2020, 54(3): 427-434.

[14]	Mei-ying QIAO,Xia-xia TANG,Shu-hao YAN,Jian-ke SHI. Bearing fault diagnosis based on improved sparse filter and deep network fusion[J]. Journal of ZheJiang University (Engineering Science), 2020, 54(12): 2301-2309.

[15]	Xiao-hu ZHAO,Liang-fei YIN,Cheng-long ZHAO. Image captioning based on global-local feature and adaptive-attention[J]. Journal of ZheJiang University (Engineering Science), 2020, 54(1): 126-134.

Viewed

Full text

Abstract

Cited

Shared

Discussed