A Survey of Camouflaged Object Detection and Beyond
Camouflaged object detection (COD) refers to the task of identifying and segmenting objects that blend seamlessly into their surroundings, posing a significant challenge for computer vision systems. In recent years, COD has garnered widespread attention due to its potential applications in surveilla...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2024-12-01
|
| Series: | CAAI Artificial Intelligence Research |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.26599/AIR.2024.9150044 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841550219684085760 |
|---|---|
| author | Fengyang Xiao Sujie Hu Yuqi Shen Chengyu Fang Jinfa Huang Longxiang Tang Ziyun Yang Xiu Li Chunming He |
| author_facet | Fengyang Xiao Sujie Hu Yuqi Shen Chengyu Fang Jinfa Huang Longxiang Tang Ziyun Yang Xiu Li Chunming He |
| author_sort | Fengyang Xiao |
| collection | DOAJ |
| description | Camouflaged object detection (COD) refers to the task of identifying and segmenting objects that blend seamlessly into their surroundings, posing a significant challenge for computer vision systems. In recent years, COD has garnered widespread attention due to its potential applications in surveillance, wildlife conservation, autonomous systems, and more. While several surveys on COD exist, they often have limitations in terms of the number and scope of papers covered, particularly regarding the rapid advancements made in the field since mid-2023. To address this void, we present the most comprehensive review of COD to date, encompassing both theoretical frameworks and practical contributions to the field. This paper explores various COD methods across four domains, including both image-level and video-level solutions, from the perspectives of traditional and deep learning approaches. We thoroughly investigate the correlations between COD and other camouflaged scenario methods, thereby laying the theoretical foundation for subsequent analyses. Furthermore, we delve into novel tasks such as referring-based COD and collaborative COD, which have not been fully addressed in previous works. Beyond object-level detection, we also summarize extended methods for instance-level tasks, including camouflaged instance segmentation, counting, and ranking. Additionally, we provide an overview of commonly used benchmarks and evaluation metrics in COD tasks, conducting a comprehensive evaluation of deep learning-based techniques in both image and video domains, considering both qualitative and quantitative performance. Finally, we discuss the limitations of current COD models and propose 9 promising directions for future research, focusing on addressing inherent challenges and exploring novel, meaningful technologies. This comprehensive examination aims to deepen the understanding of COD models and related methods in camouflaged scenarios. For those interested, a curated list of COD-related techniques, datasets, and additional resources can be found at https://github.com/ChunmingHe/awesome-concealed-object-segmentation. |
| format | Article |
| id | doaj-art-cbe4736ff32f47dba0db8fa53bf7fc87 |
| institution | Kabale University |
| issn | 2097-194X 2097-3691 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | CAAI Artificial Intelligence Research |
| spelling | doaj-art-cbe4736ff32f47dba0db8fa53bf7fc872025-01-10T06:44:32ZengTsinghua University PressCAAI Artificial Intelligence Research2097-194X2097-36912024-12-013915004410.26599/AIR.2024.9150044A Survey of Camouflaged Object Detection and BeyondFengyang Xiao0Sujie Hu1Yuqi Shen2Chengyu Fang3Jinfa Huang4Longxiang Tang5Ziyun Yang6Xiu Li7Chunming He8Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, ChinaTsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, ChinaTsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, ChinaTsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, ChinaSchool of Electrical and Computer Engineering, Peking University, Shenzhen 518055, ChinaTsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, ChinaDepartment of Biomedical Engineering, Duke University, Durham, NC 27708, USATsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, ChinaTsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, ChinaCamouflaged object detection (COD) refers to the task of identifying and segmenting objects that blend seamlessly into their surroundings, posing a significant challenge for computer vision systems. In recent years, COD has garnered widespread attention due to its potential applications in surveillance, wildlife conservation, autonomous systems, and more. While several surveys on COD exist, they often have limitations in terms of the number and scope of papers covered, particularly regarding the rapid advancements made in the field since mid-2023. To address this void, we present the most comprehensive review of COD to date, encompassing both theoretical frameworks and practical contributions to the field. This paper explores various COD methods across four domains, including both image-level and video-level solutions, from the perspectives of traditional and deep learning approaches. We thoroughly investigate the correlations between COD and other camouflaged scenario methods, thereby laying the theoretical foundation for subsequent analyses. Furthermore, we delve into novel tasks such as referring-based COD and collaborative COD, which have not been fully addressed in previous works. Beyond object-level detection, we also summarize extended methods for instance-level tasks, including camouflaged instance segmentation, counting, and ranking. Additionally, we provide an overview of commonly used benchmarks and evaluation metrics in COD tasks, conducting a comprehensive evaluation of deep learning-based techniques in both image and video domains, considering both qualitative and quantitative performance. Finally, we discuss the limitations of current COD models and propose 9 promising directions for future research, focusing on addressing inherent challenges and exploring novel, meaningful technologies. This comprehensive examination aims to deepen the understanding of COD models and related methods in camouflaged scenarios. For those interested, a curated list of COD-related techniques, datasets, and additional resources can be found at https://github.com/ChunmingHe/awesome-concealed-object-segmentation.https://www.sciopen.com/article/10.26599/AIR.2024.9150044camouflaged object detectioncamouflaged scenario understandingdeep learningartificial intelligence |
| spellingShingle | Fengyang Xiao Sujie Hu Yuqi Shen Chengyu Fang Jinfa Huang Longxiang Tang Ziyun Yang Xiu Li Chunming He A Survey of Camouflaged Object Detection and Beyond CAAI Artificial Intelligence Research camouflaged object detection camouflaged scenario understanding deep learning artificial intelligence |
| title | A Survey of Camouflaged Object Detection and Beyond |
| title_full | A Survey of Camouflaged Object Detection and Beyond |
| title_fullStr | A Survey of Camouflaged Object Detection and Beyond |
| title_full_unstemmed | A Survey of Camouflaged Object Detection and Beyond |
| title_short | A Survey of Camouflaged Object Detection and Beyond |
| title_sort | survey of camouflaged object detection and beyond |
| topic | camouflaged object detection camouflaged scenario understanding deep learning artificial intelligence |
| url | https://www.sciopen.com/article/10.26599/AIR.2024.9150044 |
| work_keys_str_mv | AT fengyangxiao asurveyofcamouflagedobjectdetectionandbeyond AT sujiehu asurveyofcamouflagedobjectdetectionandbeyond AT yuqishen asurveyofcamouflagedobjectdetectionandbeyond AT chengyufang asurveyofcamouflagedobjectdetectionandbeyond AT jinfahuang asurveyofcamouflagedobjectdetectionandbeyond AT longxiangtang asurveyofcamouflagedobjectdetectionandbeyond AT ziyunyang asurveyofcamouflagedobjectdetectionandbeyond AT xiuli asurveyofcamouflagedobjectdetectionandbeyond AT chunminghe asurveyofcamouflagedobjectdetectionandbeyond AT fengyangxiao surveyofcamouflagedobjectdetectionandbeyond AT sujiehu surveyofcamouflagedobjectdetectionandbeyond AT yuqishen surveyofcamouflagedobjectdetectionandbeyond AT chengyufang surveyofcamouflagedobjectdetectionandbeyond AT jinfahuang surveyofcamouflagedobjectdetectionandbeyond AT longxiangtang surveyofcamouflagedobjectdetectionandbeyond AT ziyunyang surveyofcamouflagedobjectdetectionandbeyond AT xiuli surveyofcamouflagedobjectdetectionandbeyond AT chunminghe surveyofcamouflagedobjectdetectionandbeyond |