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 ha...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 CODrelated techniques,datasets,and additional resources can be found at https://github.com/ChunmingHe/awesome-concealed-objectsegmentation.展开更多
基金supported by the STI 2030-Major Projects(No.2021ZD0201404).
文摘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 CODrelated techniques,datasets,and additional resources can be found at https://github.com/ChunmingHe/awesome-concealed-objectsegmentation.
