CAMotion: A High-Quality Benchmark for Camouflaged Moving Object Detection in the Wild
2026-04-09 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors created a new dataset called CAMotion to help with spotting camouflaged animals that move in videos. Because camouflaged objects look a lot like their background, it’s hard for computers to find them, especially when the existing data is small or not diverse enough. CAMotion includes many video sequences with tricky features like blurry movement and hidden parts to better train and test detection programs. The authors also tested current top detection models on CAMotion and highlighted ongoing difficulties in the task.
Camouflaged object detectionVideo object detectionBenchmark datasetMotion blurOcclusionDeep learningComputer visionDataset annotationSequential framesVisual challenges
Authors
Siyuan Yao, Hao Sun, Ruiqi Yu, Xiwei Jiang, Wenqi Ren, Xiaochun Cao
Abstract
Discovering camouflaged objects is a challenging task in computer vision due to the high similarity between camouflaged objects and their surroundings. While the problem of camouflaged object detection over sequential video frames has received increasing attention, the scale and diversity of existing video camouflaged object detection (VCOD) datasets are greatly limited, which hinders the deeper analysis and broader evaluation of recent deep learning-based algorithms with data-hungry training strategy. To break this bottleneck, in this paper, we construct CAMotion, a high-quality benchmark covers a wide range of species for camouflaged moving object detection in the wild. CAMotion comprises various sequences with multiple challenging attributes such as uncertain edge, occlusion, motion blur, and shape complexity, etc. The sequence annotation details and statistical distribution are presented from various perspectives, allowing CAMotion to provide in-depth analyses on the camouflaged object's motion characteristics in different challenging scenarios. Additionally, we conduct a comprehensive evaluation of existing SOTA models on CAMotion, and discuss the major challenges in VCOD task. The benchmark is available at https://www.camotion.focuslab.net.cn, we hope that our CAMotion can lead to further advancements in the research community.