CAMotion: A High-Quality Benchmark for Camouflaged Moving Object Detection in the Wild

TL;DR

CAMotion introduces a comprehensive high-quality benchmark dataset for camouflaged moving object detection in natural environments, addressing limitations of existing datasets and enabling better evaluation of deep learning models.

Contribution

The paper presents CAMotion, a new large-scale, diverse dataset with detailed annotations for camouflaged object detection, facilitating deeper analysis and evaluation of algorithms.

Findings

Existing SOTA models show limited performance on CAMotion.

CAMotion's diverse attributes reveal key challenges in VCOD.

Benchmark enables comprehensive evaluation of camouflaged object detection methods.

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.