Explicit Motion Handling and Interactive Prompting for Video Camouflaged Object Detection

TL;DR

This paper introduces EMIP, a novel framework for video camouflaged object detection that explicitly handles motion cues using a two-stream architecture with interactive prompting, achieving state-of-the-art results.

Contribution

The paper proposes a new explicit motion handling framework with interactive prompting and learnable modules, improving detection in complex dynamic scenes.

Findings

Achieves state-of-the-art performance on VCOD benchmarks.

Effectively incorporates long-term historical information for robustness.

Utilizes a frozen pre-trained optical flow model for motion cues.

Abstract

Camouflage poses challenges in distinguishing a static target, whereas any movement of the target can break this disguise. Existing video camouflaged object detection (VCOD) approaches take noisy motion estimation as input or model motion implicitly, restricting detection performance in complex dynamic scenes. In this paper, we propose a novel Explicit Motion handling and Interactive Prompting framework for VCOD, dubbed EMIP, which handles motion cues explicitly using a frozen pre-trained optical flow fundamental model. EMIP is characterized by a two-stream architecture for simultaneously conducting camouflaged segmentation and optical flow estimation. Interactions across the dual streams are realized in an interactive prompting way that is inspired by emerging visual prompt learning. Two learnable modules, i.e., the camouflaged feeder and motion collector, are designed to incorporate segmentation-to-motion and motion-to-segmentation prompts, respectively, and enhance outputs of the both streams. The prompt fed to the motion stream is learned by supervising optical flow in a self-supervised manner. Furthermore, we show that long-term historical information can also be incorporated as a prompt into EMIP and achieve more robust results with temporal consistency. Experimental results demonstrate that our EMIP achieves new state-of-the-art records on popular VCOD benchmarks. Our code is made publicly available at https://github.com/zhangxin06/EMIP.