Efficient Camouflaged Object Detection via Progressive Refinement Network

doi:10.1109/LSP.2023.3348390

Efficient Camouflaged Object Detection via Progressive Refinement Network

2024-01-01

2

PRE

AI

DOI：10.1109/LSP.2023.3348390

Original

Original request for help

Save

Abstract

En 中文

Camouflaged object detection (COD) aims to identify objects that are perfectly concealed in their surroundings and has attracted increasing attention in recent years. The challenge with COD is the intrinsic similarity between camouflaged objects and background, as well as the weak boundary that often accompanies camouflaged objects. In this letter, a Progressive Refinement Network called PRNet is proposed based on human perception of camouflaged images. Specifically, we develop a position-aware module to roughly locate the position of camouflaged objects by reverse-guiding with high-level semantic information. Moreover, an edge-guided fusion module is designed to simultaneously refine the boundaries and regions of camouflaged objects by using edge features as a guide in cross-level feature fusion. Benefited from the utility of the above two modules, our PRNet is able to identify camouflaged objects accurately and quickly. Numerous experiments on four widely used benchmark datasets demonstrate that the proposed PRNet is an efficient COD model, outperforming 14 state-of-the-art algorithms significantly and running at a real-time speed (41.0 FPS).

Keywords:

Image edge detection

Feature extraction

Computer vision

Semantics

Object detection

Visualization

Training

Camouflaged object detection

position-aware module

edge-guided fusion module

cross-level feature fusion

Efficient Camouflaged Object Detection via Progressive Refinement Network

Abstract

Journal

Organization