Cascade and Fusion: A Deep Learning Approach for Camouflaged Object Sensing.

Kaihong Huang,Beilun Wang,Jiaqi Zhang,Chunshu Li

doi:10.3390/s21165455

Kaihong Huang, Beilun Wang + Show 2 more

Open Access

https://doi.org/10.3390/s21165455

Copy DOI

Abstract

The demand for the sensor-based detection of camouflage objects widely exists in biological research, remote sensing, and military applications. However, the performance of traditional object detection algorithms is limited, as they are incapable of extracting informative parts from low signal-to-noise ratio features. To address this problem, we propose Camouflaged Object Detection with Cascade and Feedback Fusion (CODCEF), a deep learning framework based on an RGB optical sensor that leverages a cascaded structure with Feedback Partial Decoders (FPD) instead of a traditional encoder–decoder structure. Through a selective fusion strategy and feedback loop, FPD reduces the loss of information and the interference of noises in the process of feature interweaving. Furthermore, we introduce Pixel Perception Fusion (PPF) loss, which aims to pay more attention to local pixels that might become the edges of an object. Experimental results on an edge device show that CODCEF achieved competitive results compared with 10 state-of-the-art methods.

Highlights

In order to use this edge information, we introduce Pixel Perception Fusion Loss (PPF), which consists of Pixel Frequency Aware Loss (PFA) [27] to optimize the prediction results of each component
We proposed a new framework for camouflaged object detection, namely
The experiments showed that CODCEF achieved state-of-the-art performance on three benchmark datasets of camouflaged object detection on four evaluation metrics

Summary

Introduction

Object detection as a fundamental component of optical sensor systems has been extensively applied in various practical scenarios, such as automatic driving, human–. When practitioners try to apply object detection techniques in biological, security, or military scenarios, traditional object detection algorithms are often incapable of dealing with harsh or extreme situations that are even challenging to the naked eye. This brings about the need for a powerful detection method for camouflage targets. This challenging task is named camouflaged object detection (COD)

Methods

Results

Conclusion