Lightweight method improves camouflaged object detection using rgb polarization data
LGFN: Lightweight Gated RGB-Polarization Fusion with Modality-Availability Conditioning for Camouflaged Object Detection
Computer Vision and Pattern Recognition
Summary
Detecting objects that blend into their surroundings is very challenging. The authors present a new method called LGFN that combines regular color cameras (RGB) with polarization sensors to spot these hidden objects better. Their approach can work when polarization data is available or not by switching configurations. LGFN is efficient, requiring fewer computations while achieving better accuracy compared to similar methods.
What this means in practice
- •For autonomous vehicle engineers: Improve detection of camouflaged hazards in driving scenes by integrating rgb and polarization sensors with efficient fusion techniques.
- •For surveillance system developers: Build monitoring systems that better detect hidden or camouflaged objects by combining rgb and polarization imagery with adaptive processing.
Authors
Zhuangfan Huang, Xiaosong Li, Yang Liu, Tao Ye, Haishu Tan
Abstract
Camouflaged object detection (COD) is an important engineering task in intelligent optical perception, but it remains challenging when targets closely resemble their surroundings. Polarization imaging provides complementary physical cues, whereas existing methods typically assume fixed multimodal input configurations and entangle intra-polarization coordination with interaction between red-green-blue (RGB) and polarization representations. We propose LGFN, a lightweight gated RGB-polarization fusion framework supporting separately optimized RGB-only and polarization-assisted configurations. A deterministic Modality Router selects the appropriate configuration according to polarization availability. In the multimodal configuration, an availability-conditioned Modality Gate calibrates the available polarization branches; the Gated Polarization Hub coordinates learned degree of linear polarization (DoLP) and angle of polarization (AoP) representations with explicit polarization cues; and RGB-Polarization Cross Fusion introduces the coordinated representation into the RGB hierarchy through controlled residual interaction. The multimodal configuration requires neither sample-dependent statistics nor handcrafted quality descriptors during inference. On the complete 230-image PCOD_1200 test set, the RGB-only configuration achieves a mean absolute error of 0.0090, a Dice score of 0.8806, and an intersection over union of 0.8144, obtaining the best results on all six metrics among the evaluated RGB-based methods. Under a common local reevaluation protocol, the multimodal configuration outperforms PolarNet and IPNet on all six metrics. Relative to IPNet, it reduces the parameter count, floating-point operations, and latency by 53.1%, 73.6%, and 63.0%, respectively.