Exploring Thermal Images for Object Detection in Underexposure Regions for Autonomous Driving

TL;DR

This paper introduces a domain adaptation framework using style transfer via GANs to improve object detection in thermal images for autonomous driving, addressing data scarcity and challenging conditions.

Contribution

It presents a novel style transfer-based transfer learning approach that enhances thermal object detection by leveraging visible spectrum images.

Findings

Improved detection accuracy on thermal datasets

Effective style transfer from visible to thermal images

Addresses data scarcity in thermal domain

Abstract

Underexposure regions are vital to construct a complete perception of the surroundings for safe autonomous driving. The availability of thermal cameras has provided an essential alternate to explore regions where other optical sensors lack in capturing interpretable signals. A thermal camera captures an image using the heat difference emitted by objects in the infrared spectrum, and object detection in thermal images becomes effective for autonomous driving in challenging conditions. Although object detection in the visible spectrum domain imaging has matured, thermal object detection lacks effectiveness. A significant challenge is scarcity of labeled data for the thermal domain which is desiderata for SOTA artificial intelligence techniques. This work proposes a domain adaptation framework which employs a style transfer technique for transfer learning from visible spectrum images to thermal images. The framework uses a generative adversarial network (GAN) to transfer the low-level features from the visible spectrum domain to the thermal domain through style consistency. The efficacy of the proposed method of object detection in thermal images is evident from the improved results when used styled images from publicly available thermal image datasets (FLIR ADAS and KAIST Multi-Spectral).