Feature distribution alignments for object detection in the thermal domain

Highlights

1. Importance of aligning features: Emphasizing the need for aligning features from visible and thermal domains for effective object detection.
2. Adaptive detector with feature distribution alignments: Introducing an adaptive detector that incorporates feature distribution alignments into the Faster R-CNN architecture.
3. Improved overall performance: Demonstrating better results compared to baseline detectors and existing works, addressing domain shift and enhancing object detection in both visible and thermal domains.

Abstract

Infrared imaging has recently played an important role in a wide range of applications including video surveillance, robotics and night vision. However, the manufacturing cost of high-resolution infrared cameras is more expensive regarding similar quality in visible cameras. This could explain the fact that thermal databases are less available compared to visible ones. In this paper, we mainly emphasis the need for aligning features from visible and thermal domains for object detection in order to ensure effective results in both domains without the need to retrain data and to perform additional annotations. To address that, we incorporate feature distribution alignments into Faster R-CNN architecture at dierent levels. The resulting proposed adaptive detector has the advantage of covering different aspects of the domain shift in order to improve the overall performance. Using KAIST and FLIR ADAS datasets, the effectiveness of the proposed detector is assessed and better results are obtained compared to the baseline detector and to the obtained results by other existing works.