Low-light Object Detection

TL;DR

This paper presents a model fusion approach using CO-DETR trained on dark and enhanced images, employing multiple enhancement techniques and clustering to improve low-light object detection accuracy.

Contribution

It introduces a novel fusion and clustering method combining multiple low-light image enhancements with CO-DETR for improved detection performance.

Findings

Achieved detection results close to those on well-lit images

Effective use of multiple enhancement techniques

Improved aggregation method for low-light conditions

Abstract

In this competition we employed a model fusion approach to achieve object detection results close to those of real images. Our method is based on the CO-DETR model, which was trained on two sets of data: one containing images under dark conditions and another containing images enhanced with low-light conditions. We used various enhancement techniques on the test data to generate multiple sets of prediction results. Finally, we applied a clustering aggregation method guided by IoU thresholds to select the optimal results.