Low-light Object Detection
This is an incremental improvement for applications requiring object detection in low-light conditions.
The paper tackled low-light object detection by using a model fusion approach with CO-DETR trained on dark and enhanced images, achieving results close to those of real images.
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.