Abstract: Object detection using visible-infrared images has become increasingly crucial for all-day applications of uncrewed aerial vehicles (UAVs). However, existing multimodal detection methods ...

Training-free framework that converts SAM3 into a real-time multi-class open-vocabulary detector. Achieves 55.8 AP on COCO val2017 (80 classes) at 15.8 FPS (4 classes, 1008px) on a single RTX 4080.

Abstract: This paper presents a colour detection application that utilises a deep learning model to predict the name of a colour based on its HSV value. The use of the HSV values rather than the RGB ...