Tech Xplore

Enhanced YOLO framework boosts 360-degree small-object detection to 90% accuracy

Omnidirectional cameras are widely popular as they capture a full 360-degree view. They are often utilized for surveillance, ...
IEEE

IM-CMDet: An Intramodal Enhancement and Cross-Modal Fusion Network for Small Object Detection in UAV Aerial Visible-Infrared Imagery

Abstract: Uncrewed aerial vehicle (UAV) aerial visible–infrared [RGB-thermal (RGBT)] object detection has been widely applied in fields such as military operations and rescue missions. However, ...
IEEE

A Cross-Modality Feature Adaptive Interaction Approach for RGB-Infrared Object Detection in Aerial Imagery

Abstract: Object detection in aerial imagery, particularly from unmanned aerial vehicles (UAVs) and remote sensing platforms, is crucial but faces significant challenges such as modality misalignment, ...
Nature

Underwater Object Detection Algorithms Using Deep Learning Techniques

Underwater object detection has emerged as a pivotal field for marine exploration, environmental monitoring and underwater robotics. The unique challenges of aquatic environments—such as light ...
GitHub

ESCNet:Edge-Semantic Collaborative Network for Camouflaged Object Detection

Visual comparison between ESCNet and other SOTA methods. Our model accurately segments objects with complex backgrounds and intricate boundaries. For ease of use, we create a eval.sh script and a use ...
Nature

Oriented Object Detection in Remote Sensing Imagery

Oriented object detection in remote sensing imagery has emerged as a critical field of study, addressing the challenge of recognising and localising objects that appear at arbitrary angles in aerial ...