Tag: Computer Vision

Researchers in Norway have developed Hjort-YOLO, a lightweight and explainable AI framework that detects wildlife from camera-trap images faster and ...

A Chinese research team has developed HSM-YOLO, a lightweight deep learning model that detects estrus-related mounting behavior in group-housed sheep ...

A new parallel Transformer-CNN architecture called TCNNISTD achieves state-of-the-art accuracy and real-time speed in detecting infrared targets smaller than ten ...

Researchers in Serbia have built and validated a modular collaborative robotic workstation that combines foundation-model perception with safe human-robot collaboration ...

A systematic review of nineteen studies finds AI-powered navigation, object recognition, and reading aids are technically impressive but largely untested ...

A multi-region computer vision framework uses YOLO detection, depth estimation and explainable AI to extract anatomical features for automated body ...

A University of Guelph validation study found that a computer-vision system monitoring dairy milking parlours matched trained human observers almost ...

A systematic review of 91 studies shows AI-based medication recognition advancing rapidly through detection, OCR, and few-shot learning, while external ...

Researchers at Kocaeli University combined RGB video features and skeleton-based motion features in a multimodal deep learning framework that detects ...

Researchers at TU Delft have developed MonoRace, an AI system that flew a racing drone at up to 100 km/h ...

A new graph neural network framework evaluates dance training in real time and automatically adapts practice plans, achieving record accuracy ...

A sweeping review of 1,081 studies from 2014 to 2024 shows convolutional neural networks rapidly becoming the world's leading tool ...

Researchers have developed S2Fusion, a local-to-global framework that improves infrared and visible image fusion through cross-modal dynamic kernels and a ...

Tanzanian researchers trained deep neural networks to classify nitrogen status in maize leaves from smartphone photos, achieving over 93 percent ...

A new end-to-end AI detector called SFM-DETR combines Mamba state space modeling with frequency-domain analysis to identify maize seedlings and ...

A new reliability-aware neural radiance field workflow reconstructs public art sculptures with sub-1.5-percent geometric error and delivers smooth 27-fps interactive ...

Researchers have reimagined pixels as three-dimensional cuboids whose sizes are set by RGB values, using the empty space between them ...

Researchers in Colombia have developed Col-Ovo, a smartphone-based artificial intelligence system that counts Aedes aegypti mosquito eggs in seconds, matching ...

A new taxonomy-aware segmentation framework links every diseased pixel to both its host crop and its disease, delivering state-of-the-art results ...

Researchers in Mexico have built an AI pipeline combining SAM2, Florence2 and Stable Diffusion XL to detect and segment cracks ...