Advancements in Computer Vision for Medical Imaging and Autonomous Systems

The field of computer vision is rapidly advancing, with a focus on improving image quality and accuracy in medical imaging and autonomous systems. Recent developments have led to the creation of innovative frameworks and models that can classify image properties, detect occlusions, and predict accidents. These advancements have the potential to significantly improve patient outcomes and road safety. Notable papers include CLAIRE-DSA, which achieved excellent performance in classifying image properties, and OccluNet, which demonstrated high precision and recall in occlusion detection. Additionally, STAGNet and Predicting Road Crossing Behaviour using Pose Detection and Sequence Modelling showcased impressive results in accident anticipation and road crossing intent prediction, respectively.

Sources

CLAIRE-DSA: Fluoroscopic Image Classification for Quality Assurance of Computer Vision Pipelines in Acute Ischemic Stroke

OccluNet: Spatio-Temporal Deep Learning for Occlusion Detection on DSA

STAGNet: A Spatio-Temporal Graph and LSTM Framework for Accident Anticipation

Predicting Road Crossing Behaviour using Pose Detection and Sequence Modelling

Built with on top of