Litcius/Paper detail

Detecting Road Obstacles by Erasing Them

Krzysztof Lis, Sina Honari, Pascal Fua, Mathieu Salzmann

2023IEEE Transactions on Pattern Analysis and Machine Intelligence34 citationsDOIOpen Access PDF

Abstract

Vehicles can encounter a myriad of obstacles on the road, and it is impossible to record them all beforehand to train a detector. Instead, we select image patches and inpaint them with the surrounding road texture, which tends to remove obstacles from those patches. We then use a network trained to recognize discrepancies between the original patch and the inpainted one, which signals an erased obstacle.

Topics & Concepts

Computer visionComputer scienceArtificial intelligenceObstacleImage (mathematics)DetectorGeographyTelecommunicationsArchaeologyAdvanced Neural Network ApplicationsVideo Surveillance and Tracking MethodsAutonomous Vehicle Technology and Safety