Detecting Road Obstacles by Erasing Them
Related Experiment Video
Updated: Jul 9, 2025

Evaluating the Effect of Roadside Parking on a Dual-Direction Urban Street
Published on: January 20, 2023
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.
Related Concept Videos
Design Example: Alignment of a Road Line Using GIS
Design Example: Maintaining Level of an Embankment
Design Example: Identifying the Locations of Monuments in the Field Using Global Positioning System Device
Design Example: Measuring Distance Between Two Points with Obstructions
Sight Distance in a Vertical Curve
Common Leveling Mistakes and Errors

