Vehicle Detection on Low Altitude Images Based on Edge Density

摘要

The popularity of unmanned aerial vehicles, usually denoted as drones, is increasing these days due to various factors. Their capability of capturing images from above, allowing new perspectives of a scene, is for sure one of the most significant. It gets even more interesting when captured images are processed using Computer Vision algorithms, creating a powerful technology combination with appliances in several areas. In this paper, we present algorithms under development to process images captured by drones over parking lots in order to detect parked vehicles and further estimate occupancy rates or cars parked in a wrong place. Another application that we are developing is the monitoring of boats in the Aveiro lagoon. As far as we know, the processing of low altitude images is still an open problem in the computer vision community. The preliminary results presented in this paper show the effectiveness of the approaches under development.