Traffic accident scene three-dimensional reconstruction system and method based on unmanned aerial vehicle aircraft aerial photography

Abstract

The invention discloses a traffic accident scene three-dimensional reconstruction system based on unmanned aerial vehicle aircraft aerial photography. The system comprises an unmanned aircraft system which comprises an unmanned aircraft body used for carrying and flying, an inertial measuring unit, a positioning and orienteering module, a communication module and an airborne camera, a ground control platform which communicates with the communication module of the unmanned aircraft system to realize control communication and picture information transmission, and an accident scene three-dimensional image processing system which communicates with the ground control platform to transmit picture information. According to the invention, the image collection of a road traffic accident scene is carried out from different heights and angles by setting the flight route and the waypoint of the unmanned aircraft; a multi-view stereoscopic vision processing technology is used to establish a three-dimensional traffic accident scene model; and from the technical point of view, the method gives full play to the advantages of maneuvering, flexibility and good viewshed of the unmanned aircraft.

Description

technical field [0001] The invention relates to the technical field of intelligent transportation, in particular to a three-dimensional reconstruction system and reconstruction method for a traffic accident scene based on aerial photography of an unmanned aerial vehicle. Background technique [0002] With the rapid increase in the number of motor vehicles, some drivers do not have a high awareness of safe driving. At the same time, affected by bad roads, weather and other conditions, road traffic accidents occur from time to time. After a traffic accident, the traffic police usually take temporary traffic control measures, such as road restrictions or even road closures, and then measure and photograph the scene of the traffic accident to obtain first-hand information for subsequent traffic accident identification and responsibility division. However, there are some defects in the above-mentioned traditional method. The one is that a long road closure time (such as more than...

AI Technical Summary

Problems solved by technology

However, this method does not consider the 3D modeling of the traffic accident scene

[0006] In addition, the quality of aerial images is easily affected by factors such as poor lighting and object occlusion, which makes it difficult to extract feature points and image matching from aerial images.

Images