1,721,007 research outputs found
An extension to the Inverse Perspective Mapping to handle non-flat roads
No full textIn this paper, the authors examine the issue of Inverse Perspective Mapping (IPM) which removes the perspective effect from acquired images that are associated with autonomous driving systems. They in turn present an Extended IPM (EIPM) which is based on stereo image processing and which is used to update the road slope ahead of the vehicle. The EIPM removes the assumption of a flat road ahead of the vehicle and allows for the recovery of road texture even in the presence of a slope. The authors describe how this technique is applied to synthetic images and how it has been integrated into the GOLD system on the ARGO autonomous vehicle
Architectural Issues on Vision-based Automatic Vehicle Guidance: the Experience of the ARGO Project
No full text
Visual Perception and Learning in Road Environments
No full textThis paper describes the new Lane Detection module which is now operative on the ARGO autonomous vehicle and enables the vehicle to drive itself on roads and highways. It is only based on the processing of a monocular sequence of images acquired from the moving vehicle. A first simpler version, tested and demonstrated in a 2000+ km tour throughout Italy in 1998, showed some problems which have now been eliminated by the current approach. The paper describes how the new algorithm can adapt to different road and environmental conditions, as well as how it can reconstruct scenes which are partly occluded by other vehicles or in which lane markings are partly missing
VisLab and the Evolution of Vision-Based UGVs,
No full textThanks to the reduced costs of image acquisition devices and to the increasing computational power of current computer systems, Computer Vision has recently become a very popular method to sense the surrounding environment. This work presents a challenging application of machine vision to the automatic guidance of autonomous vehicles, discusses the key problems intrinsic to this field, and describes the solutions adopted in the development of different prototype vehicles worldwide.
In the second part this paper focuses on the GOLD system, a stereo vision system developed at the University of Parma, Italy, for generic obstacle detection and lane localization, able to process images in real-time. GOLD was tested on the MOB-LAB experimental land vehicle for more than 3,000~km along extra-urban roads and freeways at speeds up to 80 km/h
Development and Test of an Intelligent Vehicle Prototype
No full textThis paper presents the current status of the ARGO Project, whose main target is the development of an active safety system and an automatic pilot for a standard road vehicle. First the ARGO project is briefly described along with its main objectives and goals; then the autonomous vehicle prototype and its functionalities are presented. An overview of the computer vision algorithms for the detection of lane markings, generic obstacles, leading vehicles and pedestrians is given
- …
