The DARPA grand challenge - development of an autonomous vehicle

Behringer, Reinhold; Sundareswaran, Savithri; Elsley, R. K.; Addison, B.; Guthmiller, W.; Daily, R.; Bevly, David M.

doi:10.1109/ivs.2004.1336386

Cited by 65 publications

(34 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Radars based methods [1,2], laser range finder based methods [3,4], stereo vision based methods [5,6] can be found in literature. The 2007 DARPA Grand Challenge competition was successfully achieved on simulated city environment [7], and most of the teams used lidar based strategy [8]. Although laser sensors provide refined and easy-to-use information about the surrounding area, they also present some intrinsic limitations to their functioning as mentioned in [9].…”

Section: Introductionmentioning

confidence: 99%

Stereo vision based road scene segment and vehicle detection

Zhu

Zhang

2014

Proceedings of 2nd International Conference on Information Technology and Electronic Commerce

View full text Add to dashboard Cite

A stereo vision based road scene segment and vehicle detection method was proposed in this paper. In the method, First, dynamic programming was used for stereo matching, and then mismatching pixels were removed by leftright-consistency check; Second, V disparity was built by computing the disparity map, and a fast projection based line detection method was used to detect lines in V disparity map, after that, the road surface and vanishing line was extracted, and the intersection point between road and vehicle was computed; Third, the U disparity map was built to detect the horizontal position of vehicle. The experiment results have shown that our method not only can extract road area correctly, but also can detect vehicle position correctly too.

show abstract

Section: Introductionmentioning

confidence: 99%

Stereo vision based road scene segment and vehicle detection

Zhu

Zhang

2014

Proceedings of 2nd International Conference on Information Technology and Electronic Commerce

View full text Add to dashboard Cite

show abstract

“…The 2005 DARPA Grand Challenge competition was successfully achieved on unstructured roads [6]. Most of the teams used lidar, radar or sonar [2] but no one succeed with a single vision-based system. Here will be an interesting and important evolution, because such systems have strong advantages such as low cost and passivity, which are key points for industrial or military matters.…”

Section: Introductionmentioning

confidence: 99%

Road Segmentation Supervised by an Extended V-Disparity Algorithm for Autonomous Navigation

Soquet¹,

Didier²,

Hautiére³

2007

2007 IEEE Intelligent Vehicles Symposium

View full text Add to dashboard Cite

This paper presents an original approach of road segmentation supervised by stereovision. It deals with free space estimation by stereovision and road detection by color segmentation. The v-disparity algorithm is extended to provide a reliable and precise road profile on all types of roads. The free space is estimated by classifying the pixels of the disparity map. This classification is performed by using the road profile and the u-disparity image. Then a color segmentation is performed on the free space. Here is the supervision. Each stage of the algorithm is presented and experimental results are shown.

show abstract

“…Zu den Anwendungsgebieten b), die den Schwerpunkt dieses Beitrags bilden, gehören • dynamische Straßenkartierung [7], • mobile Roboter zu Wasser [5], zu Lande [1] und in der Luft [2],…”

Section: Introductionunclassified

Motion-Scan-Effekt (Motion-Scan Effect)

Kapp¹,

Gröll²

2006

At - Automatisierungstechnik

View full text Add to dashboard Cite

Ing. habil. Georg Bretthauer zum 60. Geburtstag gewidmet Bei Laserscannern ist das Scannen zeitlich ausgedehnt, sodass eine Relativbewegung zwischen Sensor und Objekt während des Scans zu einer bewegungsbedingten Unschärfe führt -hier Motion-Scan-Effekt genannt. In Folge des Effekts wird das Entfernungsbild des Scanners verfälscht, was die weitere Signalverarbeitung negativ beeinflusst. In diesem Beitrag wird dieser seit langem bekannte Effekt quantitativ erfasst, analysiert und kompensiert. Damit kann die Genauigkeit und das Regelungsverhalten verbessert werden, was insbesondere bei sicherheitskritischen Anwendungen autonomer Fahrzeuge wichtig ist.The scanning process of lidar scanners is extended over time. Hence, relative motion between sensor and object during the scanning leads to a motion-dependent blur, here called motionscan effect . Due to this effect the lidar's distance map is deteriorated which has a negative impact on the subsequent signal processing. This article quantifies and analyzes this effect and compensates for it. Thus the accuracy and the control mode can be improved which is particularly important for safety-critical applications of autonomous vehicles.

show abstract

The DARPA grand challenge - development of an autonomous vehicle

Cited by 65 publications

References 3 publications

Stereo vision based road scene segment and vehicle detection

Stereo vision based road scene segment and vehicle detection

Road Segmentation Supervised by an Extended V-Disparity Algorithm for Autonomous Navigation

Motion-Scan-Effekt (Motion-Scan Effect)

Contact Info

Product

Resources

About