A compact vision system for road vehicle guidance

Maurer, Markus; Behringer, Reinhold; Fürst, Simon; Thomanek, F.; Dickmanns, Ernst D.

doi:10.1109/icpr.1996.546962

Cited by 63 publications

(25 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different authors have proposed the use of different low-level image features to identify vehicles owing to their shadows and lateral edges (Maurer et al, 1996), symmetry (Liu et al, 2005), a combination of shadows, symmetry and edges (Broggi et al, 2004;Hilario et al, 2005), their perceived motion (Betke et al, 2000;Lefaix et al, 2002), texture (Kalinke et al, 1998;ten Kate et al, 2004), etc. These methods are rather too naive to reach reliable detection rates, and commonly generate many false detections, as well as misdetections under challenging illumination conditions.…”

Section: Vehicle Detectionmentioning

confidence: 99%

On-board image-based vehicle detection and tracking

Ponsa

Serrat

López

2009

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

In this paper we present a computer vision system for daytime vehicle detection and localization, an essential step in the development of several types of advanced driver assistance systems. It has a reduced processing time and high accuracy thanks to the combination of vehicle detection with lane-markings estimation and temporal tracking of both vehicles and lane markings. Concerning vehicle detection, our main contribution is a frame scanning process that inspects images according to the geometry of image formation, and with an Adaboost-based detector that is robust to the variability in the different vehicle types (car, van, truck) and lighting conditions. In addition, we propose a new method to estimate the most likely three-dimensional locations of vehicles on the road ahead. With regards to the lane-markings estimation component, we have two main contributions. First, we employ a different image feature to the other commonly used edges: we use ridges, which are better suited to this problem. Second, we adapt RANSAC, a generic robust estimation method, to fit a parametric model of a pair of lane markings to the image features. We qualitatively assess our vehicle detection system in sequences captured on several road types and under very different lighting conditions. The processed videos are available on a web page associated with this paper. A quantitative evaluation of the system has shown quite accurate results (a low number of false positives and negatives) at a reasonable computation time.

show abstract

Section: Vehicle Detectionmentioning

confidence: 99%

On-board image-based vehicle detection and tracking

Ponsa

Serrat

López

2009

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

show abstract

“…• the VaMP prototype was experimented on the route from Munich (Germany) to Odense (Denmark) [21] in 1995, * • the RALPH system was tested on NavLab 5 through a journey (No Hands Across America [24]) from Pittsburgh, PA to San Diego, CA in 1995, † and • the ARGO experimental vehicle was driven by the GOLD system for nearly 2000 km throughout Italy during the MilleMiglia in Automatico Tour [4] in 1998. ‡ These tests allowed to experiment the vehicles in the most different conditions and to bring out their robustness and weakness.…”

Section: Extensive Tests Of Prototype Vehiclesmentioning

confidence: 99%

Vision-based intelligent vehicles: State of the art and perspectives

Bertozzi

Broggi

Fascioli

2000

Robotics and Autonomous Systems

376

178

View full text Add to dashboard Cite

Recently, a large emphasis has been devoted to Automatic Vehicle Guidance since the automation of driving tasks carries a large number of benefits, such as the optimization of the use of transport infrastructures, the improvement of mobility, the minimization of risks, travel time, and energy consumption. This paper surveys the most common approaches to the challenging task of Autonomous Road Following reviewing the most promising experimental solutions and prototypes developed worldwide using AI techniques to perceive the environmental situation by means of artificial vision.The most interesting results and trends in this field as well as the perspectives on the evolution of intelligent vehicles in the next decades are also sketched out.

show abstract

“…Some universities, institutes and vehicle manufactures have developed driving environment recognition systems on their Advanced Safety Vehicle platforms. For example, the NavLab series intelligent vehicles by Carnegie Mellon University, USA [1]; the VaMP and VaMoRs intelligent vehicles by UBM, Germany [2]; the ARGO intelligent vehicle and its GOLD vision guidance system by University of Parma, Italy [3]; the THMR series intelligent vehicles of Tsinghua University, China [4], etc. Except for the above platforms in research, some products have been put into practice, including the AutoVue system by DaimlerChrysler Corporation, Germany and Iteris Corporation, USA together [8]; the LDW system by Nissan's north American corporation Infiniti; the STAR system by Toyoto Corporation, Japan, etc.…”

Section: Introductionmentioning

confidence: 99%

An Integrated System of Driving Environment Recognition based on THASV-II

Liu

Guo

Wang

et al. 2008

JMTL

View full text Add to dashboard Cite

In this paper, an integrated driving environment recognition system is established on THASV-Ⅱ (Tsinghua Advanced Safety Vehicle) test platform. The system collects environment information and vehicular motion information based on the fusion of machine vision, laser radar and other vehicular sensors. An adaptive bi-threshold method and steerable filters are adopted in the image pre-processing to enhance the lane marker and vehicle features. A multi-level fusion structure is designed to recognize the front vehicles and a high-order statistic method is proposed to recognize the side and rear vehicles. The anti-interference ability of lane marker recognition is improved by a point set optimization method and the target vehicle is determined through a multi-feature fusion algorithm. Field tests demonstrate that the integrated system can meet the demands of environment recognition for various lateral and longitudinal active safety systems, achieving good adaptability to environmental variation and good anti-interference ability under heavy traffic situation.

show abstract

A compact vision system for road vehicle guidance

Cited by 63 publications

References 5 publications

On-board image-based vehicle detection and tracking

On-board image-based vehicle detection and tracking

Vision-based intelligent vehicles: State of the art and perspectives

An Integrated System of Driving Environment Recognition based on THASV-II

Contact Info

Product

Resources

About