The Single Frame Stereo Vision System for Reliable Obstacle Detection Used during the 2005 DARPA Grand Challenge on TerraMax

Broggi, Alberto; Caraffi, C.; Porta, Pier Paolo; Zani, Paolo

doi:10.1109/itsc.2006.1706831

Cited by 75 publications

(37 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Stereo vision has been extensively researched for decades because images contain more information than other range sensors. The single frame stereo vision system was used for obstacle avoidance during the DARPA Grand Challenge 2005 by TerraMax [6] . The Sato Laboratory of Osaka in Japan applied the techniques to tracking the location of moving objects of complex shapes in the image [7] .…”

Section: Introductionmentioning

confidence: 99%

A Real-time Range Finding System with Binocular Stereo Vision

Lai¹,

Hai-shun²,

2012

Int J Adv Robotic Sy

View full text Add to dashboard Cite

To acquire range information for mobile robots, a TMS320DM642 DSP-based range finding system with binocular stereo vision is proposed. Firstly, paired images of the target are captured and a Gaussian filter, as well as improved Sobel kernels, are achieved. Secondly, a feature-based local stereo matching algorithm is performed so that the space location of the target can be determined. Finally, in order to improve the reliability and robustness of the stereo matching algorithm under complex conditions, the confidence filter and the left-right consistency filter are investigated to eliminate the mismatching points. In addition, the range finding algorithm is implemented in the DSP/BIOS operating system to gain real-time control. Experimental results show that the average accuracy of range finding is more than 99% for measuring single-point distances equal to 120cm in the simple scenario and the algorithm takes about 39ms for ranging a time in a complex scenario. The effectivity, as well as the feasibility, of the proposed range finding system are verified.

show abstract

Section: Introductionmentioning

confidence: 99%

A Real-time Range Finding System with Binocular Stereo Vision

Lai¹,

Hai-shun²,

2012

Int J Adv Robotic Sy

View full text Add to dashboard Cite

show abstract

“…The v-disparity method [2], [9], [10] is generally used for road surface identification, owing to its simplicity and effectiveness. However, we previously reported that this method became inaccurate when the vehicle was moving fast on a curve.…”

Section: Road Surface Extractionmentioning

confidence: 99%

“…In this experiment, 200 frames were examined. In the worst frame, there were 370 measurements calculated by equation (2) in the frame, and 7 of them (1.9%) were false positives. However, the proposed method completely eliminated these false positives.…”

Section: Evaluation Of Obstacle Detection Using Ogmmentioning

confidence: 99%

Obstacle Detection Based on Occupancy Grid Maps Using Stereovision System

et al. 2010

View full text Add to dashboard Cite

We previously reported on an obstacle detection method using a stereovision system. The system generated disparity images that include three-dimensional spatial information. Using these images, obstacles could be detected, but some false positives were generated. In this paper, we attempt to eliminate this problem and propose a method that generates Occupancy Grid Maps based on measurements from a stereovision system which leads to robust obstacle detection. Furthermore, it is confirmed that high distance accuracy can be achieved by using our method.

show abstract

“…For example, you can visualize the data coming from different sensors, such as a stereo camera system or a laser scanner. Figure 2a shows laser-scanner data for the TerraMax prototype vehicle, 3 one of only five vehicles to complete the 2005 Grand Challenge course and the only one to do so using a vision system for obstacle detection. The GOLD architecture Figure 3 shows the GOLD architecture and components.…”

Section: The Gold Frameworkmentioning

confidence: 99%

GOLD: A Framework for Developing Intelligent-Vehicle Vision Applications

et al. 2008

View full text Add to dashboard Cite

The use of vision in intelligent transportation systems has been in development for the past 20 years. It has evolved rapidly and is widely considered one of the most promising perception technologies.Effective vision-based systems require developers to consider both hardware and software issues. Hardware issues include the computing engine and the sensing technologies-in vision systems, the cameras. Several camera technologies are available: daylight, far infrared (thermal), near IR, or even range cameras. The choice depends mainly on the specific application and cost-benefit analysis.Software issues include the offline development and debugging software and the final system software. A rapiddevelopment tool lets programmers focus on their application's specific vision problem without having to tend to other details. VisLab has developed GOLD to give programmers such a tool. GOLD includes APIs for common tasks such as I/O operations (acquisition from cameras and other sensors, sensor synchronization, network and file management, data graphical display, and so on) and low-level image-processing functions. A user-friendly GUI supports programming (see figure 1).We originally conceived GOLD as the main engine to detect lanes and obstacles on board the Argo autonomous vehicle. 2 After 15 years of continuous R&D, GOLD has evolved into a framework aimed at providing a complete set of tools for fast development of computer-vision applications. Moreover, GOLD runs the final onboard system. In spite of this complex functionality, GOLD's user-friendly GUI manages all the system applications. For example, you can visualize the data coming from different sensors, such as a stereo camera system or a laser scanner. Figure 2a The GOLD architecture Figure 3 shows the GOLD architecture and components. We conceived the architecture to ensure scalability and independence among the components. The whole system comprises several subsystem layers, which provide the different functionalities to developers. A cleanly defined interface makes it easy to add or remove subsystems, depending on the target project's specific needs. The framework views all applications as plug-ins that developers can easily remove or connect independently and port to different platforms.The hardware abstraction layers mask the input device complexities from the programmer.Developers can also easily produce highly interactive, consistent user interfaces through a set of widgets specifi- I n t e l l i g e n t T r a n s p o r t a t i o n S y s t e m s

show abstract

The Single Frame Stereo Vision System for Reliable Obstacle Detection Used during the 2005 DARPA Grand Challenge on TerraMax

Cited by 75 publications

References 18 publications

A Real-time Range Finding System with Binocular Stereo Vision

A Real-time Range Finding System with Binocular Stereo Vision

Obstacle Detection Based on Occupancy Grid Maps Using Stereovision System

GOLD: A Framework for Developing Intelligent-Vehicle Vision Applications

Contact Info

Product

Resources

About