Real-time semi-global matching disparity estimation on the GPU

Banz, Christian; Blume, Holger; Pirsch, P.

doi:10.1109/iccvw.2011.6130286

Cited by 49 publications

(24 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [156], an early GPU was used for monocular vehicle detection. In [157], real-time stereo matching using semiglobal matching [109] was implemented on the GPU. In [40], the GPU was used to implement real-time vehicle detection using HOG [34] features.…”

Section: Real-time Implementation and System Architecturementioning

confidence: 99%

Looking at Vehicles on the Road: A Survey of Vision-Based Vehicle Detection, Tracking, and Behavior Analysis

Sivaraman

Trivedi

2013

IEEE Trans. Intell. Transport. Syst.

792

319

View full text Add to dashboard Cite

Abstract-This paper provides a review of the literature in on-road vision-based vehicle detection, tracking, and behavior understanding. Over the past decade, vision-based surround perception has progressed from its infancy into maturity. We provide a survey of recent works in the literature, placing vision-based vehicle detection in the context of sensor-based on-road surround analysis. We detail advances in vehicle detection, discussing monocular, stereo vision, and active sensor-vision fusion for on-road vehicle detection. We discuss vision-based vehicle tracking in the monocular and stereo-vision domains, analyzing filtering, estimation, and dynamical models. We discuss the nascent branch of intelligent vehicles research concerned with utilizing spatiotemporal measurements, trajectories, and various features to characterize on-road behavior. We provide a discussion on the state of the art, detail common performance metrics and benchmarks, and provide perspective on future research directions in the field.

show abstract

Section: Real-time Implementation and System Architecturementioning

confidence: 99%

Looking at Vehicles on the Road: A Survey of Vision-Based Vehicle Detection, Tracking, and Behavior Analysis

Sivaraman

Trivedi

2013

IEEE Trans. Intell. Transport. Syst.

792

319

View full text Add to dashboard Cite

show abstract

“…I. While two solutions exhibit a higher disparity rate [15], [16], and one has an essentially identical performance [14], all of them run on hardware devices of considerably higher cost and power consumption.…”

Section: Resultsmentioning

confidence: 99%

“…In particular, PC-based solutions can reach 20 fps at VGA resolution on a standard desktop CPU [14] by exploiting both multi-core and SIMD 1 processing capabilities. GPU implementations exist as well, reaching more than 60 fps at VGA resolution [15]; however, they require high end, expensive devices, with more than doubled power consumption.…”

Section: Introductionmentioning

confidence: 99%

3DV — An embedded, dense stereovision-based depth mapping system

Camellini

Felisa

Medici

et al. 2014

2014 IEEE Intelligent Vehicles Symposium Proceedings

View full text Add to dashboard Cite

This paper describes the architecture and hardware implementation of an embedded, low-cost and low-power dense stereo reconstruction system, running at 30 fps at VGA resolution. The processing pipeline includes an initial image rectification stage, a cost generation unit based on the nonparametric census transform, a state-of-the-art Semi-Global cost optimization stage, and a final minimization and noise suppression step. The hardware implementation is based on a Xilinx Zynq TM System-on-Chip, which besides the FPGA provides a physical dual-core ARM CPU, which is exploited for control and to deliver output over the integrated Gigabit Ethernet connection.

show abstract

“…This supports the GPU accelerated computer vision for ADAS of vehicles. GPU acceleration can boost the speed of detection [30]; and, it can boost the speed of distance measurement via computer vision by a great degree [31].…”

Section: Distance Measurement Systems On Vehiclesmentioning

confidence: 99%

Distance measurement system for smart vehicles

Zhao

Mammeri

Boukerche

2015

2015 7th International Conference on New Technologies, Mobility and Security (NTMS)

View full text Add to dashboard Cite

Advanced Driver Assistance Systems (ADAS) refer to the set of smart components such as object detection and tracking systems used to protect drivers and road users. An important task that should be performed by ADAS is the measurement of the distance between a vehicle and a detected object. This helps to anticipate the position of objects in the lane, prevents collisions and improves the safety on the road. For this purpose, Distance Measurement Systems (DMS) including Visionbased techniques, Millimeter wave radars, Infrared ranging, and LIDAR are used in the automotive industry. In this paper, we discuss the design of such systems and their use in smart vehicles. Particular attention is given to vision-based techniques because they are considered among the most accurate systems used to identify targets and to measure the distance from them to a vehicle.

show abstract

Real-time semi-global matching disparity estimation on the GPU

Cited by 49 publications

References 15 publications

Looking at Vehicles on the Road: A Survey of Vision-Based Vehicle Detection, Tracking, and Behavior Analysis

Looking at Vehicles on the Road: A Survey of Vision-Based Vehicle Detection, Tracking, and Behavior Analysis

3DV — An embedded, dense stereovision-based depth mapping system

Distance measurement system for smart vehicles

Contact Info

Product

Resources

About

Real-time semi-global matching disparity estimation on the GPU

Cited by 49 publications

References 15 publications

Looking at Vehicles on the Road: A Survey of Vision-Based Vehicle Detection, Tracking, and Behavior Analysis

Looking at Vehicles on the Road: A Survey of Vision-Based Vehicle Detection, Tracking, and Behavior Analysis

3DV &#x2014; An embedded, dense stereovision-based depth mapping system

Distance measurement system for smart vehicles

Contact Info

Product

Resources

About

3DV — An embedded, dense stereovision-based depth mapping system