Performance Evaluation of Stereo Algorithms for Automotive Applications

Steingrube, Pascal; Gehrig, Stefan; Franke, Uwe

doi:10.1007/978-3-642-04667-4_29

Cited by 34 publications

(17 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The goal was to publish large datasets to support other researchers to verify and evaluate their algorithms. An evaluation strategy for stereo algorithms on large amounts of images was also proposed in [36]. In that publication a performance evaluation scheme and corresponding metrics were suggested.…”

Section: Evaluation Of Computer Vision Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

An Evaluation Framework for Stereo-Based Driver Assistance

Schneider

Gehrig

Pfeiffer

et al. 2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. The accuracy of stereo algorithms or optical flow methods is commonly assessed by comparing the results against the Middlebury database. However, equivalent data for automotive or robotics applications rarely exist as they are difficult to obtain. As our main contribution, we introduce an evaluation framework tailored for stereo-based driver assistance able to deliver excellent performance measures while circumventing manual label effort. Within this framework one can combine several ways of ground-truthing, different comparison metrics, and use large image databases. Using our framework we show examples on several types of groundtruthing techniques: implicit ground truthing (e.g. sequence recorded without a crash occurred), robotic vehicles with high precision sensors, and to a small extent, manual labeling. To show the effectiveness of our evaluation framework we compare three different stereo algorithms on pixel and object level. In more detail we evaluate an intermediate representation called the Stixel World. Besides evaluating the accuracy of the Stixels, we investigate the completeness (equivalent to the detection rate) of the Stixel World vs. the number of phantom Stixels. Among many findings, using this framework enables us to reduce the number of phantom Stixels by a factor of three compared to the base parametrization. This base parametrization has already been optimized by test driving vehicles for distances exceeding 10000 km.

show abstract

Section: Evaluation Of Computer Vision Algorithmsmentioning

confidence: 99%

“…The main aim of our evaluation framework is to provide an automatic method for evaluating and optimizing different stereo and flow algorithms over a large dataset [36]. By now, it has proved its strength to be well suited for all kind of image processing tasks.…”

Section: Evaluation Frameworkmentioning

confidence: 99%

An Evaluation Framework for Stereo-Based Driver Assistance

Schneider

Gehrig

Pfeiffer

et al. 2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Unlike other methods, in practice, SGM appears rather robust and insensitive to the choice of parameters. This makes it suitable for real world applications like tile-wise aerial image matching (Hirschmüller, 2008) (Gehrke et al, 2010) and automotive applications (Steingrube et al, 2009). The SGM describes a very efficient approximation method to find the minimum of a global energy function based on the input images.…”

Section: Image Matchingmentioning

confidence: 99%

Real Time Data Processing for Optical Remote Sensing Payloads

Wohlfeil

Börner²,

Buder

et al. 2012

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:The application of operational systems for remote sensing requires new approaches for data processing. It has to be the goal to derive user relevant information close the sensor itself and to downlink this information to a ground station or to provide them as input to an actuator of the space-borne platform. A complete automation of data processing is an essential first step for a thematic onboard data processing. In a second step, an appropriate onboard computer system has to be de-signed being able to fulfill the requirements. In this paper, standard data processing steps will be introduced correcting systematic errors during image capturing. A new hardware operating system, which is the interface between FPGA hardware and data processing algorithms, gives the opportunity to implement complex data processing modules in an effective way. As an example the derivation the camera's orientation based on data of an optical payload is described in detail. The thereby derived absolute or relative orientation is essential for high level data products. This will be illustrated by means of an onboard image matcher

show abstract

“…In order to produce a quantitative estimation of the algorithm performance two of the three metrics presented in [16] have been computed on a 1000 frames sequence acquired in the downtown of Kiev (Ukraine) on August, 5, 2010 approximately at 14:00 local time. While this data represents only a tiny fraction of the whole trip it is quite representative of typical driving conditions in city traffic.…”

Section: A Performancementioning

confidence: 99%

“…The second metric is the leader vehicle lateral position measurement, defined as m l p = |l p measure −l p groundtruth |, with the ground truth being generated by direct LIDAR measurements of the preceding vehicle. Table II contains the computed values, both for the correlation-based and SGM stereo matching algorithms; as a reference, the values reported in [16] have also been inserted in the table, although they refer to a different dataset. The results are very similar; only the m f c value for the SGM reconstruction case changes significantly, probably because of the different amount of data the test has been run on.…”

Section: A Performancementioning

confidence: 99%

Stereo obstacle detection in challenging environments: The VIAC experience

Broggi

Buzzoni

Felisa

et al. 2011

2011 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-Obstacle detection by means of stereo-vision is a fundamental task in computer vision, which has spurred a lot of research over the years, especially in the field of vehicular robotics. The information provided by this class of algorithms is used both in driving assistance systems and in autonomous vehicles, so the quality of the results and the processing times become critical, as detection failures or delays can have serious consequences. The obstacle detection system presented in this paper has been extensively tested during VIAC, the VisLab Intercontinental Autonomous Challenge [1], [2], which has offered a unique chance to face a number of different scenarios along the roads of two continents, in a variety of conditions; data collected during the expedition has also become a reference benchmark for further algorithm improvements.

show abstract

Performance Evaluation of Stereo Algorithms for Automotive Applications

Cited by 34 publications

References 8 publications

An Evaluation Framework for Stereo-Based Driver Assistance

An Evaluation Framework for Stereo-Based Driver Assistance

Real Time Data Processing for Optical Remote Sensing Payloads

Stereo obstacle detection in challenging environments: The VIAC experience

Contact Info

Product

Resources

About