Curb Detection Based on Elevation Maps from Dense Stereo

Oniga, Florin; Nedevschi, Sergiu; Meinecke, Marc-Michael

doi:10.1109/iccp.2007.4352150

Cited by 15 publications

(28 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where a is a scale factor to balance the numeric issue between the stereo depth uncertainty and the cost value which is set as a ¼ 10 in this article, and λ is a scale factor as well, c i is the cost value calculated from the fused features, and z err is the stereo uncertainty 44 which is modeled as follows…”

Section: Covariance Matrix Selectionmentioning

confidence: 99%

Gaussian process regression-based robust free space detection for autonomous vehicle by 3-D point cloud and 2-D appearance information fusion

Xiao

Dai

et al. 2017

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

Free space detection is crucial to autonomous vehicles while existing works are not entirely satisfactory. As cameras have many advantages on environment perception, a stereo vision-based robust free space detection method is proposed which mainly depends on geometry information and Gaussian process regression. In this work, in order to improve the performance by exploiting multiple source information, we apply Bayesian framework and conditional random field inference to fuse the multimodal information including 2-D image and 3-D point geometric information. Particularly, a Bayesian framework is used for multiple feature fusion to provide a normalized and flexible output. Gaussian process regression is used to automatically and incrementally regress the data, resulting enhanced performance. Finally, conditional random field with color and geometry constrains is applied to make the result more robust. In order to evaluate the proposed method, quantitative experiments on popular KITTI-road data set and qualitative experiments on our own campus data set are tested. The results show satisfactory and inspiring performance compared to the outstanding works and even are competitive to some relevant Lidar-based methods.

show abstract

Section: Covariance Matrix Selectionmentioning

confidence: 99%

Gaussian process regression-based robust free space detection for autonomous vehicle by 3-D point cloud and 2-D appearance information fusion

Xiao

Dai

et al. 2017

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

show abstract

“…Both methods [1] and [2] detect curb as lines in the space of interest, without extracting the actual curb segments along these lines. In many scenes, real curbs are segments (with visible ends) in the space of interest.…”

Section: Introductionmentioning

confidence: 99%

“…Approaches [1] and [2] deal explicitly with curb detection. Both are based on the extraction of linear curbs with the Hough transform.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Curb segments detection with temporal filtering for urban driving scenarios

Oniga

Nedevschi

Meinecke

2008

2008 4th International Conference on Intelligent Computer Communication and Processing

Self Cite

View full text Add to dashboard Cite

An improved approach for the detection of curbs (border of relevant traffic isles, sidewalks, etc) is presented, in the context of urban driving assistance systems. A rectangular elevation map is built from 3D dense stereo data. Edge detection is applied to the elevation map in order to highlight height variations. Temporal filtering is performed for edge points, based on the ego car motion, and only persistent points are validated. Relevant lines are extracted using a Hough accumulator. Curb segments are extracted from each relevant line by applying a set of proposed conditions. The algorithm was evaluated in an urban scenario. It works in real-time and provides robust detection of curbs.

show abstract

“…Because of the height difference between the road surface and road shoulder, the curb is represented as an edge in the depth image. The most direct way of curb detection is to find the curb line from the depth map (60) . More sophisticated algorithm for curb detection was developed based on the texture and depth information together, which is shown in Fig.…”

Section: (A) (B) (C)mentioning

confidence: 99%

Autonomous Vehicle Technologies :Localization and Mapping

俊介

艶磊

立達

2015

Fundamentals Review

View full text Add to dashboard Cite

Vehicle self-localization is an important and challenging issue in current driving assistance and autonomous driving research activities. This paper mainly investigates two kinds of methods for vehicle self-localization: active sensor based and passive sensor based. Active sensor based localization was firstly proposed for robot localization, and was introduced into autonomous driving recently. The Simultaneous Localization and Mapping (SLAM) techniques is the representative in active sensor based localization. The passive sensor based localization technologies are categorized and explained based on the type of sensors, Global Navigation Satellite System (GNSS), inertial sensors and cameras. In this paper, researches utilizing active sensors and passive sensors for autonomous vehicles are reviewed extensively. Finally, our challenges on self-localization in urban canyon by the system integration of passive sensors is introduced. GNSS error has been improved for the purpose of the self-localization in urban canyon. The performance of the proposed method would suggest possible solution autonomous vehicles which makes use of passive sensors more.

show abstract

Curb Detection Based on Elevation Maps from Dense Stereo

Cited by 15 publications

References 11 publications

Gaussian process regression-based robust free space detection for autonomous vehicle by 3-D point cloud and 2-D appearance information fusion

Gaussian process regression-based robust free space detection for autonomous vehicle by 3-D point cloud and 2-D appearance information fusion

Curb segments detection with temporal filtering for urban driving scenarios

Autonomous Vehicle Technologies :Localization and Mapping

Contact Info

Product

Resources

About