A lane detection algorithm based on reliable lane markings

Yeniaydın, Yasin
Schmidt, Klaus Verner
This paper proposes a robust and effective vision-based lane detection approach. First, two binary images are obtained from the region of interest of gray-scale images. The obtained binary images are merged by a novel neighborhood AND operator and then transformed to a bird's eye view (BEV) via inverse perspective mapping. Then, gaussian probability density functions are fit to the left and right regions of a histogram image acquired from the BEV. Finally, a polynomial lane model is estimated from the identified regions. Experimental results show that the proposed method accurately detects lanes in complex situations including worn-out and curved lanes.


A lane keeping system with a weighted preview measurement
Saraçoğlu, Kıvanç; Üleş, Buğra; Schmidt, Klaus Verner (2018-07-09)
This paper proposes a new lane keeping system (LKS) based on a weighted preview measurement. The paper first identifies shortcomings of existing methods that use the sole measurement of lateral displacement error at a preview distance or at the center of gravity. Then, the novel idea of computing a weighted average of both measurements is proposed. The stability of the resulting LKS is analyzed and the improved performance of the resulting LKS is supported by simulation experiments.
Robust Lane Recognition Based on Arc Splines
Yeniaydın, Yasin; Schmidt, Klaus Verner (null; 2018-10-26)
This paper develops a general lane detection method and proposes new techniques for feature extraction and lane modeling. The proposed method first determines a static region of interest. Then, feature extraction is used to establish candidate lane pixels in a binary image. Next, the binary image is transformed to a bird's eye view (BEV) via inverse perspective mapping. After that, a reliable region for the detection of the left or right lane markings is chosen based on the distribution of the candidate lan...
A method for detecting RGPO/VGPO jamming
Kural, F; Ozkanzanc, Y (2004-04-30)
This paper proposes a general approach to detect the presence of deceptive counter measures such as RGPO or VGPO. The method which is based on Kalman filter lays its foundation on drift between Doppler measurement and the Doppler information obtained from the range measurement of a target in track. By measuring this drift by Mahalonobis distance metric and comparing it with a predefined threshold; detection is performed. The performance of the proposed approach is illustrated through a simulation.
A Graph-Based Approach for Video Scene Detection
Sakarya, Ufuk; Telatar, Zjya (2008-04-22)
In this paper, a graph-based method for video scene detection is proposed. The method is based on a weighted undirected graph. Each shot is a vertex on the graph. Edge weights among the vertices are evaluated by using spatial and temporal similarities of shots. By using the complete information of the graph, a set of the vertices mostly similar to each other and dissimilar to the others is detected. Temporal continuity constraint is achieved on this set. This set is the first detected video scene. The verti...
A Multi-Dimensional Hough Transform Algorithm Based on Unscented Transform as a Track-Before-Detect Method
Sahin, Gozde; Demirekler, Mübeccel (2014-07-10)
In this study, a new Multi-Dimensional Hough Transform technique is proposed for the detection of dim targets in radar data. Multi-Dimensional Hough Transform is a Track-Before-Detect method that fuses Hough Transform results obtained on (x-t), (y-t) and (x-y) domains. The proposed study models Hough Transform results in (x-t) and (y-t) domains by Gaussians and transforms these Gaussians to (x-y) domain using Unscented Transform. This improves the computational efficiency significantly without degrading per...
Citation Formats
Y. Yeniaydın and K. V. Schmidt, “A lane detection algorithm based on reliable lane markings,” 2018, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/43263.