JACIII Vol.23 No.1 pp. 97-101
doi: 10.20965/jaciii.2019.p0097

Short Paper:

The Framework of Passable Region Recognition Based on Vanish-Line

Xintian Cheng

Jinling Institute of Technology
Room 522, No.99, Hongjing Road, Nanjing, Jiangsu, China

April 26, 2018
June 18, 2018
January 20, 2019
unstructured, normalized cross correlation, weight-accuracy

For the defect of the traditional vanishing point detection algorithm that is invalid in unstructured environment, a novel vanishing detection algorithm based on Dynamic Template Matching (DTM) is proposed. And a framework of access area recognition is put forward according to the vanishing point line. First, a series of lines are selected from the image in the form of the scanning at the same interval and then calculate the between each line and the previous one. The horizontal position of vanish point is that of the line with the minimum normalized correlation value in all scanning line. Second, a new image is constructed by getting rid of the part above of the viewpoint line, and be divided into several subimages without overlap to extract the multi features. The end, a train set is constructed based on the assumption of no deviation of the vehicle and the test set is classified by multi-kernel learning (MKL) method to obtain passable area. In addition, according to the need of intelligent vehicles during working, a weight-accuracy is delimited by assigning the different weights to the near areas and far areas. This kind of accuracy is more significative than the original one. In the experiments on various environments image sets, the proposed method exhibits favorable performances compared to the other methods.

Cite this article as:
X. Cheng, “The Framework of Passable Region Recognition Based on Vanish-Line,” J. Adv. Comput. Intell. Intell. Inform., Vol.23 No.1, pp. 97-101, 2019.
Data files:
  1. [1] Q. Li, N. Zheng, and H. Cheng, “Springrobot: A Prototype Autonomous Vehicle and its Algorithms for Lane Detection,” IEEE Trans. on Intelligent Transportation Systems, Vol.5, pp. 300-308, 2004.
  2. [2] I. A. Sulistijono and N. Kubota, “Human Head Tracking Based on Particle Swarm Optimization and Genetic Algorithm,” J. Adv. Comput. Intell. Intell. Inform.,Vol.11, No.6, pp. 681-687, 2007.
  3. [3] J. M. Álvarez and A. M. Lopez, “Road Detection Based on Illuminant Invariance,” IEEE Trans. Intell. Transp. Syst., Vol.12, pp. 184-193, 2011.
  4. [4] G. Kaur and D. Kumar, “Lane Detection Techniques: A Review,” Int. J. of Computer Applications, Vol.112, pp. 4-8, 2015.
  5. [5] S. P. Narote, P. N. Bhujbal, A. S. Narote, et al., “A Review of Recent Advances in Lane Detection and Departure Warning System,” Pattern Recognition, Vol.6, pp. 216, 2017.
  6. [6] Y. Zhou, R. Xu, X. Hu, et al., “A robust lane detection and tracking method based on computer vision,” Measurement Science & Technology, Vol.17, pp. 736, 2006.
  7. [7] N. Werghi, S. Berretti, and A. del Bimbo, “The Mesh-LBP: A Framework for Extracting Local Binary Patterns From Discrete Manifolds,” IEEE Trans. on Image Processing, Vol.24, pp. 220-235, 2015.
  8. [8] X. Hong, G. Zhao, M. Pietikainen, et al., “Combining LBP Difference and Feature Correlation for Texture Description,” IEEE Trans. on Image Processing, Vol.23, pp. 2557-2568, 2014.
  9. [9] P. Filitchkin and K. Byl, ”Feature-based Terrain Classification for LittleDog,” Int. Conf. on Intelligent Robots and Systems, pp. 1387-1392, 2012.
  10. [10] Y. Hamasuna, and Y. Endo, “On Sequential Cluster Extraction Based on L1-Regularized Possibilistic ıtc-Means,” J. Adv. Comput. Intell. Intell. Inform., Vol.19, No.5, pp. 655-661, 2015.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Jul. 12, 2024