Enhanced Roadway Geometry Data Collection Using an Effective Video Log Image-Processing Algorithm

Abstract

With the advancement of information technology, video logging has become a feasible and common practice for state-level departments of transportation (DOTs) to visualize roadway conditions to support various transportation activities. A new and innovative image-processing algorithm and method using video log images to enhance the highway roadway geometry data collection is presented. The algorithm is based on Canny edge detection, slope-adaptive edge reduction, a novel recursive approximation of the vanishing point, localized color thresholding, and knowledge-based Hough transform. Experiments on real digital images indicate that the algorithm is feasible for automated road geometric data collection, especially in recognizing lane marks and shoulder edges. The algorithm was implemented with Visual C++ language and tested on a Pentium IV 3.06-GHz computer. It indicates that the average processing speed is about 280 ms for an image size of 1,300 × 1,050. The developed method can be used by state DOTs to save money and cost by flagging the video images with a variation index. Thus, the video images with a high variation index (e.g., changing lane location) can be identified for a focused visual measurement Future studies for evaluating the algorithm under various weather, lighting, and roadway conditions are also discussed.

References

Tsai

and Wu

. Shape and Texture-Based 1-D Image Processing Algorithm for Real-Time Stop Sign Road Inventory Data Collection. Journal of Intelligent Transportation Systems, Vol. 7, 2003, pp. 213–234.

and Tsai

. Speed Limit Extraction and Recognition Algorithm Using Locally Adaptive Thresholding and Depth-First-Search. Photogrammetric Engineering and Remote Sensing Journal, Vol. 71, No. 4 2005, pp. 405–414.

Behringer

Road Recognition from Multifocal Vision. Proceedings of IEEE Intelligent Vehicle 1994, Paris, 1994, pp. 302–307.

Kluge

Extracting Road Curvature and Orientation from Image Edge Points Without Perceptual Grouping into Features. Proceedings of IEEE Intelligent Vehicles 1994, Paris, 1994, pp. 109–114.

Pomerleau

RALPH: Rapidly Adapting Lateral Position Handler. Proceedings of IEEE Intelligent Vehicle Symposium, Detroit, Mich., Sept. 1995, pp. 506–511.

Kluge

A Deformable-Template Approach to Lane Detection. Proceedings of IEEE Intelligent Vehicle Symposium, Detroit, Mich., Sept. 1995, pp. 54–59.

Kreucher

Lakshmanan

and Kluge

. A Driver Warning System Based on the LOIS Lane Detection Algorithm. Proceedings of IEEE International Conference on Intelligent Vehicles, Stuttgart, Germany, Oct. 28–30, 1998, pp. 17–22.

Kreucher

and Lakshmanan

. LANA: A Lane Extraction Algorithm That Uses Frequency Domain Features. IEEE Transactions on Robotics and Automation, Vol. 15, No. 2 1999, pp. 343–350.

Takahashi

Ninomiya

Ohta

and Tange

K. A.

. Robust Lane Detection Using Real-Time Voting Processor. Proceedings of the IEEE Intelligent Transportation Systems, Tokyo, Japan, Oct. 5–8, 1999, pp. 76–79.

10.

Apostoloff

and Zelinsky

. Robust Vision-Based Lane Tracking Using Multiple Cues and Particle Filtering. Proceedings of the IEEE Intelligent Vehicles Symposium 2003, Columbus, Ohio, June 9–11, 2003, pp. 558–563.

11.

Gern

Moebus

and Franke

. Vision-Based Lane Recognition Under Adverse Weather Conditions Using Optical Flow. Proceedings of the IEEE Intelligent Vehicles Symposium 2002, Versailles, France, June 17–21, 2002, pp. 652–657.

12.

Wang

and Ji

. A Vision Navigation Algorithm Based on Linear Lane Model. Proceedings of the IEEE Intelligent Vehicles Symposium 2000, Dearborn, Mich., Oct. 3–5, 2000, pp. 240–245.

13.

Bertozzi

Broggi

Cellario

Fascioli

Lombardi

and Porta

. Artificial Vision in Road Vehicles. Proceedings of the IEEE—Special issue on Technology and Tools for Visual Perception, Vol. 90, No. 7 2002, pp. 1258–1271.

14.

Bucher

Measurement of Distance and Height in Images Based on Easy Attainable Calibration Parameters. Proceedings of the IEEE Intelligent Vehicles Symposium 2000, Dearborn, Mich., Oct. 3–5, 2000, pp. 314–319.

15.

Hough

P. V.

Methods and Means to Recognized Complex Patterns. U.S. Patent 3,069,654, 1962.

16.

Barnard

S. T.

Interpreting Perspective Images. Artificial Intelligence Journal, Vol. 21, No. 4 1983, pp. 435–462.

17.

Quan

and Mohr

. Determining Perspective Structures Using Hierarchical Hough Transform. Pattern Recognition Letters, Vol. 9, 1989, pp. 279–286.

18.

Magee

M. J.

and Aggrawal

J. K.

. Determining the Vanishing Points from the Perspective Images. CVGIP, Vol. 26, 1984, pp. 256–267.

19.

Collins

R. T.

and Weiss

R. S.

. Vanishing Point Calculation As a Statistical Inference on the Unit Sphere. Proc., 3rd Conference on Computer Vision (ICCV'90), Osaka, Japan, Dec. 1990, pp. 400–403.

20.

Baltzakis

H. G.

and Trahanias

P. E.

. The VPLF Method for Vanishing Point Computation. Image and Vision Computing, Vol. 19, 2001, pp. 393–400.

21.

Collins

and Weiss

. An Efficient and Accurate Method for Computing Vanishing Points. In Proceedings of the Optical Society of America Workshop, Image Understanding and Machine Vision, Vol. 14, 1989, pp. 92–94.

22.

McLean

G. F.

and Kotturi

. Vanishing Point Detection by Line Clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 17, No. 11 1995, pp. 1090–1095.

23.

Shufelt

J. A.

Performance Evaluation and Analysis of Vanishing Point Detection Techniques. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 21, No. 3 1999, pp. 282–288.

24.

Canny

A Computational Approach to Edge Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 8, No. 6 1986, pp. 679–698.