|Table of Contents|

Automatic detection method of roads from fuzzy aerial images(PDF)

《交通运输工程学报》[ISSN:1671-1637/CN:61-1369/U]

Issue:
2015年04期
Page:
110-117
Research Field:
交通信息工程及控制
Publishing date:

Info

Title:
Automatic detection method of roads from fuzzy aerial images
Author(s):
LIU Sheng;  WANG Wei-xing;  WANG Shan-shan;  HAN Ya;  HUANG Ling-xiao;  ZHANG Xin
School of Information Engineering, Chang’an University, Xi’an 710064, Shaanxi, China
Keywords:
image processing;  road detection;  fuzzy aerial image;  multi-scale;  Retinex algorithm;  Canny edge detection algorithm;  road shape
PACS:
U491.2
DOI:
-
Abstract:
In order to accurately detect the road from fuzzy aerial images, an automatic road detection method was proposed based on the characteristics of roads in images. The fuzzy images were enhanced by using multiple scale Retinex algorithm. The main road segments in images were detected by using improved Canny edge detection algorithm, and the high and low thresholds in gradient images were automatically obtained by using cross-entropy theory and Bayesian judgment theory, the gray image was transformed into the binary images, and the skeletons of linear target in the image were extracted. The noise was filtered based on the shape and size characteristics in the linear target, the gaps between segments were linked based on the curvatureand the distances between segments, and the detected road was adjusted and modified by combing the edge and the original image information. The proposed automatic road detection method was compared with several widely used traditional algorithms, such as Otsu threshold segmentation algorithm, Canny edge detection algorithm, and graph theory based on the minimum segmentation algorithm. a single road, cross roads and several roads in fuzzy images were detected by using the proposed road detection method. Detection result indicates that as for fuzzy or uneven-illumination aerial road images, the trunk roads can be clearly displayed after enhancing images by Retinex algorithm, while the conventional image segmentation algorithm can not do. The trunk road can be well extracted by using the improved Canny edge detection algorithm with image post-processing function. In the detection of single road, cross roads and several roads in the fuzzy aerial images, the target roads can be clearly detected by using the proposed method. The effect of detection method is close to the result of artificial recognition. 20 figs, 21 refs.

References:

[1] FISCHLER M A, TENENBAUM J M, WOLF H C. Detection of roads and linear structures in low-resolution aerial imagery using a multisource knowledge integration technique[J]. Computer Graphics and Image Processing, 1981, 15(3): 201-223.
[2] 杨 俊,王润生.遥感道路的场景感知与分类检测[J].计算机辅助设计与图形学学报,2007,19(3):334-339.YANG Jun, WANG Run-sheng. Scene perception and classified detection for roads in remote sensing images[J]. Journal of Computer-Aided Design and Computer Graphics, 2007, 19(3): 334-339.(in Chinese)
[3] CORD A, CHAMBON S. Automatic road defect detection by textural pattern recognition based on AdaBoost[J]. Computer-Aided Civil and Infrastructure Engineering, 2012, 27(4): 244-259.
[4] RAJESWARI M, GURUMURTHY K S, REDDY L P, et al. Automatic road extraction based on level set normalized cuts and mean shift methods[J]. International Journal of Computer Science Issues, 2011, 8(3): 250-257.
[5] HILLEL A B, LERNER R, LEVI D, et al. Recent progress in road and lane detection: a survey[J]. Machine Vision and Applications, 2014, 25(3): 727-745.
[6] üNSALAN C, SIRMACEK B. Road network detection using probabilistic and graph theoretical methods[J]. IEEE Transaction on Geoscience and Remote Sensing, 2012, 50(11): 4441-4453.
[7] HU Jiu-xiang, RAZDAN A, FEMIANI J C, et al. Road network extraction and intersection detection from aerial images by tracking road footprints[J]. IEEE Transactions on Geoscience and Remote Sensing, 2007, 45(12): 4144-4157.
[8] 罗庆洲,尹 球,匡定波.光谱与形状特征相结合的道路提取方法研究[J].遥感技术与应用,2007,22(2):339-344.LUO Qing-zhou, YIN Qiu, KUANG Ding-bo. Research on extracting road based on its spectral feature and shape feature[J]. Remote Sensing Technology and Application, 2007, 22(2): 339-344.(in Chinese)
[9] SALAH M B, MITICHE A, AYED I B. Multiregion image segmentation by parametric kernel graph cuts[J]. IEEE Transactions on Image Processing, 2011, 20(2): 545-557.
[10] ZHANG Shao-yang, WANG Wei-xing, LIU Sheng, et al. Image enhancement on fractional differential for road traffic and aerial images under bad weather and complicated situations[J]. Transportation Letters: The International Journal of Transportation Research, 2014, 6(4): 197-205.
[11] 王卫星,于 鑫,赖 均.一种改进的分数阶微分掩模算子[J].模式识别与人工智能,2010,23(2):171-177.WANG Wei-xing, YU Xin, LAI Jun. An improved fractional differential mask[J]. Pattern Recognition and Artificial Intelligence, 2010, 23(2): 171-177.(in Chinese)
[12] MA Rong-gui, WANG Wei-xing, LIU Sheng. Extracting roads based on Retinex and improved Canny operator with shape criteria in vague and unevenly illuminated aerial images[J]. Journal of Applied Remote Sensing, 2012, 6(23): 1-14.
[13] WANG Wei-xing, ZHAO Wei-sen, HUANG Ling-xiao, et al. Applications of terrestrial laser scanning for tunnels: a review[J]. Journal of Traffic and Transportation Engineering: English Edition, 2014, 1(5): 325-337.
[14] WANG Wei-xing. Image analysis of aggregates[J]. Computers and Geosciences, 1999, 25(1): 71-81.
[15] WANG Wei-xing. Colony image acquisition system andsegmentation algorithms[J]. Optical Engineering, 2011, 50(12): 1-9.
[16] ZHAO Xiang-mo, WANG Wei-xing, WANG Li-ping. Parameter optimal determination for Canny edge detection[J]. Imaging Science Journal, 2011, 59(9): 332-341.
[17] WANG Wei-xing, BERGHOLM F, YANG B. Froth delineation based on image classification[J]. Minerals Engineering, 2003, 16(11): 1183-1192.
[18] RAHMAN Z U, JOBSON D J, WOODELL G A. Investigating the relationship between image enhancement and image compression in the context of the multi-scale retinex[J]. Journal of Visual Communication and Image Representation, 2011, 22(3): 237-250.
[19] KIMMELR, ELAD M, SHAKED D, et al. A variational framework for Retinex[J]. International Journal of Computer Vision, 2003, 52(1): 7-23.
[20] WANG Wei-xing, LUO Dai-jian, LI Wei-sheng. Algorithm for automatic image registration on Harris-Laplace feature[J]. Journal of Applied Remote Sensing, 2009, 3(8): 1-13.
[21] 雷小奇,王卫星,赖 均.一种基于形状特征进行高分辨率遥感影像道路提取方法[J].测绘学报,2009,38(5):457-465.LEI Xiao-qi, WANG Wei-xing, LAI Jun. A method of road extraction from high-resolution remote sensing images based on shape features[J]. Acta Geodaetica et Cartographica Sinica, 2009, 38(5): 457-465.(in Chinese)

Memo

Memo:
-
Last Update: 2015-08-30