Line Segment Optimization Algorithm for High Resolution Optical Remote Sensing Image Based on Geometric and Texture Constraints

doi:10.11947/j.JGGS.2020.0311

Abstract

Abstract: Aiming at the problem that high-resolution optical remote sensing image, lines are prone to fracture, and a line segment optimization algorithm is proposed in this paper. Firstly, the line segment is regarded as a way to express the contour of the ground object,and the laws of line segment fracture from two aspects of geometric features and texture features are analyzed; Secondly, the line segment optimization algorithm is proposed. It takes the results of detecting line segments as the processing primitives, determines the initial optimized line segment according to the length of the line segment, establishes the tracking rectangular region and geometric constraint model for the fractured line segments, builds a dynamic optimization model, and gives a complete line optimization process. Through the analysis of experimental results of multiple actual scenes and different types of remote sensing images, it is shown that this algorithm can not only solve the problem of line segment fracture caused by terrain occlusion, edge blurring, and edge serration, but also comparing with other methods, the proposed algorithm has great advantages in optimizing line length and restraining over extraction problem.

Key words: optimization; line segment; constraint

DAI Jiguang,GU Yue,JIN Guang,ZHU Lei. Line Segment Optimization Algorithm for High Resolution Optical Remote Sensing Image Based on Geometric and Texture Constraints[J]. Journal of Geodesy and Geoinformation Science, 2020, 3(3): 115-127.

Figures/Tables 12

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Fig.10

Tab.1

References 25

[1]	ZHANG Linyan, ZHU Li . 3D line segments reconstruction for building facades with line matching across multi-image with non-geometry constraint[J]. Journal of Xi’an Jiaotong University, 2014,48(4):15-19, 25.
[2]	MARSHALL S . Line structure representation for road network analysis[J]. The Journal of Transport and Land Use, 2016,9(1):29-64.
[3]	WANG C K, HSU P H . Building detection and structure line extraction from airborne LiDAR data[J]. Journal of Photogrammetry and Remote Sensing, 2007,12(4):365-379.
[4]	TSENG Y H, HUNG H C. Extraction of building boundary lines from airborne LiDAR point clouds[J]. ISPRS-International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2016, XLI-B3:957-962.
[5]	DAI Jiguang, ZHANG Li, LI Jinwei , et al. A line extraction method for chain code tracking with phase verification[J]. Acta Geodaetica et Cartographica Sinica, 2017,46(2):218-227. DOI: 10.11947/j.AGCS.2017.20160303.
[6]	BALLARD D H . Generalizing the Hough transform to detect arbitrary shapes[J]. Pattern Recognition, 1981,13(2):111-122.
[7]	XU Shenghua, ZHU Qing, LIU Jiping , et al. Straight line extraction via multi-scale Hough transform based on pre-storage weight matrix[J]. Acta Geodaetica et Cartographica Sinica, 2008,37(1):83-88. DOI: 10.3321/j.issn:1001-1595.2008.01.015.
[8]	WANG Jingxue, ZHU Qing, WANG Weixi , et al. Straight line extraction algorithm by Hough transform combining edge grouping[J]. Journal of Remote Sensing, 2014,18(2):378-389.
[9]	XU Zezhong, SHIN B S, KLETTE R . Accurate and robust line segment extraction using minimum entropy with Hough transform[J]. IEEE Transactions on Image Processing, 2015,24(3):813-822.
[10]	BURNS J B, HANSON A R, RISEMAN E M. Extracting straight lines[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, PAMI-8(4):425-455.
[11]	FREEMAN H. Boundary encoding and processing[M] ∥LIPKIN B S, ROSENFELD A. Picture Processing and Psychopictorics. New York:Academic Press, 1970: 241-266.
[12]	ZHAO Like, SONG Weidong, WANG Jingxue . Straight line extraction algorithm of freeman chain code priority[J]. Geomatics and Information Science of Wuhan University, 2014,39(1):42-46.
[13]	WANG Jingxue, ZHU Qing, ZHANG Yunsheng , et al. Phase grouping line extraction algorithm using overlapped partition[J]. Acta Geodaetica et Cartographica Sinica, 2015,44(7):768-774, 790.
[14]	LI Chang, WEI Dong . A line segment detector based on pixels grouping and step-by-step quality control[J]. Journal of Infrared and Millimeter Waves, 2016,35(6):681-687.
[15]	VON GIOI R G, JAKUBOWICZ J, MOREL J M , et al. LSD:A fast line segment detector with a false detection control[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010,32(4):722-732.
[16]	AKINLAR C, TOPAL C . EDLines:a real-time line segment detector with a false detection control[J]. Pattern Recognition Letters, 2011,32(13):1633-1642.
[17]	LIU Bo, XU Lihua, LU Shengchang . Simulation of extraction and optimization for building image[J]. Computer Simulation, 2015,32(12):327-331.
[18]	XI Xueqiang, ZHAI Weigang, LU Libin . The approach of grouping straight line segments based on perceptual organization[J]. Application Research of Computer, 2002,19(6):64-67.
[19]	DAI Jiguang, ZHANG Li, ZHU Enze , et al. Principal line detection in remote sensing image[J]. Journal of Remote Sensing, 2017,21(2):228-238.
[20]	CHEN Renjie, LIU Ligang, DONG Guangchang . Detection of principal lines in images[J]. Journal of Image and Graphics, 2010,15(3):403-408.
[21]	LI Chang, LI Fangfang . Auto-extracting sub-pixel line feature of digital images based on hypojournal testing[J]. Acta Geodaetica et Cartographica Sinica, 2013,42(1):67-72.
[22]	CHO N G, YUILLE A, LEE S W . A novel linelet-based representation for line segment detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018,40(5):1195-1208.
[23]	ZHU Changsheng, ZHOU Wei, GUAN Jian . Main road extraction from SAR imagery based on parallel pairs detection[J]. Journal of Image and Graphics, 2011,16(10):1908-1917.
[24]	STEGER C, ULRICH M, WIEDEMANN C. Machine vision algorithms and applications[M]. YANG Shaorong, WU Dijing, DUAN Deshan, trans. Beijing:Tsinghua University Press, 2008.
[25]	SARKAR S. An introduction to perceptual organization [C]∥Proceedings of the IEMC’03 Proceedings. Managing Technologically Driven Organizations:The Human Side of Innovation and Change. Cambridge, MA:IEEE, 2003: 330-335.

Programs	The proposed algorithm			The algorithm in Literature [21]				The algorithm in Literature [22]
Programs	Fig.8	Fig.9	Fig.10		Fig.8	Fig.9	Fig.10		Fig.8	Fig.9	Fig.10
Line segment to be optimized/strip	90	100	200	90		100	200	169		264	1870
Error Optimizing Line Segments/strip	2	6	10	13		21	40	0		0	0
Total number of line segments after optimization/strip	1417	4793	11964	1396		4752	11879	1278		2350	8280
Total length of optimized line segment/ megapixel	2.94	8.55	31.54	2.95		8.57	31.57	2.15		4.07	17.57
Average length of optimized line segment/ pixel	20.75	17.84	26.36	21.13		18.03	26.58	16.82		17.66	21.22
Time consuming/s	13.90	33.03	314.62	2.66		10.55	55.63	31.18		143.35	856.89