An effective method to detect straight lines from high spatial resolution remotely sensed imagery and its applications for runway extraction
This paper presents a straight line extraction method combining Canny edge detection, vectorization, topology cleaning, and depth-first search to identify long, straight features such as airport runways in high-resolution remotely sensed imagery, achieving effective runway detection through gap filling and line grouping.
It has always been an important low-level operation to extract edges from images in the fields of computer vision and image procession, in which straight line extraction is typical and representative. Because most man-made spatial objects, e.g. buildings, roads, etc. often take on near straight-line boundaries, extracting straight lines is often the first step to extract these targets. Straight lines can then be looked as the elementary units for other higher level image interpretations. In this paper, a straight line extraction method combining edge detection and depth-first searching on the vector line layer is proposed and applied to extract runways of airports. The steps include: 1) edges are found with the Canny operator and vectorirzed. The reason to use the Canny operator is because it is designed to be an optimal edge detector, which gives very good results on detecting step or slop like edges. It takes as input a grey scale image, and produces as output an image showing the positions of tracked intensity discontinuities. After this operation, we then vectorize the edge points to be a vector layer with edge tracing.2) With the vector-formatted edge lines, the straight line searching can then be carried out. In order to complete this, topology between arcs should be cleaned and rebuilt, which includes the deletion of repetitive, one-node arcs, and splitting on the intersections, etc. 3) Straight lines are detected with the depth-first searching strategy. With the rebuilt topology, we can easily obtain the begin, end nodes of every line. If the distances of its all vertices to the line connecting the begin, end nodes of an arc are less than some pre-defined threshold, it could be looked as a 'straight line' and extracted. Besides, we are certainly only interested in the straight lines with lengths larger than certain threshold, thus a minimum length threshold should be specified to delete these very short lines. In the searching of straight lines, some arcs should be grouped as a single straight line; some un-straight lines should be split to extract its straight parts. The suitable straight lines are outputted to a vector layer after being reselected and re-grouped, with distinguishing short, long isolating, long not isolating straight lines. With all these steps, we can get the initial straight vector line layer. 4) To these lines with small interspaces but locate on a single straight line, we use a simple but effective connecting step to 'fill' the gaps. Starting from the vector layer and with the operations of broken line connecting and parallel line detection, the main airport runway can be well extracted, which helps us to locate and recognize airports from high spatial remotely sensed imagery.
- Conference Article
51
- 10.1109/dcabes.2018.00037
- Oct 1, 2018
This paper proposes a lane detection method based on the constraint Hough Transform double edge extraction. Firstly, the image of the road is grayed out and dealt with the lane line area extraction process based on the lane width feature and color feature. For grayscale images, the Canny edge detection operator is used to obtain the lane line edge information. Then the lane line features are extracted through the lane line edge information and the lane line area information. For the straight lane line, the Hough transform based on the polar angle and polar radius constraints is used to obtain the double edges of the lane lines, and straight line points are used to determine the end points and starting points of the straight lane lines to complete the straight line fitting. For the curve, the near-field part is a straight line, the far-field is a curve, and the straight part adopts the detection method of the straight lane line, and the characteristic points of the curve are searched in the lane line characteristic diagram. Finally, the curve is fitted by a parabola. Experiments show that the lane detection using the double-edge extraction method is fast and accurate.
- Book Chapter
1
- 10.1007/978-981-13-2224-2_34
- Oct 11, 2018
This paper presents the results of a study undertaken to enhance the stability of a landfill on sloping ground of a hilly region. The base of the landfill has a significant elevation difference from one end to the other causing an overall inclination of the base with the horizontal. The study highlights the influence of the following factors on the base sliding stability along the geomembrane interface as: (a) leachate head; (b) pore water pressures in wet waste; (c) seismic forces and (d) smooth versus textured geomembrane (GM). Limit equilibrium methodology is adopted for analyses and three types of failure surfaces are analysed – circular, planar (single straight line) and planar (two straight lines). The study reveals that stability against sliding along liner is low, whenever (a) pore pressures/leachate head are high; (b) earthquake forces are large and (c) smooth GM are used. Usually planar failure surface (two straight lines) is observed as the critical surface.Furthermore, it is also observed that the stability of the sloping liner can be enhanced significantly by providing adequate size of earthen berm at the toe. After application of the berm at the toe, the possible critical failure surface may pass over the back slope of the berm or pass under the bottom of the berm. This depends on the geometric dimensions (height & base-width/back slope) of the berm. Planar failure surfaces (two and three straight lines) are analysed to check the stability. The study reveals that by varying the berm height as well as the base width, one can arrive at an optimal solution for stability.KeywordsLandfillsStability enhancementSloping groundEarthen berms
- Conference Article
- 10.1117/12.903443
- Nov 20, 2011
- Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
Straight line is an important intermediate symbol, and the straight line extraction is one of the key technologies in image processing and computer vision. Aiming to the characteristics of digital image spatial domain, a straight line model of image spatial domain is established, and a heuristic algorithm based on the model for straight line extraction is presented, Which gets the edge amplitude image by edge detecting, and extracts the straight line which matches the straight line model through employing heuristic search guided by the edge information. The simulation shows that the algorithm is robust for image noise, and it not only can extract the low contrast straight line, but also can eliminate the short fractured straight line effectively.
- Research Article
5
- 10.1109/jstars.2016.2601068
- Dec 1, 2016
- IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Made available in DSpace on 2018-11-26T17:15:38Z (GMT). No. of bitstreams: 0\n Previous issue date: 2016-12-01
- Research Article
5
- 10.1093/jee/48.4.372
- Aug 1, 1955
- Journal of Economic Entomology
As discussed by Gunther & Blinn (1955), there appear to be two principal types of residues on and in treated plant parts. When log residue or percentage of loss or retention of residue is plotted against days after application, a single straight line is obtained with most substrates. With citrus peel as the substrate, however, two intersecting straight lines are usually obtained. The single line represents the summation of degradation3 and persistence behavior, whereas the initial straight line of an intersecting pair is considered to represent degradation, and the line of subsequent behavior to represent the persistence phenomenon. Obviously, the two types of behavior overlap with citrus peel, but it is convenient for purposes of discussion to consider that degradation curves demonstrate graphically the sum of the processes usually classified as weathering, and that falling persistence curves undoubtedly demonstrate enzymatic or other alterations of the parent molecule within the plant part (Gunther & Blinn 1955).
- Book Chapter
1
- 10.1533/9780857099723.15
- Jan 1, 1999
Definitions and basic concepts
- Book Chapter
- 10.1007/978-1-4612-2102-9_6
- Jan 1, 2001
In elementary books (like this one) the development of hyperbolic geometry is often based on a stronger version of ~ Playfair’s Postulate: Postulate H. If P is any point and AB is any straight lines YPZ and WPX such that (1) YPX is not a single straight line, (2) YPZ and WPX are each parallel to AB, and (3) no straight line through P entering LYPX is parallel to AB. (See figure 146). KeywordsAcute AngleEuclidean GeometryHyperbolic GeometrySmall TriangleEqual AngleThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
- Research Article
15
- 10.1364/josa.32.000002
- Jan 1, 1942
- Journal of the Optical Society of America
Projective transformations of a standard coordinate system can be written in the form: u=c3+(e1x+e2y)/(c7x+c8y+1),υ=c3+(e4x+e5y)/(c7x+c8y+1).The shapes and relative sizes of all geometrical figures subjected to such transformations will be invariant if the values of c7, and c8 are invariant, and if the following quantities are also invariant: (e1e5−e2e4)/(e1e2+e4e5),(e22+e52)/(e12+e42).The sizes of such figures are invariant when the numerators and denominators of these expressions are themselves invariant.Colors having equally noticeable differences can be represented by equidistant points in some projective transformation of the standard color-mixture diagram only if in the standard diagram the separations of the points on any line representing a series of equally noticeably different colors are proportional to the square of the distance from some unique point on that line, and if the locus of such unique points for all linear series of colors is a straight line. The locus of colors equally noticeably different from any standard color can be represented adequately in the standard color-mixture diagram by an ellipse. All such ellipses can be transformed by a single projective transformation into equal-sized circles only if the common tangents of every pair of ellipses intersect on a single straight line. This line is the same as the locus of unique points for the series of colors just described. The equation of this straight line is (c7x+c8y+1 = 0), where the constants are those appearing in the denominators of the successful transformation formulas. If the separations of points representing equally noticeably different colors in the standard color-mixture diagram cannot be represented adequately in the manners described, then such colors cannot be represented adequately by equidistant points in any projective transformation of the standard coordinate system.
- Research Article
28
- 10.1016/s0020-1693(00)84212-7
- Jan 1, 1984
- Inorganica Chimica Acta
Stabilities and 1H NMR studies of (diethylenetriamine)Pd(II) and (1,1,4,7,7-pentamethyldien)Pd(II) with nucleosides and related ligands
- Conference Article
- 10.23919/siceiscs51787.2021.9495324
- Mar 2, 2021
For railway signalling and control tasks, Takagi's synchronization control approach [1] can be used to shorten the headway between adjacent trains which operate under the moving block signalling system. However, such a control approach assumes that each train runs on a single straight track line and therefore cannot be used directly to the existing railway configurations which in practice have turning and crossing points. This paper proposes a solution to this practical implementation issue by combining a measurement-based map conversion algorithm to Takagi's synchronization control scheme. The proposed algorithm essentially converts a two-dimensional measurement data set from a GPS into a single straight track line position as required by the train detection system in Takagi's synchronization control approach. Experimental results from the implementation of the proposed approach are presented.
- Research Article
25
- 10.1016/s0301-4622(02)00178-3
- Aug 14, 2002
- Biophysical Chemistry
Extensions of counterion condensation theory. I. Alternative geometries and finite salt concentration
- Conference Article
3
- 10.1117/12.832387
- Oct 30, 2009
- Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
This paper presents a registration method which based on straight lines primitive. Firstly, 2D straight lines are extracted from aerial images using Canny operator and straight line fitting. In the similar way, 3D straight lines are extracted from LiDAR range images which derive from laser scanning point cloud. Secondly, 3D straight lines are projected to aerial images using collinearity equations and Position and Orientation System (POS) data. Then the corresponding lines are determined by straight line error. At last, each image's new exterior orientation elements are calculated by generalized point (straight line) photogrammetry.
- Research Article
2
- 10.1061/jyceaj.0001740
- Jan 1, 1968
- Journal of the Hydraulics Division
Hydrologists use double-mass analysis to verify the consistency of a precipitation or streamflow record. Precipitation of a station is plotted against the combined precipitation of the surrounding stations. The consistency of the record is verified if a single straight line fitted through the points is reasonable. The analysis is done on the computer by fitting a straight line and a fourth-degree polynomial through the points and comparing the two sums of squares of deviations of the points from the fitted curves. If a record is found to be inconsistent, it is adjusted by bringing the deviated points along a desired single straight line. The method should be of value to the hydrologists having access to computers.
- Research Article
31
- 10.1002/pd.4056
- Jan 27, 2013
- Prenatal Diagnosis
To compare three methods of cervical length measurements using ultrasound in the first trimester: single-line, two-line, and tracing. Images appropriate for cervical length measurements were obtained using transvaginal ultrasound between 11 + 0 and 13 + 6 weeks' gestation. The cervix was measured on stored images using three methods: a single straight line, two segments (two-line method), and by tracing the distance along the cervical canal. Results were compared for intraoperator repeatability and interoperator variability. The degree of the cervical curvature was measured. The mean cervical measurement using the single-line measurement was 32.8 (SD 4.4) mm. The mean cervical length was essentially the same using the two-line and tracing measurement: 34.4 (SD 4.7) mm and 34.5 (SD 4.7) mm, respectively. Both intra- and interoperator agreement was high. The degree of curvature of the cervical canal was variable, with a resultant variability in the difference between the single straight line measurement and the other two types of measurement. Using stored images, each of the measurement techniques is highly reproducible. Both the two-line and the tracing methods yield larger measurements than the single-line technique. Therefore, it appears that in select cases the straight line measurement significantly underestimates the actual cervical length.
- Conference Article
1
- 10.1109/icip.1998.723555
- Oct 4, 1998
We present a new lossy technique for document image compression by using straight line extraction and a block context model. Straight line segments are extracted from a binary document image and subtracted from the original image. Their endpoint coordinates and width can then be efficiently coded. The remaining part of the image, which mainly contains text and other symbols, is coded using a high-order block context model (HOBCM) based on vector quantization (VQ). The proposed method is particularly effective for document images containing a large number of straight line segments, such as engineering or architectural drawings. It achieves much higher compression than conventional lossless techniques, such as the JBIG and CCITT G3 and G4 standards, with little loss of visual quality. In the experiments we carried out, a group of engineering drawings digitized at 200 dpi, compression ratios ranging from 30 to 70 were obtained.