Linear array image sleeper positioning and counting method based on multi-region gray projection
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology of grayscale projection and line array image, which is applied in image data processing, image enhancement, image analysis, etc., and can solve problems such as low precision and poor reliability
Active Publication Date: 2018-09-21
成都精工华耀科技有限公司
View PDF5 Cites 6 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0006] The purpose of the present invention is to provide a railway sleeper positioning and counting method for high-precision mileage coun...
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0069] Embodiment 1: use the number of square waves in the joint projection curve to count sleepers.
[0070] Step 1: Take the qth track two-dimensional image I, and select K detection areas {R 1 ...R K}, the value range of K is 1~10, in the specific implementation process, take K=3, such as Figure 6 As shown, respectively for K detection areas {R 1 ...R K} to perform horizontal projection on the pixel values to obtain K horizontal projection curves {S 1 ... S K}, detection area R 2 The corresponding horizontal projection curve S 2 Such as Figure 7 shown. The heights of the K detection areas are equal, and only sleepers are included in the detection area, fasteners and rails are not included;
[0071] Step 2: For K horizontal projection curves {S 1 ... S K} for fusion to obtain the joint projection curve S′;
[0072] Step 3: Use the adaptive threshold method to binarize the joint projection curve S′ to obtain the binarized curve B, such as Figure 10 shown;
...
Embodiment 2
[0081] Embodiment 2: counting sleepers by using the number of crests or troughs in the first derivative of the joint projection curve.
[0082] Utilize the linear array imaging system to acquire Q two-dimensional images of tracks containing sleepers, and sequentially perform the following processing on the Q two-dimensional images of tracks:
[0083] Step 1: Take the qth track two-dimensional image I, and select K detection areas {R 1 ... R K}, K ranges from 1 to 100, in the actual implementation process, K = 3, respectively for K detection areas {R 1 ... R K} to perform horizontal projection on the pixel values to obtain K horizontal projection curves {S 1 ... S K}. The heights of the K detection areas are equal, and only sleepers are included in the detection area, fasteners and rails are not included;
[0084] Step 2: For K projection curves {S 1 ... S K} for fusion to obtain the joint projection curve S′;
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
PUM
Login to view more
Abstract
The invention discloses a linear array image sleeper positioning and counting method based on multi-region gray projection and belongs to the field of rail detection. The method comprises the steps that a linear array imaging system is utilized to perform linear array scanning imaging on a rail pavement along the advancing direction of a train or a detection platform, and a linear array image containing sleepers is acquired; multiple detection regions are set in a sleeper region of the linear array image, image gray value horizontal projection is performed in each detection region to obtain multiple horizontal projection curves; the horizontal projection curves are fused after being subjected to filtering and smoothing to obtain united projection curves; and then sleeper counting is performed according to the quantity of square waves in the united projection curves or the quantity of crests or troughs in first-order derivatives of the united projection curves. According to the method,after sleeper positioning and counting, high-precision mileage counting can be realized, precise position information is provided for a rail inspection system, and convenience is brought to accurate positioning of a rail inspection result and quick finding in later maintenance.
Description
technical field [0001] The invention relates to the technical field of rail detection, in particular to a method for locating and counting sleepers of linear array images based on multi-region grayscale projection. Background technique [0002] Rail transportation includes ordinary railways, high-speed railways, subways, etc., and plays an important role in the development of the national economy and people's daily life. In order to ensure the safety of rail transit operation, the rail transit operation department needs to conduct regular inspections on rail safety. Specific inspection contents include: rail geometric parameter detection, abnormal detection of rail fasteners loose, missing, cracks, etc., rail wear detection, pantograph-catenary line detection, foreign object detection on the road surface, etc. [0003] At present, the detection of rail geometric parameters mainly uses inertial navigation system and laser image measurement system for automatic detection of t...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more