KR20240064383A - A method of detecting a rail tile picture by a line scan and an apparatus of detecting a rail tile picture by a line scan - Google Patents

Abstract

A railway image sleeper detection method according to embodiments includes acquiring a railway image by line scanning; Processing railway images; Analyzing railway video; and detecting sleepers in the railway image; may include.

Description

Line scan sensor railway image sleeper detection method and device {A METHOD OF DETECTING A RAIL TILE PICTURE BY A LINE SCAN AND AN APPARATUS OF DETECTING A RAIL TILE PICTURE BY A LINE SCAN}

Embodiments relate to a line scan sensor railroad image sleeper detection method and device.

Railways move along rails. If there is a problem with the rails, railway operations may be disrupted and it may lead to a railway accident.

It is important to inspect the rails and repair any abnormalities. However, there are many parts that make up the rail, the length of the rail is long, and there are limitations in the method of inspecting the moving rail.

In the past, there was a problem that rails had to be installed manually and people had to inspect and manage the rails themselves.

Therefore, a method and device for automatically inspecting a large number of rails and efficiently detecting abnormalities regarding the rails is required.

Embodiments provide a line scan sensor railroad image sleeper detection method and device.

Embodiments provide a method and device for quickly and accurately automatically detecting sleepers.

However, it is not limited to the above-described technical issues, and the scope of rights of the embodiments may be expanded to other technical issues that can be inferred by a person skilled in the art based on the entire contents described.

A railway image sleeper detection method according to embodiments includes acquiring a railway image by line scanning; Processing railway images; Analyzing railway video; and detecting sleepers in the railway image; may include.

The line scan sensor railroad image sleeper detection method and device according to embodiments can detect rails from railroad images at high speed in real time.

The line scan sensor railroad image sleeper detection method and device according to embodiments can accurately and quickly detect rails from railroad images using an AI algorithm.

The line scan sensor railroad image sleeper detection method and device according to embodiments can provide useful data for railroad-related work by analyzing railroad images.

The drawings are included to further understand the embodiments, and the drawings represent the embodiments along with descriptions related to the embodiments. For a better understanding of the various embodiments described below, reference should be made to the following description of the embodiments in conjunction with the following drawings, in which like reference numerals refer to corresponding parts throughout the drawings.
Figure 1 shows a method for detecting railway image rails according to embodiments.
Figure 2 shows rails of a railroad image according to embodiments.
Figure 3 shows a process for a railroad image including rails according to embodiments.
Figure 4 shows a process for a railroad image including rails according to embodiments.
Figure 5 shows an example of analysis after processing of a railroad image including rails according to embodiments.
Figure 6 shows analysis of a railroad image including rails according to embodiments.
Figure 7 shows rail detection according to embodiments.
Figure 8 shows a method for detecting railway image rails according to embodiments.
Figure 9 shows a railway image rail detection device according to embodiments.
Figure 10 shows a line scan railroad image sleeper detection method according to embodiments.
Figure 11 shows a line scan railroad image according to embodiments.
Figure 12 shows rail direction edge detection according to embodiments.
Figure 13 shows image binarization according to embodiments.
Figure 14 shows a histogram for the rail vertical direction component according to embodiments.
Figure 15 shows clustering according to embodiments.
Figure 16 shows rail edge removal of a railroad image according to embodiments.
Figure 17 shows a histogram of the rail direction according to embodiments.
Figure 18 shows clustering according to embodiments.
Figure 19 shows sleeper detection according to embodiments.

Preferred embodiments of the embodiments will be described in detail, examples of which are shown in the attached drawings. The detailed description below with reference to the accompanying drawings is intended to explain preferred embodiments of the embodiments rather than showing only embodiments that can be implemented according to the embodiments. The following detailed description includes details to provide a thorough understanding of the embodiments. However, it will be apparent to those skilled in the art that embodiments may be practiced without these details.

Most of the terms used in the embodiments are selected from common ones widely used in the field, but some terms are arbitrarily selected by the applicant and their meaning is detailed in the following description as necessary. Accordingly, the embodiments should be understood based on the intended meaning of the terms rather than their mere names or meanings.

Figure 1 shows a method for detecting railway image rails according to embodiments.

The railway image rail detection method according to embodiments may include a flowchart as shown in Figure 1: 1) acquiring a railway image, 2) detecting a rail direction edge, 3) binarizing the railway image, 4) acquiring a histogram in the rail vertical direction from the binarized railway image, 5) clustering the railway image, and/or 6) detecting the rail. Each step is described below with reference to each drawing.

Figure 2 shows rails of a railroad image according to embodiments.

Figure 2 shows an example of the configuration of the railway image described in Figure 1. The method/device according to embodiments can acquire a railroad image (picture) of a railroad rail taken by a camera. The image captured by the camera may include railroad rails, as shown in Figure 2. Railway images can be acquired by line scan method.

Figure 3 shows a process for a railroad image including rails according to embodiments.

Figure 3 shows the railway image processing described in Figure 1. For example, the method/device according to embodiments may detect an edge in the rail direction from a railroad image. A vertical edge detection filter can be applied to railway images such as Figure 2. Additionally, a noise removal filter can be applied. Since the rail in the image is located in the vertical direction, an edge image in the rail direction can be obtained as shown in Figure 3 through a filter that detects the vertical direction and/or a noise removal filter.

Figure 4 shows a process for a railroad image including rails according to embodiments.

Figure 4 shows the railway image processing described in Figure 1. For example, as shown in Figure 3, a rail direction edge image to which a vertical edge detection filter and/or noise removal filter is applied may be binarized. The method/device according to embodiments can acquire a binarized image of a railroad rail as shown in FIG. 4.

Figure 5 shows an example of analysis after processing of a railroad image including rails according to embodiments.

Figure 5 shows an example of obtaining a histogram in the rail vertical direction from the image described in Figure 1.

As shown in FIG. 4, after acquiring the binarized image, the method/apparatus according to embodiments may generate a histogram for the image to analyze the rail vertical direction component. The x-axis of the information graph that makes up the histogram represents the horizontal pixel position of the image, and the y-axis represents information related to the number of pixels in the binarized image. For example, the x-axis may represent the pixel position on the horizontal axis of the image in the vertical direction of the rail, and the y-axis may represent the number of pixels On/””. It can be seen that more than 600 pixels are distributed between 300 and 400 in the horizontal position. Based on the number and location of pixels, the method/device according to embodiments can detect the location and direction of the rail in the image.

Figure 6 shows analysis of a railroad image including rails according to embodiments.

Figure 6 shows an example of clustering pixels of an image based on analysis of the number and location of pixels in the image described in Figure 1. For example, the method/device according to embodiments may cluster data in which 500 to 600 pixels are distributed at 300 to 400 positions. In other words, the cluster with the largest number of pixels can be estimated as the location of the rail. For example, when a first cluster, a second cluster, and a third cluster are created, and the second cluster includes a relatively large number of pixels, it can be estimated that the second cluster is the location of the rail.

Figure 7 shows rail detection according to embodiments.

Figure 7 shows an example of detecting the rail 700 described in Figure 1. The configuration and direction of the rail may vary as shown in Figure 7. The spacing and number of sleepers supporting the rails may vary from location to location, and the number and direction of rails may vary from region to region. Even if various rail configurations are given, the method/device according to embodiments can effectively detect a vertical rail as shown in FIG. 7 based on the method shown in FIGS. 1 to 6.

Figure 8 shows a method for detecting railway image rails according to embodiments.

S800, a method of detecting a railroad image rail according to embodiments may include acquiring a railroad image by line scanning. For the acquisition operation, refer to the description of Figures 1 and 2.

S801, the railway image rail detection method according to embodiments may further include the step of processing the railway image. For the railway image processing method, refer to the description of Figures 1 to 4.

S802, the railway image rail detection method according to embodiments may further include the step of analyzing the railway image. For the railroad image analysis method, refer to the descriptions of Figures 5 and 6. The method of analyzing railway images can detect rails from railway images using AI algorithms and learning models.

S8013, the method for detecting rails in a railroad image according to embodiments may further include detecting a rail in the railroad image. For the rail detection method, refer to the description of Figure 7.

Figure 9 shows a railway image rail detection device according to embodiments.

Figure 9 shows a configuration diagram of a railway image rail detection device that performs the method of Figures 1 to 8. Each component in Figure 9 may correspond to hardware, processor, software, and/or a combination thereof.

Devices according to embodiments may include an interface unit, a processor, and/or memory.

The interface unit can transmit and receive signals for railway video rail detection. Additionally, the interface unit may be connected to a camera and/or sensor. The device may further include cameras and/or sensors. Railway images acquired by line scan may be transmitted to a processor and/or memory through an interface unit.

The memory may store information related to the operations of FIGS. 1 to 8 and provide necessary data to the interface unit and/or processor.

The processor may be connected to an interface unit and/or memory to control and perform the operations of Figures 1 to 8.

Referring to Figure 8, the method according to embodiments includes acquiring a railroad image by line scanning; Processing railway images; Analyzing railway video; and detecting rails in the railway image; may include.

Referring to Figure 1, in relation to rail edge detection and binarization, the step of processing a railroad image may include detecting an edge in the rail direction from the railroad image and binarizing the railroad image. there is.

Referring to Figures 2 and 3, in relation to vertical edge detection and noise processing, the edge detection step involves applying a filter that detects vertical edges to the railroad image and Noise can be removed, and an edge image in the rail direction can be obtained from the railroad image.

Referring to Figure 4, in relation to binarization, the step of binarizing the railroad image may involve binarizing the rail direction edge of the railroad image.

Referring to Figure 5, in relation to histogram (statistics) analysis, the step of analyzing a railroad image may obtain the number of pixels and pixel positions included in the binarized image of the railroad image.

Referring to Figure 6, in relation to clustering, the step of analyzing the railroad image is to cluster the railroad image based on the number of pixels and the pixel location, and detect the clustered area as the location of the rail based on the number of pixels. You can.

The railway image rail detection method may be performed by the device. Referring to Figure 9, the device includes memory; and a processor coupled to the memory; It includes, wherein the processor acquires a railroad image by line scanning; Processing railway images; Analyzing railway video; and detecting rails in the railway image; can be performed. The processor may perform the steps of detecting edges in the rail direction from the railroad image and binarizing the railroad image. The processor may apply a filter that detects a vertical edge to the railroad image, remove noise from the railroad image, and obtain an edge image in the rail direction from the railroad image. The processor can binarize the rail direction edges of the railroad image. The processor may obtain the number of pixels and pixel positions included in the binarized image of the railroad image. The processor may cluster the railroad image based on the number of pixels and the pixel location, and detect the clustered area as the location of the rail based on the number of pixels.

Because of this, the method/device according to embodiments can provide the effect of detecting rails from railroad images in real time and at high speed.

Figure 10 shows a line scan railroad image sleeper detection method according to embodiments.

The railway image rail detection device according to FIG. 9 can detect sleepers from railway images as well as detecting rails. Figure 10 shows a flow chart of a rail detection method according to embodiments.

A line scan sensor railway image rail and/or sleeper detection method/device according to embodiments may be referred to as a method/device according to embodiments.

The railway image sleeper detection method according to embodiments includes 1) acquiring a railway image, 2) detecting rail direction edges, 3) binarizing the railway image, and 4) histogram for the rail vertical direction from the railway image. , 5) clustering the railway image, 6) removing rail edges of the railway image, 7) acquiring a histogram of the rail direction from the railway image, 8) clustering the railway image, and /or 9) it may include the step of detecting sleepers from railway images. Below, each operation will be described with reference to each drawing.

Figure 11 shows a line scan railroad image according to embodiments.

Like Figures 1 and 2, the method/device according to embodiments can acquire railroad images through line scanning, as shown in Figure 11. The line scan railway image may include rails and at least one sleeper. For example, a railroad image including first and second sleepers supporting the rail may be obtained.

Figure 12 shows rail direction edge detection according to embodiments.

Figure 12 explains the edge detection method described in Figure 10. The method/device according to embodiments may acquire a railroad image and apply image processing to the obtained railroad image. For example, a vertical edge detection filter and/or noise removal filter can be applied to a railroad image. By applying a filter, the method/device according to embodiments can obtain a rail direction edge image as shown in FIG. 12.

Figure 13 shows image binarization according to embodiments.

Figure 13 shows an example of applying image binarization, the image processing technique described in Figure 10. The method/device according to embodiments can obtain a binarized image by applying binarization for rail direction edges to a railroad image including sleepers and rails.

Figure 14 shows a histogram for the rail vertical direction component according to embodiments.

The method/apparatus according to embodiments can generate a histogram to represent the rail vertical direction component from a binarized railroad image as shown in FIG. 13. The method/apparatus according to embodiments may generate a histogram for the image to analyze the rail vertical direction component. The x-axis of the information graph that makes up the histogram represents the horizontal pixel position of the image, and the y-axis represents information related to the number of pixels in the binarized image. For example, the x-axis may represent the pixel position on the horizontal axis (vertical rail direction) of the image in the rail vertical direction, and the y-axis may represent the number of pixels On/””. It can be seen that more than 600 pixels are distributed between 300 and 400 in the horizontal position. Based on the number and location of pixels, the method/device according to embodiments can detect the location and direction of the rail in the image.

Figure 15 shows clustering according to embodiments.

Figure 15 shows an example of clustering pixels of an image based on analysis of the number and location of pixels in the image described in Figure 14. For example, the method/device according to embodiments may cluster data in which 500 to 600 pixels are distributed at 300 to 400 positions. In other words, the cluster with the largest number of pixels can be estimated as the location of the rail. For example, when a first cluster, a second cluster, and a third cluster are created, and the second cluster includes a relatively large number of pixels, it can be estimated that the second cluster is the location of the rail.

Figure 16 shows rail edge removal of a railroad image according to embodiments.

The method/apparatus according to embodiments can remove rail edges included in a binarized railroad image as shown in FIG. 14. Rail edge refers to the edge component representing the rail included in the railroad image. The method/apparatus according to embodiments can remove rail components from a railroad image through an edge removal filter. As a result, a railroad image containing sleeper elements can be obtained.

Figure 17 shows a histogram of the rail direction according to embodiments.

The method/apparatus according to embodiments can analyze a railroad image including sleeper components using a histogram to analyze components in the rail direction. For example, in a histogram as shown in Figure 17, the X-axis represents the vertical pixel position of the image (rail direction), and the Y-axis represents the number of pixels in the binarized image. Many pixels may be distributed around the 100 vertical position, many pixels may be distributed around the 400-500 vertical position, and many pixels may be distributed around the 800 vertical position. That is, since many pixels are distributed around the first to third sleepers based on the vertical position in the rail direction, the position of the sleepers can be estimated through histogram analysis.

Figure 18 shows clustering according to embodiments.

The method/device according to embodiments can analyze pixels as shown in FIG. 17 and then apply clustering according to location and number of pixels to the railroad image as shown in FIG. 18. By clustering locations where many pixels are distributed, first clustering, second clustering, and third clustering can be obtained. Each clustering may correspond to a region of sleeper locations in the railway image.

Figure 19 shows sleeper detection according to embodiments.

The method/device according to the embodiments can efficiently detect the area where the sleeper is located from the railroad image including the sleeper and rail as shown in FIG. 19 according to the above-described method.

Referring to Figure 20, the sleeper detection method according to embodiments includes acquiring a railroad image by line scanning; Processing railway images; Analyzing railway video; and detecting sleepers in the railway image; may include.

Referring to Figure 12, in relation to rail edge detection and binarization, the step of processing a railroad image may include detecting an edge in the rail direction from the railroad image and binarizing the railroad image. there is.

Referring to Figure 12, in relation to vertical edge detection and noise processing, the edge detection step involves applying a filter that detects vertical edges to the railroad image and removing noise from the railroad image. After removal, an edge image in the rail direction can be obtained from the railroad image.

Referring to FIG. 13, in relation to binarization, the step of binarizing the railroad image may binarize the rail direction edge of the railroad image.

Referring to Figure 14, in relation to the histogram, the step of analyzing the railroad image may be to obtain the number of pixels and pixel positions included in the binarized image of the railroad image.

Referring to Figure 15, in relation to clustering, the step of analyzing the railroad image is to cluster the railroad image based on the number of pixels and the pixel location, and detect the clustered area as the location of the rail based on the number of pixels. there is.

Referring to FIG. 16, in relation to rail edge removal, the step of analyzing a railroad image may include removing a rail edge included in the railroad image.

Referring to FIG. 17, in relation to the histogram of vertical pixel positions in the rail direction, the step of analyzing the railroad image can obtain the vertical position in the rail direction and the number of pixels from the railroad image from which the rail edge has been removed.

Referring to Figure 18, in relation to sleeper clustering, the step of detecting sleepers in a railroad image is to cluster the railroad image based on the rail direction and the number of pixels, and based on the number of pixels, convert the clustered area to the location of the sleeper. It can be detected.

The railway image sleeper detection method can be performed by a device as shown in FIG. 9. Specifically, devices according to embodiments include memory; and a processor coupled to the memory; It includes, wherein the processor acquires a railroad image by line scanning; Processing railway images; Analyzing railway video; and detecting sleepers in the railway image; can be performed.

Additionally, the processor may perform the steps of detecting edges in the rail direction from the railroad image and binarizing the railroad image. Additionally, the processor may apply a filter that detects a vertical edge to the railroad image, remove noise from the railroad image, and obtain an edge image in the rail direction from the road image. Additionally, the processor can binarize the rail direction edges of the railroad image. The processor may obtain the number of pixels and pixel positions included in the binarized image of the railroad image. The processor may cluster the railroad image based on the number of pixels and the pixel location, and detect the clustered area as the location of the rail based on the number of pixels. The processor may perform a step of removing rail edges included in the railroad image. The processor can obtain the vertical position in the rail direction and the number of pixels from the railroad image from which the rail edge has been removed. The processor may cluster the railroad image based on the rail direction and number of pixels, and detect the clustered area as the location of the sleeper based on the number of pixels.

Due to this, the method/device according to the embodiments has the effect of efficiently detecting rails and/or sleepers in real time based on the characteristics of the railroad image and the process method according to the embodiments.

The embodiments have been described in terms of a method and/or an apparatus, and the description of the method and the description of the apparatus may be applied to complement each other.

For convenience of explanation, each drawing has been described separately, but it is also possible to design a new embodiment by merging the embodiments described in each drawing. In addition, according to the needs of those skilled in the art, designing a computer-readable recording medium on which programs for executing the previously described embodiments are recorded also falls within the scope of the rights of the embodiments. The apparatus and method according to the embodiments are not limited to the configuration and method of the embodiments described above, but all or part of the embodiments can be selectively combined so that various modifications can be made. It may be composed. Although preferred embodiments of the embodiments have been shown and described, the embodiments are not limited to the specific embodiments described above, and are within the scope of common knowledge in the technical field to which the invention pertains without departing from the gist of the embodiments claimed in the claims. Of course, various modifications are possible by those who have, and these modifications should not be understood individually from the technical ideas or perspectives of the embodiments.

The various components of the devices of the embodiments may be implemented by hardware, software, firmware, or a combination thereof. Various components of the embodiments may be implemented with one chip, for example, one hardware circuit. Depending on the embodiments, the components according to the embodiments may be implemented with separate chips. Depending on the embodiments, at least one or more of the components of the device according to the embodiments may be composed of one or more processors capable of executing one or more programs, and the one or more programs may be executed. It may perform one or more of the operations/methods according to the examples, or may include instructions for performing them. Executable instructions for performing the methods/operations of the device according to embodiments may be stored in a non-transitory CRM or other computer program products configured for execution by one or more processors, or may be stored in one or more processors. It may be stored in temporary CRM or other computer program products configured for execution by processors. Additionally, memory according to embodiments may be used as a concept that includes not only volatile memory (eg, RAM, etc.) but also non-volatile memory, flash memory, and PROM. Additionally, it may also be implemented in the form of a carrier wave, such as transmission over the Internet. Additionally, the processor-readable recording medium is distributed in a computer system connected to a network, so that the processor-readable code can be stored and executed in a distributed manner.

In this document, “/” and “,” are interpreted as “and/or.” For example, “A/B” is interpreted as “A and/or B”, and “A, B” is interpreted as “A and/or B”. Additionally, “A/B/C” means “at least one of A, B and/or C.” Additionally, “A, B, C” also means “at least one of A, B and/or C.” Additionally, in this document, “or” is interpreted as “and/or.” For example, “A or B” may mean 1) only “A”, 2) only “B”, or 3) “A and B”. In other words, “or” in this document may mean “additionally or alternatively.”

Terms such as first, second, etc. may be used to describe various components of the embodiments. However, the interpretation of various components according to the embodiments should not be limited by the above terms. These terms are merely used to distinguish one component from another. It's just a thing. For example, a first user input signal may be referred to as a second user input signal. Similarly, the second user input signal may be referred to as the first user input signal. Use of these terms should be interpreted without departing from the scope of the various embodiments. The first user input signal and the second user input signal are both user input signals, but do not mean the same user input signals unless clearly indicated in the context.

The terminology used to describe the embodiments is for the purpose of describing specific embodiments and is not intended to limit the embodiments. As used in the description of the embodiments and the claims, the singular is intended to include the plural unless the context clearly dictates otherwise. The expressions and/or are used in a sense that includes all possible combinations between the terms. The expression includes describes the presence of features, numbers, steps, elements, and/or components and does not imply the absence of additional features, numbers, steps, elements, and/or components. . Conditional expressions such as when, when, etc. used to describe the embodiments are not limited to optional cases. It is intended that when a specific condition is satisfied, the relevant action is performed or the relevant definition is interpreted in response to the specific condition.

Additionally, operations according to embodiments described in this document may be performed by a transmitting and receiving device including a memory and/or a processor depending on the embodiments. The memory may store programs for processing/controlling operations according to embodiments, and the processor may control various operations described in this document. The processor may be referred to as a controller, etc. In embodiments, operations may be performed by firmware, software, and/or a combination thereof, and the firmware, software, and/or combination thereof may be stored in a processor or stored in memory.

Meanwhile, operations according to the above-described embodiments may be performed by a transmitting device and/or a receiving device according to the embodiments. The transmitting and receiving device may include a transmitting and receiving unit that transmits and receives media data, a memory that stores instructions (program code, algorithm, flowchart and/or data) for the process according to embodiments, and a processor that controls the operations of the transmitting and receiving device. You can.

A processor may be referred to as a controller, etc., and may correspond to, for example, hardware, software, and/or a combination thereof. Operations according to the above-described embodiments may be performed by a processor. Additionally, the processor may be implemented as an encoder/decoder, etc. for the operations of the above-described embodiments.

Claims (18)

Acquiring railway images by line scanning;
Processing the railway image;
Analyzing the railway video; and
Detecting sleepers in the railway image; Including,
Railway video sleeper detection method. According to paragraph 1,
The step of processing the railway image is,
Detecting edges in the rail direction from the railway image,
Including the step of binarizing the railway image,
Railway video sleeper detection method. According to paragraph 2,
The edge detection step is,
Apply a filter that detects vertical edges to the railway image,
Remove noise from the railway image,
An edge image in the rail direction is obtained from the railway image,
Railway video sleeper detection method. According to paragraph 2,
The step of binarizing the railway image is,
Binarizing the rail direction edge of the railway image,
Railway video sleeper detection method. According to paragraph 1,
The step of analyzing the railway video is,
Obtaining the number of pixels and pixel positions included in the binarized image of the railway image,
Railway video sleeper detection method. According to clause 5,
The step of analyzing the railway video is,
Clustering the railroad image based on the number of pixels and the pixel location,
Based on the number of pixels, detecting the clustered area as the position of the rail,
Railway video sleeper detection method. According to clause 6,
The step of analyzing the railway video is
Including the step of removing the rail edge included in the railway image,
Railway video sleeper detection method. In clause 7,
The step of analyzing the railway video is
Obtaining the vertical position and number of pixels in the rail direction from the railway image from which the rail edge has been removed,
Railway video sleeper detection method. According to clause 8,
The step of detecting sleepers in the railway image is
Clustering the railway image based on the rail direction and the number of pixels,
Based on the number of pixels, detecting the clustered area as the location of the sleeper,
Railway video sleeper detection method. Memory; and
a processor connected to the memory; Including,
The processor,
Acquiring railway images by line scanning;
Processing the railway image;
Analyzing the railway video; and
Detecting sleepers in the railway image; To perform,
Railway video sleeper detection device. According to clause 10,
The processor,
Detecting edges in the rail direction from the railway image,
Performing the step of binarizing the railway image,
Railway video sleeper detection device. According to clause 11,
The processor,
Apply a filter that detects vertical edges to the railway image,
Remove noise from the railway image,
An edge image in the rail direction is obtained from the railway image,
Railway video sleeper detection device. According to clause 11,
The processor,
Binarizing the rail direction edge of the railway image,
Railway video sleeper detection device. According to clause 10,
The processor,
Obtaining the number of pixels and pixel positions included in the binarized image of the railway image,
Railway video sleeper detection device. According to clause 14,
The processor,
Clustering the railroad image based on the number of pixels and the pixel location,
Based on the number of pixels, detecting the clustered area as the position of the rail,
Railway video sleeper detection device. According to clause 15,
The processor,
Performing the step of removing the rail edge included in the railway image,
Railway video sleeper detection device. According to clause 16,
The processor,
Obtaining the vertical position and number of pixels in the rail direction from the railway image from which the rail edge has been removed,
Railway video sleeper detection device. According to clause 17,
The processor,
Clustering the railway image based on the rail direction and the number of pixels,
Based on the number of pixels, detecting the clustered area as the location of the sleeper,
Railway video rail detection device.