Quantification system and method for ballast saturation of a ballasted track

Abstract

The application discloses a kind of ballast saturation quantification system and method of ballast track, it is related to ballast saturation detection technical field, utilize image acquisition module to collect the gray scale diagram and depth map of ballast bed, the gray scale diagram is preprocessed by image preprocessing module, the real-time position of sleeper in ballast bed is obtained by sleeper detection module through extracting sleeper feature in gray scale diagram;Ballast measuring module utilizes depth map and sleeper position, determines steel rail area, sleeper area and ballast area, and further calculates to obtain the actual value of rail bottom height and sleeper height, the actual value of ballast height on both sides of ballast bed and the actual value of ballast height in the center of ballast bed;Ballast saturation quantification module, rail bottom height is used as the reference value of ballast height on both sides of ballast bed, sleeper height is used as the reference value of ballast height in the center of ballast bed, using two groups of reference values and actual values, the saturation of ballast is quantified.The application can simply and efficiently detect the saturation of ballast bed ballast, and form quantification result.

Description

Technical Field

[0001] This invention relates to the field of ballast saturation detection technology, and in particular to a quantitative system and method for ballast saturation of ballasted track ballast. Background Technology

[0002] Ballasted tracks are often used in the construction of conventional heavy-duty railway lines due to their advantages such as low construction costs, small noise propagation range, and short construction period.

[0003] When a train is running, the wheels act on the rails, generating not only vertical and lateral forces, but also longitudinal forces due to wheel rolling, longitudinal sliding, and train braking. This causes the rails to bear longitudinal forces under dynamic loads. When the longitudinal force exceeds the rail foundation resistance (including fastener resistance, joint resistance, and ballast resistance), it causes longitudinal displacement of the rails. In summer, high temperatures can easily squeeze the rail gaps into narrow openings, leading to rail stretching and track slippage. In winter, braking can widen the rail gaps, causing damage to the rails, rail plates, and bolts, or even bolt breakage. It can also stretch the sleepers, causing deviations in gauge and track alignment, resulting in damage to fasteners and sleepers. At turnouts, it can cause the switch rail to not fit tightly against the stock rail, leading to switch rail rebound or poor maneuverability, and even affecting the interlocking device. To prevent rail creep from damaging the track bed components and ensure train operation safety, the fundamental measure is to increase the longitudinal resistance of the track. In addition to replacing malfunctioning anti-creep devices, it is even more important to keep the ballast in the sleeper box full. This requires regular inspection of the ballast in the sleeper box. Currently, most of these inspections are done manually, relying on workers' experience to judge the fullness of the ballast. This results in low inspection accuracy and the inability to generate quantitative results. Summary of the Invention

[0004] In view of this, this application provides a quantitative system and method for saturation of ballast in ballasted tracks to address the shortcomings of the prior art.

[0005] The first aspect of this application discloses a system for quantifying the saturation of ballast in ballasted tracks, comprising:

[0006] In one possible implementation of the first aspect, preprocessing the acquired grayscale image includes: standardizing and scaling the grayscale image.

[0007] In one possible implementation of the first aspect, determining the rail region, sleeper region, and ballast region based on the acquired depth map and the real-time position of the sleepers includes:

[0008] Based on the real-time position of the sleeper, the sleeper coordinates are obtained and a corresponding sleeper area is generated, which is denoted as the first sleeper area.

[0009] The acquired depth map is used as the original depth map. Based on the prior data of the rail position, the original depth map is segmented by height threshold and morphologically filtered to obtain a segmented binary map containing the rail region.

[0010] Based on the segmented binary map and the original depth map, the relative height value of the rail is obtained;

[0011] Based on the relative height value and the actual height value of the rail, the segmentation threshold of the track bed in the original depth map is obtained and segmented to obtain the track bed area;

[0012] The depth map corresponding to the track bed area is subjected to mean filtering and morphological dilation in sequence, and then the difference is subtracted from the original depth map to obtain the difference map;

[0013] The difference map is segmented by thresholding to obtain the initial area of ​​the sleeper;

[0014] Morphological filtering is performed on the depth map corresponding to the initial sleeper region, and an AND operation is performed with the first sleeper region to obtain the sleeper region.

[0015] The ballast area is obtained by subtracting the difference between the track bed area and the sleeper area.

[0016] In one possible implementation of the first aspect, calculating the rail base height includes:

[0017]

[0018] The height of the rail base is [height]. This is the average rail surface height of the left and right rails. This refers to the standard height of the rail.

[0019] In one possible implementation of the first aspect, calculating the sleeper height includes:

[0020]

[0021] The sleeper height is [the value of the sleeper]. This is the average height of the center of the sleeper.

[0022] In one possible implementation of the first aspect, calculating the actual height of the ballast on both sides of the track bed includes:

[0023]

[0024] The actual height of the ballast on both sides of the track bed. This is the average height of the ballast on both sides of the track bed.

[0025] In one possible implementation of the first aspect, calculating the actual height of the central ballast of the track bed includes:

[0026]

[0027] This refers to the actual height of the central ballast in the track bed. This is the average height of the ballast in the center of the track bed.

[0028] In one possible implementation of the first aspect, quantifying the ballast saturation within the track bed includes:

[0029] Calculate the actual height of the ballast on both sides of the track bed. Reference values ​​of ballast height on both sides of the track bed The ratio, and the actual value of the central ballast height of the track bed. Height of the central ballast of the track bed The ratio of the two values ​​is used to quantify the saturation of ballast in the track bed.

[0030] In one possible implementation of the first aspect, the preset location is where an electronic tag is pre-installed on the line.

[0031] A second aspect of this application provides a method for quantifying the saturation of ballast in ballasted tracks, comprising:

[0032] The grayscale and depth images of the track bed are collected at preset locations along the line using image acquisition equipment installed on the inspection vehicle.

[0033] Preprocess the acquired grayscale images;

[0034] The pre-processed grayscale image is used to detect targets using a preset target detection model to obtain the real-time position of the sleepers;

[0035] Based on the collected depth map and the real-time position of the sleepers, the rail area, sleeper area, and ballast area are determined; based on the rails and the depth map, the rail base height is calculated; based on the sleeper area and the depth map, the sleeper height is calculated; based on the rail area, the ballast area, and the depth map, the actual values ​​of the ballast height on both sides of the track bed are calculated; based on the sleeper area, the ballast area, and the depth map, the actual value of the ballast height in the center of the track bed is calculated.

[0036] The rail base height is used as a reference value for the ballast height on both sides of the track bed, and the sleeper height is used as a reference value for the ballast height in the center of the track bed. Based on the reference values ​​of the ballast height on both sides of the track bed and the actual values ​​of the ballast height on both sides of the track bed, and the reference value of the ballast height in the center of the track bed and the actual values ​​of the ballast height in the center of the track bed, the ballast saturation in the track bed is quantified.

[0037] Its beneficial effects are as follows: This invention discloses a quantitative system and method for saturation of ballasted track ballast. It utilizes an image acquisition device mounted on an inspection vehicle to acquire grayscale and depth images of the track bed at preset locations along the track. An image preprocessing module preprocesses the acquired grayscale images, and then a sleeper detection module extracts sleeper features from the preprocessed grayscale images to obtain the real-time position of the sleepers in the track bed. The ballast measurement module uses the depth image and sleeper position to determine the rail area, The invention analyzes the sleeper and ballast areas, and further calculates the actual values ​​of the rail base height, sleeper height, ballast height on both sides of the track bed, and the actual value of the ballast height in the center of the track bed. Finally, a ballast saturation quantification module uses the rail base height as a reference value for the ballast height on both sides of the track bed and the sleeper height as a reference value for the ballast height in the center of the track bed. Using the reference and actual values ​​of the ballast height on both sides of the track bed and the reference and actual values ​​of the ballast height in the center of the track bed, the ballast saturation within the track bed is quantified. This invention can simply and efficiently detect track bed ballast saturation and generate quantified results. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0039] Figure 1 This is a schematic diagram of a quantification system for ballast saturation of ballasted track provided in an embodiment of this application;

[0040] Figure 2 This is a flowchart of the image acquisition module provided in an embodiment of this application;

[0041] Figure 3 This is a flowchart of the image preprocessing module provided in the embodiments of this application;

[0042] Figure 4 This is a flowchart of the ballast measurement module provided in an embodiment of this application;

[0043] Figure 5 This is a schematic diagram of a method for quantifying the saturation of ballast in a ballast track according to an embodiment of this application. Detailed Implementation

[0044] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0045] In this application, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0046] Example 1

[0047] In existing technologies, the fundamental measure to prevent rail creep from damaging the track bed components and to ensure train operation safety is to increase the longitudinal resistance of the track. In addition to replacing the failed anti-creep devices, it is even more important to keep the ballast in the sleeper box full. This requires regular inspection of the ballast in the sleeper box. Currently, most of these inspections are done manually, relying on workers' experience to judge the fullness of the ballast. This results in low inspection accuracy and the inability to generate quantitative results.

[0048] Therefore, this application provides a quantification system for the saturation of ballast in ballasted tracks, such as... Figure 1 As shown, it includes:

[0049] Image acquisition module: Using image acquisition equipment installed on the inspection vehicle, grayscale and depth images of the track bed are acquired at preset locations along the line.

[0050] Image preprocessing module: preprocesses the acquired grayscale images;

[0051] Sleeper detection module: Uses a preset target detection model to perform target detection on the preprocessed grayscale image to obtain the real-time position of the sleeper;

[0052] Ballast Measurement Module: Based on the acquired depth map and the real-time position of the sleepers, it determines the rail area, sleeper area, and ballast area; based on the rails and the depth map, it calculates the rail base height; based on the sleeper area and the depth map, it calculates the sleeper height; based on the rail area, the ballast area, and the depth map, it calculates the actual ballast height on both sides of the track bed; based on the sleeper area, the ballast area, and the depth map, it calculates the actual ballast height in the center of the track bed.

[0053] Ballast saturation quantification module: The rail base height is used as a reference value for the ballast height on both sides of the ballast bed, and the sleeper height is used as a reference value for the ballast height in the center of the ballast bed; based on the reference values ​​of the ballast height on both sides of the ballast bed and the actual values ​​of the ballast height on both sides of the ballast bed, and the reference value of the ballast height in the center of the ballast bed and the actual values ​​of the ballast height in the center of the ballast bed, the ballast saturation in the ballast bed is quantified.

[0054] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating the workflow of the image acquisition module provided in this application embodiment. The image acquisition module consists of an image acquisition device installed on an inspection vehicle. The image acquisition device includes a light source, an industrial high-speed camera, and a supplementary lighting device. During operation, the light source and supplementary lighting device illuminate the track bed, and the high-speed industrial camera captures grayscale and depth images (e.g., 3200*512 pixels) of the track bed at preset locations on the track. The preset locations are set by installing electronic tags at stations along the track. When the inspection vehicle passes the electronic tag, it controls the high-speed camera to capture the grayscale and depth images of the track bed.

[0055] Please refer to Figure 3 , Figure 3 This is a flowchart of the image preprocessing module provided in this application embodiment. The image preprocessing module is used to perform standardization and scaling processing on the acquired grayscale image. The standardization processing is calculated according to the following formula:

[0056]

[0057] To standardize the input data, For the standardized data, This is the mean of all data for ballast track. The annotation difference for all data of ballast track;

[0058] The grayscale image is standardized and then scaled to 1600*256 pixels.

[0059] The sleeper detection module uses a preset target detection model to detect targets in the preprocessed grayscale image. The preset target detection model can be the YOLO series or the Faster RNNN series. In this embodiment, YOLO5 from the YOLO series is used as the target detection model in the sleeper detection module. It consists of three parts: Backbone, Neck, and Head. The Backbone part mainly extracts multi-scale features from the preprocessed track bed image for use in subsequent detection tasks. The Neck part mainly fuses the extracted scale features to generate a multi-scale feature pyramid. The Head part is mainly used to perform multi-scale sleeper detection on the feature pyramid. In YOLOv5, CBL is a combination of Convolution, Batch Normalization, and LeakyReLU operations to complete a single feature extraction operation. Resunit is a residual unit composed of CBLs, ensuring network depth. CSP1-X and CSP2-X are different feature extraction components composed of CBLs and Resunits, capable of extracting more complex features. SPP is a pooling module composed of cascaded MaxPools to obtain features of different sizes. Fcous is composed of Slice slices and CBLs. The object detection model is used to extract features from the sleepers, obtaining their real-time position and shape.

[0060] Please refer to Figure 4 , Figure 4 This is a flowchart of the ballast measurement module provided in this application embodiment. The ballast measurement module combines the acquired depth map and the extracted real-time sleeper positions to complete the ballast measurement. Specifically, based on prior data of the rail position, the depth map is segmented by a height threshold (extracting the rail region) and morphological filtering is performed (opening operation to remove isolated noise points, closing operation to fill the gaps between rail fasteners to ensure regional connectivity) to obtain a segmented binary map containing the rail region; using the segmented binary map and the original depth map, the relative height value of the rail is obtained, i.e., the height of the rail surface relative to the ground; based on the relative height value of the rail and the actual height of the rail itself, a segmentation threshold is determined to segment the ballast area in the original depth map, and the ballast measurement is performed. The ballast bed height is calculated by subtracting the actual height of the rail from its relative height. This height serves as a segmentation threshold to divide the ballast bed area. The depth map corresponding to the ballast bed area is then subjected to mean filtering (smoothing noise and reducing interference from ballast particle undulations) and morphological dilation (expanding the ballast bed area and compensating for edge defects in the threshold segmentation). This difference map is then compared with the original depth map to obtain a difference map. Threshold segmentation is performed on this difference map to obtain the initial sleeper area. The above operations highlight the sleeper area. Finally, the depth map corresponding to the initial sleeper area is morphologically filtered and logically ANDed with the area corresponding to the extracted real-time sleeper position coordinates to obtain the precise sleeper area. The precise ballast area is then obtained by performing a difference operation on the ballast bed area and the sleeper area.

[0061] The calculation of the rail base height includes:

[0062]

[0063] The height of the rail base is [height]. This is the average rail surface height of the left and right rails. This refers to the standard height of the rails;

[0064] The calculation of sleeper height includes:

[0065]

[0066] The sleeper height is [the value of the sleeper]. The average height of the center of the sleeper;

[0067] The calculation of the actual height of ballast on both sides of the track bed includes:

[0068]

[0069] The actual height of the ballast on both sides of the track bed. This is the average height of the ballast on both sides of the track bed;

[0070] The actual value of the center ballast height in the track bed calculation includes:

[0071]

[0072] This refers to the actual height of the central ballast in the track bed. This is the average height of the ballast in the center of the track bed.

[0073] The ballast saturation quantification module uses the calculated rail base height as a reference value for the ballast height on both sides of the track bed, and the sleeper height as a reference value for the ballast height in the center of the track bed. It then calculates the ratio between the reference values ​​and the actual values ​​of the ballast height on both sides of the track bed, and the ratio between the reference value and the actual value of the ballast height in the center of the track bed. These two ratios clearly quantify the ballast saturation in the areas on both sides and in the center of the track bed, providing decision-making suggestions for subsequent ballast adjustments. This embodiment can simply and efficiently detect ballast within the track bed and generate quantitative results, making it more efficient and standardized compared to inspections relying on manual experience.

[0074] In some embodiments, preprocessing the acquired grayscale image includes: standardizing and scaling the grayscale image.

[0075] In some embodiments, determining the rail region, sleeper region, and ballast region based on the acquired depth map and the real-time position of the sleepers includes:

[0076] Based on the real-time position of the sleeper, the sleeper coordinates are obtained and a corresponding sleeper area is generated, which is denoted as the first sleeper area.

[0077] The acquired depth map is used as the original depth map. Based on the prior data of the rail position, the original depth map is segmented by height threshold and morphologically filtered to obtain a segmented binary map containing the rail region.

[0078] Based on the segmented binary map and the original depth map, the relative height value of the rail is obtained;

[0079] Based on the relative height value and the actual height value of the rail, the segmentation threshold of the track bed in the original depth map is obtained and segmented to obtain the track bed area;

[0080] The depth map corresponding to the track bed area is subjected to mean filtering and morphological dilation in sequence, and then the difference is subtracted from the original depth map to obtain the difference map;

[0081] The difference map is segmented by thresholding to obtain the initial area of ​​the sleeper;

[0082] Morphological filtering is performed on the depth map corresponding to the initial sleeper region, and an AND operation is performed with the first sleeper region to obtain the sleeper region.

[0083] The ballast area is obtained by subtracting the difference between the track bed area and the sleeper area.

[0084] In some embodiments, calculating the rail base height includes:

[0085]

[0086] The height of the rail base is [height]. This is the average rail surface height of the left and right rails. This refers to the standard height of the rail.

[0087] In some embodiments, calculating the sleeper height includes:

[0088]

[0089] The sleeper height is [the value of the sleeper]. This is the average height of the center of the sleeper.

[0090] In some embodiments, calculating the actual height of the ballast on both sides of the track bed includes:

[0091]

[0092] The actual height of the ballast on both sides of the track bed. This is the average height of the ballast on both sides of the track bed.

[0093] In some embodiments, calculating the actual height of the central ballast of the track bed includes:

[0094]

[0095] This refers to the actual height of the central ballast in the track bed. This is the average height of the ballast in the center of the track bed.

[0096] In some embodiments, quantifying the ballast saturation in the track bed includes:

[0097] Calculate the actual height of the ballast on both sides of the track bed. Reference values ​​of ballast height on both sides of the track bed The ratio, and the actual value of the central ballast height of the track bed. Height of the central ballast of the track bed The ratio of the two values ​​is used to quantify the saturation of ballast in the track bed.

[0098] In some embodiments, the preset location is a location on the line where an electronic tag is pre-installed.

[0099] Example 2

[0100] Based on the quantification system for ballast saturation of ballasted track provided in Embodiment 1 of this application, correspondingly, Embodiment 2 of this application also provides a method for quantifying ballast saturation of ballasted track, such as... Figure 5 As shown, it includes:

[0101] The grayscale and depth images of the track bed are collected at preset locations along the line using image acquisition equipment installed on the inspection vehicle.

[0102] Preprocess the acquired grayscale images;

[0103] The pre-processed grayscale image is used to detect targets using a preset target detection model to obtain the real-time position of the sleepers;

[0104] Based on the collected depth map and the real-time position of the sleepers, the rail area, sleeper area, and ballast area are determined; based on the rails and the depth map, the rail base height is calculated; based on the sleeper area and the depth map, the sleeper height is calculated; based on the rail area, the ballast area, and the depth map, the actual values ​​of the ballast height on both sides of the track bed are calculated; based on the sleeper area, the ballast area, and the depth map, the actual value of the ballast height in the center of the track bed is calculated.

[0105] The rail base height is used as a reference value for the ballast height on both sides of the track bed, and the sleeper height is used as a reference value for the ballast height in the center of the track bed. Based on the reference values ​​of the ballast height on both sides of the track bed and the actual values ​​of the ballast height on both sides of the track bed, and the reference value of the ballast height in the center of the track bed and the actual values ​​of the ballast height in the center of the track bed, the ballast saturation in the track bed is quantified.

[0106] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computing software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0107] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the invention.

[0108] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A quantitative system for saturation of ballast in ballasted railway tracks, characterized in that, include: Image acquisition module: Using image acquisition equipment installed on the inspection vehicle, grayscale and depth images of the track bed are acquired at preset locations along the line. Image preprocessing module: preprocesses the acquired grayscale images; Sleeper detection module: Uses a preset target detection model to perform target detection on the preprocessed grayscale image to obtain the real-time position of the sleeper; Ballast Measurement Module: Based on the acquired depth map and the real-time position of the sleepers, it determines the rail area, sleeper area, and ballast area; based on the rail and the aforementioned depth map, it calculates the rail base height. Calculate the sleeper height based on the sleeper area and the depth map; Based on the rail area, the ballast area, and the depth map, the actual values ​​of the ballast height on both sides of the track bed are calculated. Based on the sleeper area, the ballast area, and the depth map, the actual value of the ballast height in the center of the track bed is calculated. The calculation of the rail base height includes: The height of the rail base is [height]. This is the average rail surface height of the left and right rails. This refers to the standard height of the rails; The calculation of sleeper height includes: The sleeper height is [the value of the sleeper]. The average height of the center of the sleeper; The calculation of the actual height of ballast on both sides of the track bed includes: The actual height of the ballast on both sides of the track bed. This is the average height of the ballast on both sides of the track bed; The actual value of the center ballast height in the track bed calculation includes: This refers to the actual height of the central ballast in the track bed. The average height of the ballast in the center of the track bed; Ballast saturation quantification module: The rail base height is used as a reference value for the ballast height on both sides of the ballast bed, and the sleeper height is used as a reference value for the ballast height in the center of the ballast bed; based on the reference values ​​and actual values ​​of the ballast height on both sides of the ballast bed, and the reference value and actual value of the ballast height in the center of the ballast bed, the ballast saturation in the ballast bed is quantified; Quantifying the saturation of ballast in the track bed includes: Calculate the actual height of the ballast on both sides of the track bed. Reference values ​​of ballast height on both sides of the track bed The ratio, and the actual value of the central ballast height of the track bed. Height of the central ballast of the track bed The ratio of the two values ​​is used to quantify the saturation of ballast in the track bed.

2. The quantification system for ballast saturation of ballasted track as described in claim 1, characterized in that, Preprocessing the acquired grayscale image includes: standardizing and scaling the grayscale image.

3. The quantification system for ballast saturation of ballasted track as described in claim 1, characterized in that, Based on the collected depth map and the real-time location of the sleepers, the rail area, sleeper area, and ballast area are determined to include: Based on the real-time position of the sleeper, the sleeper coordinates are obtained and a corresponding sleeper area is generated, which is denoted as the first sleeper area. The acquired depth map is used as the original depth map. Based on the prior data of the rail position, the original depth map is segmented by height threshold and morphologically filtered to obtain a segmented binary map containing the rail region. Based on the segmented binary map and the original depth map, the relative height value of the rail is obtained; Based on the relative height value and the actual height value of the rail, the segmentation threshold of the track bed in the original depth map is obtained and segmented to obtain the track bed area; The depth map corresponding to the track bed area is subjected to mean filtering and morphological dilation in sequence, and then the difference is subtracted from the original depth map to obtain the difference map; The difference map is segmented by thresholding to obtain the initial area of ​​the sleeper; Morphological filtering is performed on the depth map corresponding to the initial sleeper region, and an AND operation is performed with the first sleeper region to obtain the sleeper region. The ballast area is obtained by subtracting the difference between the track bed area and the sleeper area.

4. The quantitative system for saturation of ballast in ballasted track as described in claim 1, characterized in that, The preset location is where an electronic tag is pre-installed on the line.

5. A method for quantifying the saturation of ballast in ballasted track, employing the quantification system for the saturation of ballast in ballasted track as described in claim 1, characterized in that, include: The grayscale and depth images of the track bed are collected at preset locations along the line using image acquisition equipment installed on the inspection vehicle. Preprocess the acquired grayscale images; The pre-processed grayscale image is used to detect targets using a preset target detection model to obtain the real-time position of the sleepers; Based on the collected depth map and the real-time position of the sleepers, the rail area, sleeper area, and ballast area are determined; based on the rail and the aforementioned depth map, the rail base height is calculated. Calculate the sleeper height based on the sleeper area and the depth map; Based on the rail area, the ballast area, and the depth map, the actual height of the ballast on both sides of the track bed is calculated; based on the sleeper area, the ballast area, and the depth map, the actual height of the ballast in the center of the track bed is calculated. The rail base height is used as a reference value for the ballast height on both sides of the track bed, and the sleeper height is used as a reference value for the ballast height in the center of the track bed. Based on the reference values ​​of the ballast height on both sides of the track bed and the actual values ​​of the ballast height on both sides of the track bed, and the reference value of the ballast height in the center of the track bed and the actual values ​​of the ballast height in the center of the track bed, the ballast saturation in the track bed is quantified.

Images