A method and system for detecting wheel surface scratches of an orbital train

Abstract

The present invention provides a method and system for detecting wheel surface scratches of a rail train, including a wheel surface image acquisition step of acquiring a wheel surface image of a wheel in high-speed motion collected by a vision camera under the illumination of a stroboscope; an abnormal feature mapping step of obtaining an abnormal feature group by change detection of the wheel surface images at different angles and a template image, then performing positioning and splicing on the abnormal feature group to obtain an abnormal feature block, and mapping it in the front wheel surface image as a wheel surface abnormal map; a feature depth analysis step of obtaining depth information of a number of vertices in the abnormal feature block according to the abnormal feature block through a depth analysis strategy, the number of vertices including edge vertices and non-edge vertices of the abnormal feature block, and comparing the depth information of the edge vertices and the non-edge vertices; an abnormal screening and matching step of outputting a scratch type or other types according to the comparison result; the advantage of the present invention is that it can accurately locate the wear on the wheel side surface or the shaft surface and accurately judge that the wear is of the scratch type.

Description

Technical Field

[0001] The present invention relates to the technical field of wheel surface detection of rail vehicles, and more specifically, to a method and system for detecting wheel surface scratches of rail trains. Background Art

[0002] As a key component of the running gear of a rail vehicle, the condition of the wheel set directly affects the running safety and stability of the train. If defects such as wear, cracks, and deformation of the wheel set are not detected and processed in time, serious safety accidents may occur. Therefore, effective detection of the train wheel set is an important measure to ensure the running safety of the train.

[0003] With the rapid development of high-speed railways, the running speed of trains is constantly increasing, and the performance requirements for wheel sets are also getting higher and higher. High-speed railway trains need to bear greater loads and impacts during operation. Therefore, scratches on the wheel surface and the wheels will be more serious, resulting in a decrease in the smoothness of the train during driving, such as jitter or uneven force.

[0004] In the automated detection for the wheel surface detection of rail vehicles, there are already some technical solutions for wheel surface detection. For example, the "CN110276297B Train Tread Wear Detection System and Method" disclosed in the Chinese patent provides a method of obtaining a thermal imaging map of the bottom of the train through thermal imaging, and obtaining abnormal tread wear and scratches of the wheel set and the track according to the matching of the thermal imaging map with the model. However, this detection method cannot judge the abnormal defects on the surface of the wheel surface. When there are scratches or stains on the surface of the wheel surface, thermal imaging cannot identify them, so it is difficult to meet the surface scratch detection of the wheel surface. Summary of the Invention

[0005] Aiming at the deficiencies of the existing technology, the purpose of the present invention is to provide a method and system for detecting wheel surface scratches of rail trains, which can accurately locate the wear on the wheel side or the shaft surface and accurately judge the wear as a scratch type.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A method for detecting wheel surface scratches of a rail train, comprising the following steps:

[0008] A wheel surface image acquisition step of acquiring an image of the wheel surface under high-speed movement collected by a vision camera irradiated by a stroboscope as a wheel surface image;

[0009] An abnormal feature mapping step of obtaining a group of abnormal features by change detection of the wheel surface images at different angles and a template image, then performing positioning and splicing on the group of abnormal features to obtain an abnormal feature block, and mapping the abnormal feature block in the front image of the wheel surface as a wheel surface abnormal image;

[0010] A feature depth analysis step, obtaining depth information of a plurality of points in the abnormal feature block through a depth analysis strategy according to the abnormal feature block, wherein the plurality of points include edge points and non-edge points of the abnormal feature block, and comparing the depth information of the edge points and the non-edge points;

[0011] In the abnormal screening and matching step, when the depth of the edge item point is less than the depth of the non-edge item point, the output abnormal type is the scratch type, otherwise, the output abnormal type is other types.

[0012] Furthermore, the depth analysis strategy includes an edge trajectory planning step and a depth estimation step.

[0013] The edge trajectory planning step is to draw a plurality of edge points of the abnormal feature block in the front image of the wheel surface to obtain an edge trajectory line;

[0014] The depth estimation step selects any point in the edge trajectory as an edge point, selects any point in the area surrounded by the edge trajectory as a non-edge point, calculates the disparity in the wheel surface images at any two different angles, and then obtains the point distance between the item to be measured and the visual camera through depth calculation based on the disparity, and subtracts the point distance from the distance of the visual camera from the wheel surface to obtain the depth value of the item to be measured.

[0015] Furthermore, in the abnormal feature mapping step, edge contours of abnormal features are extracted according to edge detection, the edge contours of each abnormal feature in the abnormal feature group are point matched to obtain a matching point group, and then a transformation matrix is calculated according to the matching point group, one of the abnormal features is aligned with another abnormal feature through the transformation matrix, and after alignment, the two are fused to obtain an abnormal feature block.

[0016] Furthermore, in the abnormal feature mapping step, a transformation matrix is calculated for any wheel surface image and the wheel surface front image, and several edge contour points are selected in the wheel surface image and transformed through the transformation matrix to obtain the position points of the edge contour points in the wheel surface front image, and then the abnormal feature block is matched with the corresponding points used for mapping through the position points, so that the abnormal feature block is mapped as a whole to the wheel surface front image.

[0017] Furthermore, the method also includes a stroboscopic adjustment step, in which the corresponding stroboscope flashing frequency is indexed in a preset table according to the train speed as the current frequency value.

[0018] Furthermore, it also includes a feature verification and analysis step, in which the wheel surface abnormality map is binarized to obtain a binary image, and in the binary image, it is judged based on pixels whether the pixel value in the abnormal feature block is the same as the wheel surface pixel value outside the abnormal feature block. If so, the output abnormality type is a scratch type, if not, the output abnormality type is a stain diffusion type.

[0019] Further, it further includes a feature verification and analysis step. When the pixel values within the abnormal feature block in the binarized image are different from the pixel values of the wheel surface outside the abnormal feature block, the contour line of the abnormal feature block is obtained. If there are sub-contour lines within the contour area of the abnormal feature block, the scratch filling type is output, and the scratch filling type reflects the stain filling and diffusion after the wheel surface is scratched.

[0020] Further, it further includes an instruction feedback step. The depth value is compared with a preset value N1. If the depth value is greater than the preset value N1, a crisis instruction is output. If the depth value is less than or equal to the preset value N1, a correction instruction is output.

[0021] Further, it further includes a scratch area calculation step. The abnormal feature block under the scratch type is obtained, and the abnormal feature block is contour-segmented to obtain several scratch areas that can be calculated. The area values of the scratch areas are respectively obtained through area calculation and accumulated to obtain the scratch area value;

[0022] In the instruction feedback step, the scratch area value is compared with a preset value N2. If the scratch area value is greater than the preset value N2, a crisis instruction is output. If the scratch area value is less than or equal to the preset value N2, a correction instruction is output.

[0023] An on-rail train wheel surface scratch detection system includes

[0024] A wheel surface image acquisition module that acquires an image of the wheel surface under high-speed movement collected by a vision camera irradiated by a stroboscope as the wheel surface image;

[0025] An abnormal feature mapping module that obtains an abnormal feature group by change detection of the wheel surface images at different angles and a template image, then locates and splices the abnormal feature group to obtain an abnormal feature block, and maps the abnormal feature block in the front wheel surface image;

[0026] A feature depth analysis module that obtains the depth information of several vertices within the abnormal feature block through a depth analysis strategy according to the abnormal feature block. The several vertices include the edge vertices and non-edge vertices of the abnormal feature block, and compares the depth information of the edge vertices and non-edge vertices;

[0027] An abnormal screening and matching module that, when the depth of the edge vertices is less than the depth of the non-edge vertices, outputs the abnormal type as the scratch type, otherwise, outputs the abnormal type as other types.

[0028] Advantages of the present invention: By combining a stroboscope with vision, clear images can be captured while the train wheel surface is rotating. Using change detection technology and comparing with a template image, abnormal features in the wheel surface image can be automatically identified and extracted. Then, by stitching the abnormal features at different angles, a complete abnormal feature block that can prove the mapping in the front wheel surface image can be obtained. Compared with the existing single front wheel surface image, the stitching at different angles of the present invention can achieve the purpose of mutual verification, and it is difficult to completely cover the wheel surface with a single front image, which is likely to cause missing feature detection. In addition, through in-depth analysis of any vertex on the edge contour of the abnormal feature block and the vertices within the block area, it can be determined that the case of medium low edge high is the scratched target type to meet the real-time monitoring of the wheel surface under high-speed driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 is the overall flowchart in the present invention;

[0030] Figure 2 is the flowchart of the feature verification analysis step in the present invention;

[0031] Figure 3 is the flowchart of the instruction feedback step in the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0032] The present invention will be further described in detail below with reference to the drawings and embodiments. The same components are denoted by the same reference numerals. It should be noted that the terms "front", "rear", "left", "right", "upper" and "lower" used in the following description refer to the directions in the drawings, and the terms "bottom surface" and "top surface", "inner" and "outer" refer to the directions towards or away from the geometric center of a specific component, respectively.

[0033] Since the current detection method cannot determine the abnormal defects on the wheel surface during movement, when there are scratches or stains on the wheel surface, thermal imaging cannot identify them, and ordinary vision is also difficult to judge, which is difficult to meet the surface scratch detection of the wheel surface. Therefore, the present invention designs this method for detecting scratches on the wheel surface of a rail train, as Figure 1 shown, including the following steps:

[0034] At least two groups of stroboscopes and supporting vision cameras are installed on one side of the wheel surface of the wheels at the bottom of the train;

[0035] Stroboscopic adjustment step: Index the corresponding stroboscope flashing frequency in a preset table as the current frequency value according to the train running speed. The train running speed can be fed back by the train driving system or calculated by detecting the wheel speed;

[0036] Wheel surface image acquisition step: Obtain an image of the wheel surface under high-speed movement captured by a vision camera irradiated by a stroboscope at a corresponding wheel speed as the wheel surface image. At this time, a single wheel surface image is a side-axis view of the wheel surface. In addition, the wheel surface image needs to be preprocessed, including denoising, enhancing contrast, correcting distortion, etc., to improve the accuracy of subsequent processing.

[0037] Abnormal feature mapping step: Template image establishment: Establish a standard template image of the wheel surface, which should include a wheel surface without abnormal features. The standard template image includes a side-axis view template map of the wheel surface;

[0038] Feature extraction: The abnormal parts are obtained by change detection between the wheel surface images at two angles in the base quantity and the corresponding template images. The main process of change detection is through image segmentation, feature extraction, change detection algorithm calculation, and result verification. Existing change detection algorithms include direct comparison method, classification comparison method, difference method, ratio method, and change vector analysis method, etc.;

[0039] Abnormal feature location and splicing: The separately located abnormal feature parts in the two wheel surface images are spliced to obtain a complete abnormal feature block. The abnormal feature block is an abnormal block that can be mapped onto the front image of the wheel surface, that is, after mapping, a wheel surface abnormal map is obtained;

[0040] The splicing principle is as follows: Edge detection, use an edge detection algorithm (such as Canny) to extract the edge contours of each abnormal feature; Feature matching, match the edge contours of each abnormal feature through a matching algorithm (such as the nearest neighbor algorithm, k-nearest neighbor algorithm, etc.) to obtain a group of matching points for the corresponding feature points between the two images; Calculate the transformation, according to the matched feature points, calculate the transformation matrix between the images (such as affine transformation, perspective transformation, etc.). This transformation matrix describes how to map the points on one image to the corresponding points on another image; Image splicing, use the calculated transformation matrix to splice the two images. During the splicing process, use an image fusion algorithm (such as linear fusion, pixel fusion, etc.) to process the gap at the splicing point to ensure a smooth transition region between the images, which is equivalent to transforming one abnormal feature through the transformation matrix to align it with another abnormal feature, and after alignment, the two are fused to obtain the abnormal feature block;

[0041] The mapping principle is as follows: Calculate the transformation matrix by performing a calculation on any wheel surface image and the front wheel surface image. Select several edge contour points in the wheel surface image and transform them through the transformation matrix to obtain the position points of the edge contour points in the front wheel surface image. Then, match the corresponding points of the abnormal feature block used for mapping through the position points, so that the entire abnormal feature block is mapped onto the front wheel surface image. In the wheel surface image, find the vertex of the wheel surface as the reference point and the edge points of the abnormal feature. Since the wheel surface image is a visually stretched image, the reference point and the edge points can be determined. A point group for calculating the transformation matrix is formed by the reference point and the edge points, and then the corresponding position points in the abnormal feature block are mapped one by one onto the front wheel surface image.

[0042] Feature depth analysis steps: Obtain the depth information of several vertices within the abnormal feature block through the depth analysis strategy based on the abnormal feature block. The several vertices include the edge vertices and non-edge vertices of the abnormal feature block. Compare the depth information of the edge vertices and non-edge vertices. The depth analysis strategy includes an edge trajectory planning step and a depth estimation step.

[0043] Edge trajectory planning step: Since the abnormal feature block has been mapped onto the front wheel surface image, several edge points of the abnormal feature block are drawn in the front wheel surface image to obtain an edge trajectory line. The generation of the edge trajectory line uses the drawn edge points and generates a continuous edge trajectory line through an interpolation or fitting algorithm. This edge trajectory line is used for the subsequent depth estimation step.

[0044] Depth estimation step: Select any point on the edge trajectory line as an edge vertex, and select any point within the area surrounded by the edge trajectory line as a non-edge vertex. Calculate the parallax in the wheel surface image at two different angles, and then obtain the point distance between the vertex to be measured and the vision camera through depth calculation based on the parallax. Subtract the distance between the vision camera and the wheel surface from the point distance to obtain the depth value of the vertex to be measured. Normally, multiple edge vertices and non-edge vertices are selected for calculation.

[0045] Abnormal screening and matching step: When the depth of the edge vertex is less than the depth of the non-edge vertex, that is, the edge is high and the middle is low, then output the abnormal type as the scratch type. On the contrary, when the edge is low and the middle is high, then output the abnormal type as other types. Other types include mud stain coverage type, etc.

[0046] When the train is running in the mountains, if it rains or there are mud blocks being run over by the wheels, mud stains may adhere to the wheel surface of the wheels. If it is a stone, after the stone is hit by the wheel, the stone will bounce up and hit the wheel surface, causing scratches. Since the scratch itself is a sunken area, when the mud stain covers the scratch and the wheel rotates at high speed, the mud stain will spread, resulting in a situation where the edge is high and the middle is low. Therefore, it also includes a feature verification and analysis step, such as Figure 2As shown, the wheel surface abnormality map is binarized to obtain a binary image. In the binary image, it is determined whether the pixel value in the abnormal feature block is the same as the wheel surface pixel value outside the abnormal feature block according to the pixel. If so, the output abnormality type is the scratch type. If not, the output abnormality type is the stain diffusion type. Specifically, if the pixel value in the abnormal feature block is the same as the pixel value of the normal part of the wheel surface (or very close, considering possible noise or error), it may indicate that the abnormality is caused by scratches or similar physical damages, because these damages usually destroy the original pixel value distribution, but may appear as the same value after binarization;

[0047] If the pixel values within the abnormal feature block are different from those of the normal part of the wheel surface, it may indicate that the abnormality is caused by stain diffusion, oil stains, watermarks, etc., because these types of abnormalities usually change the pixel values so that they present different values from the normal part of the wheel surface after binarization.

[0048] like Figure 2 As shown, it also includes a feature verification analysis step. When the pixel value in the abnormal feature block of the binary image is different from the wheel surface pixel value outside the abnormal feature block, the contour line of the abnormal feature block is obtained. If there is a sub-contour line in the contour area of the abnormal feature block, the scratch filling type is output. The scratch filling type reflects the filling and diffusion of stains after the wheel surface is scratched. Specifically, sub-contour line detection is performed in the extracted contour line area of the abnormal feature block. The sub-contour line refers to the additional contour line formed inside the abnormal feature block due to the filling of stains after the scratch. These sub-contour lines usually appear as small or irregular boundaries inside the abnormal feature block. If the sub-contour line is detected in the contour area of the abnormal feature block, the scratch filling type is output. The scratch filling type reflects the situation that the wheel surface is filled and diffused by stains or other substances after the scratch. If the sub-contour line is not detected, it may belong to other types of abnormalities, such as simple scratches or stain diffusion, etc., and is output according to the previous analysis steps.

[0049] Since the wheel scratches are too serious, the bearing capacity of the wheel will be reduced, which may affect the driving safety. Therefore, the present invention also includes a command feedback step, such as Figure 3 As shown, the depth value is compared with the preset value N1. If the depth value is greater than the preset value N1, a crisis instruction is output to immediately notify relevant personnel or systems to take necessary measures, such as stopping for inspection, replacing the wheel surface, or performing emergency repairs, etc., to prevent potential safety accidents or performance degradation. If the depth value is less than or equal to the preset value N1, a correction instruction is output, which is only a recording function, and the relevant personnel or system will conduct targeted inspections and repairs on the wheel surface to ensure that it returns to normal.

[0050] like Figure 3As shown, it also includes a scratch area calculation step. All abnormal feature blocks under the scratch type are obtained. One side wheel surface of a vehicle may include multiple scratch areas (abnormal feature blocks). Since the scratches are irregular and it is difficult to calculate their areas, the abnormal feature blocks are contour-divided to obtain several scratch areas that can be calculated. The area values of the scratch areas are obtained through area calculation respectively, and the scratch area value is obtained by accumulation;

[0051] Instruction feedback step: Compare the scratch area value with the preset value N2. If the scratch area value is greater than the preset value N2, a crisis instruction is output. If the scratch area value is less than or equal to the preset value N2, a correction instruction is output.

[0052] A wheel surface scratch detection system for rail trains corresponding to the scratch detection method, including

[0053] A wheel surface image acquisition module, which acquires the image of the wheel surface under high-speed movement collected by a vision camera irradiated by a stroboscope as the wheel surface image;

[0054] An abnormal feature mapping module, which obtains an abnormal feature group by change detection of the wheel surface images at different angles and the template image, then locates and stitches the abnormal feature group to obtain an abnormal feature block, and maps the abnormal feature block in the front wheel surface image;

[0055] A feature depth analysis module, which obtains the depth information of several vertices in the abnormal feature block through a depth analysis strategy according to the abnormal feature block. The several vertices include the edge vertices and non-edge vertices of the abnormal feature block, and compares the depth information of the edge vertices and non-edge vertices;

[0056] An abnormal screening and matching module, when the depth of the edge vertex is less than the depth of the non-edge vertex, it outputs that the abnormal type is the scratch type, otherwise, it outputs that the abnormal type is other types.

[0057] The above is only the preferred embodiment of the present invention. The protection scope of the present invention is not limited to the above embodiments. All technical solutions within the idea of the present invention belong to the protection scope of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A method for detecting wheel surface scratches of an orbital train, characterized in that: It includes the following steps: The step of obtaining the wheel surface image, which obtains the image of the wheel surface under high-speed movement collected by the vision camera irradiated by the stroboscope as the wheel surface image; The step of mapping abnormal features, which obtains a group of abnormal features by change detection of the wheel surface images at different angles and the template image, then locates and splices the group of abnormal features to obtain an abnormal feature block, and maps the abnormal feature block in the front image of the wheel surface as the wheel surface abnormal map; The step of in-depth feature analysis, which obtains the depth information of several vertices in the abnormal feature block through the in-depth analysis strategy according to the abnormal feature block. The several vertices include the edge vertices and non-edge vertices of the abnormal feature block, and compares the depth information of the edge vertices and non-edge vertices; The in-depth analysis strategy includes the edge trajectory planning step and the depth estimation step. In the edge trajectory planning step, several edge points are drawn for the abnormal feature block in the front image of the wheel surface to obtain an edge trajectory line; In the depth estimation step, an arbitrary point is selected as an edge vertex in the edge trajectory line, and an arbitrary point is selected as a non-edge vertex in the area surrounded by the edge trajectory line. The parallax in the wheel surface images at two different angles is calculated, and then the point distance between the to-be-measured vertex and the vision camera is obtained through depth calculation according to the parallax. The difference between the point distance and the distance between the vision camera and the wheel surface is used to obtain the depth value of the to-be-measured vertex; The abnormal screening and matching step, when the depth of the edge vertex is less than the depth of the non-edge vertex, outputs the abnormal type as the scratch type, otherwise, outputs the abnormal type as other types.

2. The method for detecting wheel surface scratches of an orbital train according to claim 1, wherein: In the step of mapping abnormal features, the edge contour of the abnormal feature is extracted according to edge detection, the edge contours of each abnormal feature in the group of abnormal features are point-matched to obtain a group of matching points, and then the transformation matrix is calculated according to the group of matching points. One of the abnormal features is transformed through the transformation matrix to be aligned with another abnormal feature, and the two are fused after alignment to obtain an abnormal feature block.

3. The method for detecting wheel surface scratches of an orbital train according to claim 2, wherein: In the step of mapping abnormal features, a transformation matrix is calculated between any wheel surface image and the front image of the wheel surface. Several edge contour points are selected in the wheel surface image and transformed through the transformation matrix to obtain the position points of the edge contour points in the front image of the wheel surface. Then, the corresponding points for mapping the abnormal feature block are matched through the position points, so that the abnormal feature block is mapped as a whole into the front image of the wheel surface.

4. The method for detecting wheel surface scratches of an orbital train according to claim 3, characterized in that: It further includes the stroboscopic adjustment step, which indexes the corresponding stroboscope flashing frequency in a preset table according to the train running speed as the current frequency value.

5. The method for detecting wheel surface scratches of an orbital train according to claim 1 or 4, characterized in that: It further includes the feature verification and analysis step, which binarizes the wheel surface abnormal map to obtain a binary image, and judges whether the pixel value inside the abnormal feature block is the same as the pixel value of the wheel surface outside the abnormal feature block according to the pixels in the binary image. If so, outputs the abnormal type as the scratch type, if not, outputs the abnormal type as the stain diffusion type.

6. The method for detecting wheel surface scratches of an orbital train according to claim 5, characterized in that: It also includes a feature verification and analysis step. When the pixel value within the abnormal feature block in the binary image is different from the wheel surface pixel value outside the abnormal feature block, the contour line of the abnormal feature block is obtained. If there is a sub-contour line in the contour area of the abnormal feature block, the scratch filling type is output, and the scratch filling type reflects the diffusion of stain filling after the wheel surface is scratched.

7. The method for detecting wheel surface scratches of an orbital train according to claim 6, wherein: The method further includes an instruction feedback step, wherein the depth value is compared with a preset value N1, and if the depth value is greater than the preset value N1, a crisis instruction is output; if the depth value is less than or equal to the preset value N1, a correction instruction is output.

8. The method for detecting wheel surface scratches of an orbital train according to claim 7, wherein: The method also includes a scratch area calculation step, obtaining an abnormal feature block under the scratch type, performing contour segmentation on the abnormal feature block to obtain a number of calculable scratch areas, respectively obtaining area values of the scratch areas through area calculation, and accumulating them to obtain the scratch area value; The instruction feedback step compares the scratch area value with a preset value N2, and outputs a crisis instruction if the scratch area value is greater than the preset value N2; and outputs a correction instruction if the scratch area value is less than or equal to the preset value N2.

9. An on-rail train wheel surface scratch detection system, characterized in that: include The wheel surface image acquisition module acquires the image of the wheel surface under high-speed motion captured by the visual camera under the illumination of the stroboscope as the wheel surface image; The abnormal feature mapping module detects the wheel surface images and the template images at different angles to obtain an abnormal feature group, then locates and splices the abnormal feature group to obtain an abnormal feature block, and maps the abnormal feature block to the front image of the wheel surface; A feature depth analysis module, which obtains depth information of a plurality of points in the abnormal feature block through a depth analysis strategy according to the abnormal feature block, wherein the plurality of points include edge points and non-edge points of the abnormal feature block, and compares the depth information of the edge points and the non-edge points; The depth analysis strategy includes edge trajectory planning step and depth estimation step. The edge trajectory planning step is to draw a plurality of edge points of the abnormal feature block in the front image of the wheel surface to obtain an edge trajectory line; The depth estimation step comprises selecting any point in the edge trajectory line as an edge point, selecting any point in the area surrounded by the edge trajectory line as a non-edge point, calculating the disparity in the wheel surface images at any two different angles, and then obtaining the point distance between the item to be measured and the visual camera through depth calculation according to the disparity, and subtracting the point distance from the distance of the visual camera from the wheel surface to obtain the depth value of the item to be measured; The abnormal screening and matching module outputs the abnormal type as a scratch type when the depth of the edge item point is less than the depth of the non-edge item point; otherwise, the abnormal type is output as other types.

Images