Overhead wire fitting abnormality detection device and overhead wire fitting abnormality detection method

Abstract

This invention provides an overhead line fitting abnormality detection device and overhead line fitting abnormality detection device that can reduce the load of abnormality detection processing and improve abnormality detection accuracy by selecting and processing the best image from among images of the same equipment detected by equipment detection. [Solution] The system includes at least one camera 9 mounted on the roof of the vehicle 5 to photograph the overhead line fittings 7 in front of and / or behind the vehicle 5 in the direction of travel, a learning processing unit 13 that performs learning using image data captured by the camera 9, and a data processing unit 19 that performs abnormality determination using the image data. The learning processing unit 13 includes an equipment learning unit that learns to detect equipment and a parts learning unit that learns to detect parts of the equipment. The data processing unit 19 detects the equipment from the image data and determines the image data to be the best shot if the area in which the equipment is detected is within a predetermined size range.

Description

Technical Field

[0001] The present invention relates to an overhead line fitting abnormality detection device and an overhead line fitting abnormality detection method.

Background Art

[0002] Conventionally, among electric railway facilities, there has been maintenance inspection work for overhead line fittings, and inspectors visually confirmed abnormalities in the overhead line fittings and performed maintenance. An overhead line fitting refers to a fitting for holding an overhead electric trolley wire (trolley wire, hanging wire, auxiliary hanging wire; hereinafter referred to as "overhead line") for supplying power to a vehicle in electric railway facilities at a predetermined position, or for electrically connecting or dividing between a plurality of overhead lines. However, visual inspection has limitations and there is a possibility of overlooking abnormalities, so there has been a demand for automation of this inspection. Furthermore, there is also a demand to perform the inspection work of trolley wire fittings regardless of day or night during the actual line running of operating vehicles.

[0003] Therefore, in Patent Document 1, an object is photographed with a camera mounted on a moving body, an image is generated using a generation model such as a neural network using the photographed image, the similarity between the generated image and the photographed image is obtained, and when this similarity is small, it is determined that there is an abnormality.

[0004] In Patent Document 2, in order to improve the accuracy of abnormality detection, learning is performed for each part constituting an overhead line fitting, and an overhead line fitting abnormality detection device for performing abnormality detection is disclosed. In this device, first, an overhead image of a railway vehicle is acquired by a camera mounted on the roof of the railway vehicle. Next, the trolley wire fittings learned by object detection of machine learning are detected from the acquired image, and semantic segmentation is applied to the target equipment image to convert it into a one-hot representation. This simplifies the image and simplifies the abnormality determination of shape abnormalities. By semantic segmentation, it is possible to extract only the regions of each part of the fitting, so using this, a mask image of only the part is generated, normal data learning for each part is performed, and an abnormality determination is made using the restoration error of the mask part. [Prior art documents] [Patent Documents]

[0005] [Patent Document 1] Japanese Patent Publication No. 2019-133306 [Patent Document 2] Japanese Patent Publication No. 2022-159010 [Overview of the Initiative] [Problems that the invention aims to solve]

[0006] The technologies disclosed in Patent Documents 1 and 2 perform anomaly detection processing on all images captured by the camera. When these technologies are applied to forward monitoring, the overhead line equipment is photographed in the direction of the rails (forward, backward, or both). In this case, the same equipment is photographed in consecutive frames. Therefore, if anomaly detection is performed on all frames, the same equipment will undergo anomaly detection processing multiple times, which may result in wasted processing. Furthermore, when anomaly detection is performed on images in which the target object is small, the number of pixels in the area of ​​the target object decreases, leading to a decrease in detection accuracy. Conversely, when anomaly detection is performed on images in which the target object is too large, the target equipment may be cut off, resulting in a decrease in detection accuracy similar to when the target object is small.

[0007] This invention has been made in view of the circumstances described above, and the problem that this invention aims to solve is to provide an overhead line fitting abnormality detection device and overhead line fitting abnormality detection method that can reduce the load of abnormality detection processing and improve abnormality detection accuracy by selecting and processing the best image from among images of the same equipment detected by equipment detection. [Means for solving the problem]

[0008] The overhead line fitting abnormality detection device according to the present invention, which solves the above problems, comprises at least one camera installed on the roof of a vehicle that photographs overhead line fittings in front of and / or behind the vehicle in the direction of travel, a learning processing unit that learns using image data captured by the cameras, and a data processing unit that performs abnormality determination using the image data. The learning processing unit comprises an equipment learning unit that learns to detect equipment and a parts learning unit that learns to detect parts of the equipment. The data processing unit detects the equipment from the image data using an equipment detection model learned by the equipment learning unit, determines the image data as a best shot if the area in the image data where the equipment is detected is within a predetermined size range, detects the parts from the equipment in the image data determined to be a best shot using a parts detection model learned by the parts learning unit, and determines abnormalities in the detected equipment and / or parts using a pre-learned abnormality detection model.

[0009] The overhead line fitting abnormality detection method of the present invention includes: photographing overhead line fittings in front of and / or behind the direction of travel of the vehicle with at least one camera installed on the roof of the vehicle; performing learning using image data captured by the camera; and performing abnormality determination using the image data, wherein the learning includes learning to detect equipment and learning to detect parts of the equipment, and the abnormality determination includes detecting the equipment from the image data using an equipment detection model learned by learning to detect the equipment, determining the image data as a best shot if the area in the image data in which the equipment is detected is within a predetermined size range, detecting the parts from the equipment in the image data determined to be a best shot using a part detection model learned by learning to detect the parts, and determining abnormalities in the detected equipment and / or parts using a pre-learned abnormality detection model. [Effects of the Invention]

[0010] According to this invention, by selecting and processing the best image from among images of the same equipment detected by equipment detection, it is possible to provide an overhead line fitting abnormality detection device and an overhead line fitting abnormality detection method that can reduce the load of abnormality detection processing and improve the accuracy of abnormality detection. [Brief explanation of the drawing]

[0011] [Figure 1] This is a schematic diagram illustrating the implementation status of the overhead line fitting abnormality detection device according to an embodiment of the present invention. [Figure 2] This is a block diagram showing the configuration of a cable fitting abnormality detection device according to an embodiment of the present invention. [Figure 3] This is a block diagram showing the configuration of the learning processing unit of the overhead wire fitting abnormality detection device according to an embodiment of the present invention. [Figure 4] This is a schematic diagram showing an example of an image captured by a camera according to an embodiment of the present invention. [Figure 5] This is a flowchart illustrating the operation of the overhead wire fitting abnormality detection device according to an embodiment of the present invention. [Figure 6] This is a flowchart illustrating the operation of equipment detection learning according to an embodiment of the present invention. [Figure 7] This is a schematic diagram illustrating the equipment detection results according to an embodiment of the present invention. [Figure 8] This is a flowchart illustrating the operation of component detection learning according to an embodiment of the present invention. [Figure 9] This is a schematic diagram illustrating the component detection results according to an embodiment of the present invention. [Figure 10] This is a schematic diagram illustrating the image cropping and resizing results according to an embodiment of the present invention. [Figure 11] This is a flowchart illustrating the operation of anomaly detection learning according to an embodiment of the present invention. [Figure 12] This is a schematic diagram illustrating the abnormality detection results according to an embodiment of the present invention. [Figure 13] This is a schematic diagram illustrating anomaly detection due to restoration error according to an embodiment of the present invention.

Embodiments for Carrying Out the Invention

[0012] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. FIG. 1 is a schematic diagram showing the implementation status of the overhead line fitting abnormality detection device 1 according to an embodiment of the present invention. As shown in FIG. 1, the overhead line fitting abnormality detection device 1 according to the present invention is mounted on a vehicle 5 traveling on a rail 3, and by cameras 9 (9a, 9b) installed on the roof of the vehicle 5, the overhead line fittings 7 in front of and behind the traveling direction of the vehicle are photographed, and abnormalities of the overhead line fittings 7 are detected based on the obtained image data. In the present embodiment, two cameras are used for front and rear photography, but it is not limited to this, and either one or two or more cameras may be installed by changing the shooting angle, direction, etc.

[0013] FIG. 2 is a block diagram showing the configuration of the overhead line fitting abnormality detection device 1. FIG. 3 is a block diagram showing the configuration of the learning processing unit 13 of the overhead line fitting abnormality detection device 1. As shown in FIGS. 2 and 3, the overhead line fitting abnormality detection device 1 according to the present embodiment includes a camera 9, a storage device 11, a learning processing unit 13, a data processing unit 19, and an input / output unit 21 (user interface, UI: User Interface). The learning processing unit 13 includes an equipment learning unit 15 and a component learning unit 17.

[0014] The camera 9 is installed on the roof of the vehicle 5 as described above, and photographs the overhead line fittings 7 in front of and / or behind the traveling direction of the vehicle 5. In the present embodiment, it includes a camera 9a that photographs in front of the traveling direction of the vehicle and a camera 9b that photographs behind the traveling direction. In the present embodiment, the camera 9 uses an area sensor camera and uses visible light illumination or infrared light illumination as necessary, but what is necessary is a means for photographing the tram line facilities as shown in the monitoring image example in FIG. 4 described later, and the configuration is not limited. The storage device 11 stores the image data photographed by the cameras 9a and 9b. Here, the storage device 11 may be implemented by a storage device such as a semiconductor memory or a magnetic disk.

[0015] The learning processing unit 13 generates a learning model through deep learning. Here, the equipment learning unit 15 learns to detect equipment using the image data stored in the storage device 11 and generates an equipment detection model. The component learning unit 17 learns to detect components of the equipment using the image data in which the equipment has been detected and generates a component detection model.

[0016] In the data processing unit 19, the equipment is detected from the aforementioned image data using the equipment detection model learned by the equipment learning unit 15. At this time, when the area where the equipment in the image data is detected is within a range of a predetermined size, this image data is determined as the best shot. Next, components are detected from the equipment in the image data determined as the best shot using the component detection model learned by the component learning unit 17, and abnormalities in the detected equipment and / or components are determined using a pre-learned abnormality detection model.

[0017] In this embodiment, the learning processing unit 13 and the data processing unit 19 may be an information processing device such as a personal computer or a server configured on the cloud. Each function including the equipment learning unit 15 and the component learning unit 17 may be software or a program executed by a processor such as a CPU, GPU (Graphics Processing Unit), and TPU (Tensor Processing Unit) in the aforementioned information processing device. The input / output unit 21 includes an input unit including at least one of a pointing device and a keyboard, and an output unit including a display.

[0018] FIG. 5 is a flowchart for explaining the operation of the overhead line fitting abnormality detection device 1 according to this embodiment. The operation of the overhead line fitting abnormality detection device 1 will be explained using this flowchart.

[0019] <Image input> The overhead line fitting 7 is photographed by the camera 9 attached to the roof of the vehicle 5. (FIG. 5, S001). <Save to storage device> The image data captured by the camera 9 is saved to the storage device 11. (FIG. 5, S002).

[0020] <Equipment detection> The equipment detection model from the equipment detection model database M01 is used to detect the target equipment (Figure 3, S003). The equipment detection model has been pre-trained using deep learning. Figure 6 is a flowchart showing the training operation of the equipment detection model performed by the equipment learning unit 15. Figure 7 is a schematic diagram showing the results of detecting the target equipment using the equipment detection model MS. As shown in Figure 6, the equipment learning unit 15 first reads image data from the driving image dataset D13 (Figure 6, S101). Next, it performs equipment detection training using data from the equipment annotation database D14, which includes two pieces of data: position information of the rectangular region surrounding the target equipment in the image data (coordinates of the four vertices of the rectangular region) and the correct label (Figure 6, S102). The deeply trained equipment detection model is stored in the equipment detection model database M01 (Figure 6, S103).

[0021] Figure 7 illustrates the operation of equipment detection using an equipment detection model MS that has been pre-trained by deep learning. The equipment detection model MS receives the input image G11 and outputs the equipment detection result G12. As part of the equipment detection result G12, it obtains "rectangular coordinate information of the equipment" as "rectangular coordinate information in the image data" indicated by the dashed line A, and "equipment label" corresponding to the type of equipment as "label information".

[0022] <Equipment detection result determination> Next, if equipment is detected, the process proceeds to the best shot determination (Figure 5, S004, YES). If no equipment is detected, the process proceeds to the shooting end condition determination (Figure 5, S004, NO).

[0023] <Best Shot Judging> Based on the label information of the detected equipment, the best shot rectangle size threshold for that equipment label is read from the best shot database D01 and compared. If the equipment's rectangle size (image area) falls within the threshold area, it is determined to be a best shot and the process proceeds to part detection (Figure 5, S005, YES). If it is determined not to be a best shot, the process proceeds to the next image (Figure 5, S005, NO).

[0024] Let's explain the best shot determination further here. Figure 4 is a schematic diagram showing an example of a camera image (surveillance image). The frames F1 to F3 shown on the upper left of the figure are the results of the rear camera 9b in the direction of travel of vehicle 5, and equipment detection is performed as shown in rectangles A1 to A3. The frames F4 to F6 shown on the upper right of the figure are the results of the front camera 9a in the direction of travel of vehicle 5, and equipment detection is performed as shown in rectangles A4 to A6. Performing subsequent processing (a series of anomaly detection processes) following equipment detection for all frames in which equipment is detected would result in the same processing being performed multiple times for the same equipment, increasing computational costs and leading to duplicate detection results, which is not desirable from the standpoint of processing efficiency. Also, if the target equipment is detected in a small rectangle, the number of pixels of the target equipment will be small, and the detection accuracy tends to decrease in proportion to the resolution. Furthermore, if the target equipment is detected in a rectangle that is too large, there is a possibility that the target equipment is cut off from the image, and similarly, the detection accuracy may decrease.

[0025] Based on the above considerations, in order to improve processing efficiency and detection accuracy, images obtained from prior trial experiments will be analyzed, and appropriate maximum and minimum threshold values ​​will be set for the areas where equipment is detected. If the detected equipment area falls within the predetermined threshold range, the image will be judged as the best shot. Specifically, maximum and minimum threshold values ​​will be set for both the vertical and horizontal dimensions of the rectangle, and if the detected rectangle falls within these thresholds, it will be judged as the best shot. Alternatively, the maximum and minimum values ​​of the number of pixels in the detected equipment area may be set as the threshold values.

[0026] <Component presence detection> If equipment is detected during equipment detection (Figure 5, S003), the system determines whether the target part exists on the detected equipment based on the "equipment label" and the inspection item database D02 (Figure 5, S006). The inspection item database D02 contains information on whether the target part exists on each equipment label. If the target part exists, the system proceeds to the part detection process (Figure 5, S006, YES); otherwise, it proceeds to the image cropping and resizing process (Figure 5, S006, NO).

[0027] <Component Detection> In part detection, object detection is performed only within the rectangular area detected by equipment detection (Figure 5, S003). At this time, part detection is performed using a part detection model from the part detection model database M02 for each piece of equipment in which the target part exists (Figure 5, S007). The part detection model has been pre-trained with deep learning. Figure 8 is a flowchart showing the learning operation of the part detection model executed by the part learning unit 17. Figure 9 is a schematic diagram showing the result of detecting a target part using the part detection model MB, which was used as a conceptual example. As shown in Figure 8, the part learning unit 17 first reads image data from the equipment image dataset D15 (Figure 8, S201). Next, it performs part detection learning using data from the part annotation database D16, which includes two pieces of data: position information of the rectangular area surrounding the target part in the image data (coordinates of the four vertices of the rectangular area) and the correct label (Figure 8, S202). The deep-trained part detection model is stored in the part detection model database M02 (Figure 8, S203). Next, if the learning of all equipment components is not yet complete (Figure 8, S204, NO), the same flow is repeated again from image input S201. If the learning of all equipment components is complete (Figure 8, S204, YES), the learning operation ends there.

[0028] Figure 9 illustrates the operation of equipment detection using a pre-trained deep learning-based component detection model MB. The component detection model MB receives the input image G13 and outputs the component detection result G14. The component detection result obtains multiple "rectangular coordinate information of components" indicated by the dashed line B in the component detection result G14 as "rectangular coordinate information in image data," and a "component label" corresponding to the type of component as "label information." Here, the detection result retains the detection results of both equipment and components, such as the "rectangular coordinate information of equipment" and "equipment label" inherited from equipment detection, and the "rectangular coordinate information of components" and "component label" detected in component detection. Note that the figure illustrated here differs in shape from the equipment illustrated earlier in this embodiment, but the operation of component detection is equivalent. Similarly, the figures shown for illustrative purposes from here on will have different shapes, but the operation is equivalent.

[0029] <Image cropping and resizing> From the image data, an image is extracted based on the "rectangular coordinate information of the equipment" shown by the dashed line A in Figure 7, or the "rectangular coordinate information of the parts" shown by the dashed line B in Figure 9 (Figure 5, S008), and then resized to an image size that can be handled by the anomaly detection model (Figure 5, S009). Figure 10 is a schematic diagram showing an example of the image extraction and resizing process results. In Figure 10, the image extraction and resizing of the rectangular coordinate region of dashed line A is exemplified for the equipment detection result. The extracted image is resized to a square for object detection. The "rectangular coordinate information in the image data," "label information," and "resized extracted image" are sent to the subsequent processing stage.

[0030] <Image Correction Processing> In the image correction process, the image data that was extracted in the previous stage and resized to an image size that can be handled by the anomaly detection model is corrected (Figure 5, S010). For example, brightness correction and edge enhancement processing are performed. The brightness correction method and edge enhancement processing can be any method, but examples include gamma correction and contrast correction for brightness correction, and bilateral filtering for edge enhancement. The corrected "corrected image" is sent to the next image inversion process along with the "rectangular coordinate information" and "label information".

[0031] <Image inversion processing> In the image inversion process, the left-right inversion target area information is read from the left-right inversion target area information database (Figure 5, D03), and it is checked whether the position of the detected object in the corrected image data received from the previous image correction process (Figure 5, S010) belongs to the left-right inversion target area (Figure 5, S011). If the position of the detected object belongs to the left-right inversion target area (Figure 5, S011, YES), the image inversion process is performed (Figure 5, S012), and the inverted image data is sent to the anomaly score calculation process (Figure 5, S013). If the detected position of the detected object does not belong to the left-right inversion target area (Figure 5, S011, NO), the image-corrected image data is sent as is to the anomaly score calculation process (Figure 5, S013).

[0032] Here, we will briefly explain image inversion processing. The equipment and parts targeted for anomaly detection may have symmetry. If we call the parts that have symmetry the "right part" and the "left part," then without inversion processing, it would be necessary to train the anomaly detection model separately for the "right part" and the "left part." However, since the "right part" inherently has a structure equivalent to the "left part" when inverted, we can distinguish between the "right part" and the "left part" based on the position of the detected part, and by inverting one of them, we can arrange the image set so that anomaly detection can be performed with the same structure. For example, an anomaly detection model can be generated by training only the "right part" or only the "left part," thereby reducing the computational cost of model generation. This embodiment employs such image inversion processing.

[0033] <Abnormality degree calculation> Anomaly detection models for each piece of equipment or part, which have been previously trained, are read from the anomaly detection model database M03, applied to the resized cropped image, and the anomaly score is calculated (Figure 5, S013). The anomaly detection models have been pre-trained using deep learning. Figure 11 is a flowchart showing the training operation of the anomaly detection models performed in the equipment training unit 15 and the parts training unit 17. Figure 12 is a schematic diagram showing the results of calculating the anomaly score using the anomaly detection model MK. As shown in Figure 11, the equipment training unit 15 and the parts training unit 17 first read image data from their respective anomaly detection image datasets D17 (Figure 11, S301). Anomaly detection training is performed on the read images (Figure 11, S302). The deeply trained anomaly detection models are saved in the anomaly detection model database M03 (Figure 11, S303). Next, if anomaly detection training for all equipment and parts has not been completed (Figure 11, S304, NO), the same flow is repeated again from image input S301. Once the learning process for anomaly detection of all equipment and components is complete (Figure 11, S304, YES), the learning operation ends there.

[0034] Figure 12 illustrates the operation of anomaly detection using an anomaly detection model MK, which has been pre-trained by deep learning. The anomaly detection model MK takes input images G15 and G16 as input and outputs the component detection result G17. Here, G15 is an example of normal data and G16 is an example of abnormal data. Here, a distance-based anomaly detection model using multidimensional features is illustrated as an example of the anomaly detection model. The anomaly detection model used here can use either supervised or unsupervised training data, as long as it outputs multidimensional features, but if supervised training data is used, it is necessary to annotate whether it is normal or abnormal beforehand. The output multidimensional features are plotted in the latent variable space, and the anomaly score is calculated based on the distance from the normal center. Abnormal data is plotted at a position relatively far from the normal center.

[0035] <Abnormality judgment> The anomaly score, calculated as a distance in the latent variable space, is read from the previously created anomaly detection threshold database D04, and an anomaly judgment threshold set for each target equipment and target part is read. Anomaly judgment is then performed using this threshold (Figure 5, S014). As mentioned above, if the output is a multidimensional feature, the anomaly score is calculated as the distance from the normal center, and if the anomaly score is greater than or equal to the threshold (Figure 5, S014, YES), an anomaly flag is assigned (Figure 5, S016). If the anomaly score is not greater than or equal to the threshold (Figure 5, S014, NO), a normal flag is assigned (Figure 5, S015). After each flag is assigned, the anomaly detection result is saved (Figure 5, S017). The information saved here is "rectangular coordinate information," "label information," and "anomaly judgment result." <Filming completion determination> Finally, it is determined whether processing is complete for all images (Figure 5, S018). If image capture is not complete (Figure 5, S018, NO), the sequence of steps from image input S001 is repeated. If image capture is complete (Figure 5, S018, YES), the process is terminated.

[0036] Furthermore, while there are no particular limitations on the deep learning methods used in the detection models for equipment detection (Figure 3, S003) and component detection (Figure 3, S007) in this processing flow, SSD (SingleShot Multibox Detector) is one example.

[0037] Up to this point, we have used a distance space threshold based on multidimensional features as an anomaly detection model, but we are not limited to this, and we may also use a reconstruction error calculated from the input image and the image reconstructed by an autoencoder or the like. Figure 13 is a schematic diagram illustrating anomaly detection using reconstruction error. For example, when using reconstruction error, the anomaly detection model MA consists of an encoder and a decoder, and takes images G18 and G19 as input and outputs reconstructed images G20 and G21. Then it compares the difference between the input images G18 and G19 and the reconstructed images G20 and G21 and outputs the result. For difference comparison, for example, the difference in RGB values ​​for each pixel may be calculated and these can be summed up and used as an index of the degree of anomaly.

[0038] As described above, in this embodiment, equipment detection is performed using an equipment detection model, and then component detection is performed on the detected equipment using a component detection model for each piece of equipment. Since the degree of abnormality is calculated for each detected piece of equipment and component using its respective abnormality detection model, abnormality detection can be performed not only on equipment with a relatively large area but also on components with a small area, thereby improving the accuracy of abnormality detection. By performing object detection in stages, from equipment detection to component detection, it is possible to detect relatively small areas without using semantic segmentation, and by employing object detection with low computational and annotation costs for target component detection, it is possible to reduce computational costs and improve detection accuracy. Furthermore, after equipment detection, the best shot is determined based on preset maximum and minimum threshold values ​​for the detected equipment area, and the subsequent abnormality detection processing is performed on the image determined to be the best shot. Therefore, it is possible to provide an overhead line fitting abnormality detection device and overhead line fitting abnormality detection method that can reduce the load of abnormality detection processing and improve abnormality detection accuracy.

[0039] In addition to the above, it is possible to select or replace the configurations listed in the above embodiments, or to change them to other configurations as appropriate, as long as it does not deviate from the spirit of the present invention. [Explanation of Symbols]

[0040] 1. Overhead wire fitting abnormality detection device 3. Railway tracks (rails) 5 vehicles 7. Overhead wire fittings 9, 9a, 9b cameras 11 Storage device 13 Learning Processing Unit 15. Equipment Learning Department 17. Parts Learning Department 19 Data Processing Unit 21 Input / Output Section (User Interface, UI)

Claims

1. A vehicle is equipped with at least one camera mounted on the roof of the vehicle, which photographs the overhead wire fittings in front of and / or behind the vehicle in the direction of travel, A learning processing unit that performs learning using image data captured by the aforementioned camera, The system comprises a data processing unit that performs abnormality determination using the aforementioned image data, The learning processing unit includes an equipment learning unit that learns to detect equipment, and a parts learning unit that learns to detect parts of the equipment. In the aforementioned data processing unit, For each type of equipment, the system includes a database that stores minimum and maximum threshold values ​​set for the size of the rectangular area surrounding the equipment in the image data. From the aforementioned image data, the equipment is detected using the equipment detection model learned by the equipment learning unit. A threshold corresponding to the type of equipment detected from the image data is read from the database, and if the area in the image data where the equipment is detected is within the range of the read threshold, the image data is determined to be the best shot. From the image data of the equipment that was determined to be the best shot, the component is detected using the component detection model learned by the component learning unit. An anomaly detection model that has been trained in advance is used to determine the anomaly of the detected equipment and / or component. Overhead wire fitting abnormality detection device.

2. To photograph the overhead wire fittings in front of and / or behind the vehicle in the direction of travel using at least one camera installed on the roof of the vehicle, The learning process is performed using image data captured by the aforementioned camera. This includes performing an anomaly determination using the aforementioned image data, The aforementioned learning includes learning to detect equipment and learning to detect parts of the equipment. Performing the aforementioned abnormality determination means, The equipment is detected by an equipment detection model that has been trained by learning to detect the equipment from the aforementioned image data. For each type of equipment, read the threshold value corresponding to the type of equipment detected from the image data from a database that stores the minimum and maximum threshold values ​​set for the size of the rectangular area surrounding the equipment in the image data. The image data is determined to be the best shot if the area in the image data where the equipment is detected is within the range of the read threshold. The equipment used to determine the best shot is used to detect the part using a part detection model that has been trained by learning to detect the part from the image data. The abnormality of the detected equipment and / or component is determined by a pre-trained anomaly detection model. A method for detecting abnormalities in overhead wire fittings, including the above.

Images