Cable quality detection system and method based on infrared short wave and visible light image feature fusion

Abstract

The invention discloses a cable quality detection system and method based on infrared short wave and visible light image feature fusion. The system comprises an image acquisition module, an image processing module, a feature extraction module, a model training module and a detection module. The image acquisition module is used for acquiring a cable surface image and graying the cable surface image to obtain a grayed image; the image processing module is used for processing the grayed image to obtain an infrared grayscale image and a visible light grayscale image with the same size; the feature extraction module is used for respectively extracting infrared image features and visible light image features of the infrared grayscale image and the visible light grayscale image; the model training module is used for fusing the infrared image features and the visible light image features to obtain fused features, and training a cable quality detection model based on the fused features; and the detection module acquires a real-time cable surface image and performs cable quality detection on the real-time cable surface image based on the cable quality detection model.

Description

Technical Field

[0001] The invention belongs to the technical field of cable quality detection, and in particular relates to a cable quality detection system and method based on the fusion of infrared shortwave and visible light image features. Background Art

[0002] Cables are important power transmission and communication equipment. The surface quality issues in the actual production process directly affect their reliability and safety. In order to ensure accurate detection of surface quality during cable production, traditional detection technologies such as ultrasonic detection, X-ray detection, infrared image detection and visible light image detection have been widely used. However, these technologies also have some challenges in practical applications. For example, ultrasonic detection requires contact detection of cables, which affects production efficiency; X-ray detection equipment is expensive and requires professional operators; infrared and visible light image detection are sensitive to ambient light and material surface characteristics and are easily interfered.

[0003] To solve these problems, emerging technologies such as intelligent vision technology based on deep learning have gradually attracted attention. These technologies can use a large amount of data for pattern recognition and feature extraction, realize efficient detection and classification of cable surface quality, and provide a more accurate and rapid quality control method for the cable production process. For the surface quality detection of cables, the present invention studies a neural network detection method that integrates infrared images and visible light images to ensure the accuracy and reliability of the detection results. The present invention effectively analyzes and comprehensively evaluates the infrared and visible light image data obtained by cable quality detection based on a neural network to identify possible defects in the cable, such as conductor breakage, insulation layer damage, etc., and reduce the false detection rate of detection relying on a single data feature. Summary of the invention

[0004] The present invention aims to solve the deficiencies of the prior art and provides the following solutions:

[0005] The cable quality detection system based on the fusion of infrared shortwave and visible light image features includes: image acquisition module, image processing module, feature extraction module, model training module and detection module;

[0006] The image acquisition module is used to acquire the cable surface image and grayscale the cable surface image to obtain a grayscale image, wherein the grayscale image includes: an initial infrared grayscale image and an initial visible light grayscale image;

[0007] The image processing module is used to process the grayscale image to obtain an infrared grayscale image and a visible light grayscale image of the same size;

[0008] The feature extraction module is used to extract infrared image features and visible light image features of the infrared grayscale image and the visible light grayscale image respectively;

[0009] The model training module is used to fuse the infrared image features and the visible light image features to obtain fused features, and train the cable quality detection model based on the fused features;

[0010] The detection module is used to obtain a real-time cable surface image, and perform cable quality detection on the real-time cable surface image based on the cable quality detection model.

[0011] Preferably, the image acquisition module includes: an infrared image acquisition unit, a visible light image acquisition unit and a grayscale unit;

[0012] The infrared image acquisition unit is used to acquire an infrared image of the cable surface;

[0013] The visible light image acquisition unit is used to acquire a visible light image of the cable surface;

[0014] The grayscale unit is used to grayscale the infrared image and the visible light image to obtain the initial infrared grayscale image and the initial visible light grayscale image.

[0015] Preferably, the image processing module includes: an equalization unit, a filtering unit and a cropping unit;

[0016] The equalization unit is used to perform histogram equalization processing on the grayscale image to obtain a equalized image;

[0017] The filtering unit is used to perform high-pass filtering on the equalized image to obtain a filtered image;

[0018] The cropping unit is used to crop the filtered image into the same size to obtain the infrared grayscale image and the visible light grayscale image of the same size.

[0019] Preferably, the feature extraction module includes: an infrared feature extraction unit and a visible light feature extraction unit;

[0020] The infrared feature extraction unit extracts the infrared image features of the infrared grayscale image based on optimal threshold segmentation;

[0021] The visible light feature extraction unit extracts the visible light image feature of the visible light grayscale image based on edge feature detection.

[0022] Preferably, the workflow of the infrared feature extraction unit includes:

[0023] The OTSU algorithm is used to determine the optimal threshold segmentation, and the infrared grayscale image is converted into an infrared binary image;

[0024] The infrared binary image is processed to reject false defects, and the infrared image features of the processed image are extracted.

[0025] Preferably, the workflow of the visible light feature extraction unit includes:

[0026] Dividing the visible light grayscale image into a plurality of grayscale intervals by using threshold segmentation to generate a visible light binary image;

[0027] Iteratively refolding the visible light binary image, and using structural elements to cover and replace interference factors in the image;

[0028] The visible light image features of the replaced image are extracted.

[0029] Preferably, the model training module includes: a feature encoding correction unit, a feature fusion unit and a network training unit;

[0030] The feature coding correction unit is used to encode the infrared image feature and the visible light image feature, and correct the encoded infrared image feature and the encoded visible light image feature to have the same length;

[0031] The feature fusion unit is used to fuse the corrected infrared image features and the corrected visible light image features to obtain fused features;

[0032] The network training unit trains the cable quality detection model based on the fused features.

[0033] The present invention also provides a cable quality detection method based on the fusion of infrared shortwave and visible light image features. The detection method is applied to any of the above detection systems and comprises the following steps:

[0034] Collecting a cable surface image, and graying the cable surface image to obtain a grayed image, wherein the grayed image includes: an initial infrared gray image and an initial visible light gray image;

[0035] Processing the grayscale image to obtain an infrared grayscale image and a visible light grayscale image of the same size;

[0036] extracting infrared image features and visible light image features of the infrared grayscale image and the visible light grayscale image respectively;

[0037] fusing the infrared image features and the visible light image features to obtain fused features, and training a cable quality detection model based on the fused features;

[0038] A real-time cable surface image is acquired, and cable quality detection is performed on the real-time cable surface image based on the cable quality detection model.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] The present invention converts the grayscale image into a binary image through the OTSU algorithm and performs a false defect rejection process on it, which can achieve the optimal threshold segmentation of the image, obtain a clear binary image, and remove the interference of negative factors such as background noise, false defects and edge burrs. The edge detection algorithm is used to extract the main features of the defect area of ​​the visible light binary image, which can achieve accurate positioning of the image defect area, maximize the retention of the structural characteristics of the image, and reduce the amount of data required for processing and calculation. Through lightweight attention feature fusion technology, the infrared and visible light image data obtained by cable quality detection are effectively analyzed and comprehensively evaluated based on neural networks, realizing efficient detection and classification of cable surface quality, reducing the false detection rate relying on single data feature detection, and ensuring the accuracy and reliability of the detection results. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0042] Figure 1 A schematic diagram of the system structure of an embodiment of the present invention;

[0043] Figure 2 A schematic diagram of the working process of an infrared feature extraction unit according to an embodiment of the present invention;

[0044] Figure 3 A schematic diagram of the working process of a visible light feature extraction unit according to an embodiment of the present invention;

[0045] Figure 4 The figure is a schematic diagram of a method flow of an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0048] Embodiment 1

[0049] In this embodiment, if Figure 1 As shown, the cable quality detection system based on the fusion of infrared shortwave and visible light image features includes: an image acquisition module, an image processing module, a feature extraction module, a model training module and a detection module.

[0050] The image acquisition module is used to acquire the cable surface image and grayscale the cable surface image to obtain a grayscale image. The grayscale image includes: an initial infrared grayscale image and an initial visible light grayscale image.

[0051] The image acquisition module includes: an infrared image acquisition unit, a visible light image acquisition unit and a grayscale unit; the infrared image acquisition unit is used to acquire an infrared image of the cable surface; the visible light image acquisition unit is used to acquire a visible light image of the cable surface; the grayscale unit is used to grayscale the infrared image and the visible light image to obtain an initial infrared grayscale image and an initial visible light grayscale image.

[0052] In this embodiment, the visible light image acquisition unit uses a high-performance image acquisition device to acquire visible light images of the cable surface. The high-performance image acquisition device uses an optical microscopic imaging mode, which can be appropriately magnified during the image acquisition process, and can better capture the tiny cracks, pits and bulges on the cable surface. In order to ensure the quality of the acquired image during the acquisition process, this embodiment introduces a light source illumination system. An independent light source can avoid significant changes in light intensity, and can ensure the clarity of the image when the high-performance image acquisition device acquires cables of different models and colors. The infrared image acquisition unit uses an infrared sensor, and the infrared sensor is placed at the same position of the high-performance image acquisition device to acquire an infrared image of the cable surface. The quality defects on the cable surface will cause grayscale changes in infrared imaging. In order to facilitate subsequent processing, the grayscale unit converts the visible light image into grayscale to obtain an initial visible light grayscale image. Since the infrared image is relatively blurred and lacks detail features, the pixel data of the infrared image is mapped to the [0,255] interval to obtain an initial infrared grayscale image.

[0053] The transmission speed of the cable during the manufacturing process is usually 1-2.5m / s. In order to ensure that all surface defects of the cable are captured, the frame rate of the camera is set to 100 images per second. This embodiment uses four high-performance image acquisition devices placed in four directions of the cable at the same time, which can process 400 images in one second, and the processing time of each frame is within 2.5ms.

[0054] The image processing module is used to process the grayscale image to obtain an infrared grayscale image and a visible light grayscale image of the same size.

[0055] The image processing module includes: an equalization unit, a filtering unit and a cropping unit; the equalization unit is used to perform histogram equalization processing on the grayscale image to obtain an equalized image; the filtering unit is used to perform high-pass filtering processing on the equalized image to obtain a filtered image; the cropping unit is used to crop the filtered image into the same size to obtain an infrared grayscale image and a visible light grayscale image of the same size.

[0056] In this embodiment, the equalization unit can enrich the detailed features of the image by using histogram equalization processing on the cable surface image, making the image clearer and highlighting the texture and details of the cable surface, thereby making it easier to analyze and identify. The filtering unit can enhance the high-frequency information of the image by using high-pass filtering processing on the cable surface image, highlighting the subtle texture and edge features in the image, thereby enhancing the contrast. The cable surface grayscale images collected by the cropping unit have different sizes, and all infrared grayscale images and visible light grayscale images are unified to the same size through image cropping.

[0057] The feature extraction module is used to extract infrared image features and visible light image features of the infrared grayscale image and the visible light grayscale image respectively.

[0058] The feature extraction module includes: an infrared feature extraction unit and a visible light feature extraction unit; the infrared feature extraction unit extracts infrared image features of the infrared grayscale image based on optimal threshold segmentation; the visible light feature extraction unit extracts visible light image features of the visible light grayscale image based on edge feature detection.

[0059] The workflow of the infrared feature extraction unit includes: using the OTSU algorithm to determine the optimal threshold segmentation and converting the infrared grayscale image into an infrared binary image; rejecting false defects on the infrared binary image and extracting the infrared image features of the processed image.

[0060] In this embodiment, if Figure 2 As shown, in order to distinguish the foreground and background domains of the image, the infrared feature extraction unit first uses the OTSU algorithm to convert the grayscale image into a binary image to achieve image threshold segmentation. The OTSU algorithm uses the grayscale histogram of the image to dynamically determine the optimal threshold segmentation through the maximum variance between the foreground and background, thereby obtaining the corresponding binary image. Assuming L is the grayscale level of the image, its pixels can be divided into two categories, C0 and C1, and their probabilities can be described by the following equations:

[0061]

[0062] Among them, P r() represents the probability of the pixel in the bracket, w0 represents the ratio of pixels belonging to the foreground domain, w1 represents the ratio of pixels belonging to the background domain, p(i) represents the probability of a pixel with the i-th grayscale, i represents a natural number, t represents the threshold of the image, and L represents the grayscale of the image; assuming that the grayscale mean square error (GMSE) of the entire image is represented by μ, then the variance between the two categories is It can be defined as:

[0063]

[0064] Wherein, μ0 represents the GMSE of the foreground, and μ1 represents the GMSE of the background. In order to evaluate the quality, this embodiment introduces a threshold judgment function:

[0065]

[0066] Among them, t* represents the When the maximum value is reached, the OTSU algorithm expects the optimal threshold segmentation to convert the grayscale image into a binary image. represents the inverse function, which is the t value when the objective function in the brackets takes the maximum value, and l represents the grayscale level of the image. After threshold segmentation, a clear binary image is obtained, but the image still contains background noise, false defects and edge burrs; in order to remove the above negative factors and false defects, the image must be processed to reject false defects; assuming that the minimum size of the defect that the system needs to identify is εmm×εmm, then the minimum resolution should meet the corresponding ε 2 mm 2 In order to improve the accuracy of detection, this embodiment makes a pixel corresponding to ∈ 2 mm 2 (∈<ε) pixels. Assuming that the number of pixels of the relevant minimum defect is P, P is selected as a fixed threshold to separate true detection and false detection, which can be expressed as:

[0067] P = [ε / ∈]

[0068] Then the algorithm for rejecting pseudo-defects can be described as follows: (1) find the neighborhood connection domain; (2) calculate the area of ​​each connection domain, denoted as S k (k=1,…,N) (3) The resulting image after defect filtering should meet the following requirements:

[0069] f i =B,S k <P

[0070] Among them, fi represents the filtering result of pixel i, that is, the gray value after defect filtering processing, B represents the gray value of the background domain, which is 0 in this embodiment, and the connected domains with an area less than the threshold P are regarded as false defect pixels, and their gray levels are changed to 0, otherwise they are changed to 255. After completing the false defect elimination processing, the infrared image features of the processed image are extracted.

[0071] The workflow of the visible light feature extraction unit includes: using threshold segmentation to divide the visible light grayscale image into several grayscale intervals to generate a visible light binary image; refolding and iterating the visible light binary image, and using structural elements to cover and replace interference factors in the image; extracting the visible light image features of the replaced image.

[0072] In this embodiment, if Figure 3 As shown in the figure, the cable defect image is divided into multiple grayscale intervals by using threshold segmentation technology, and a suitable threshold is selected to compare each pixel in the visible light image, and the pixels of the visible light image are divided into foreground and background. The OTSU algorithm is used for adaptive threshold segmentation, and the uniformity of the grayscale distribution of the image is measured by variance to generate a visible light binary image. Then, the grayscale cable image is refolded iteratively: (1) an initial estimate T0 is selected for a grayed visible light binary image; (2) the image is segmented by T0, and it is divided into two parts (less than the grayscale value T0 and greater than the grayscale value T0), generating two groups of pixels, G1 and G2. G1 consists of all pixels in the cable image whose grayscale value is greater than T0, and G2 consists of all images of the cable image whose grayscale value is less than or equal to T0; (3) Calculate the average grayscale values ​​u1 and u2 of all pixels in G1 and G2 in the cable image; (4) Calculate the new threshold of the cable image: T = 1 / 2 (u1 + u2); (5) Repeat steps (2) to (4) until the difference in the T value in the obtained cable image is less than the predefined parameter T0, then the image parameter T0 is the required threshold; In the thresholded cable defect image, there are some very small isolated points or gaps, which are formed due to random reasons and are not the defect features that need to be extracted. Morphological operations need to be applied to filter out these interferences. The origin value of the structural element is replaced with the minimum value of the pixels in the target image covered by the structural element, and the interference factors in the image are replaced one by one; for the binary cable defect image, if all the points covered by the structural element are in the background or foreground, the minimum value in the range is equal to the origin value, that is, the origin value is not replaced; if the structural element covers an edge, the origin value will be replaced by the minimum value (that is, 0), resulting in the contraction of the boundary, and then the replacement of the interference factors is completed. Finally, the visible light image features of the replaced image are extracted.

[0073] The model training module is used to fuse infrared image features and visible light image features to obtain fused features, and to train a cable quality detection model based on the fused features.

[0074] The model training module includes: a feature coding correction unit, a feature fusion unit and a network training unit; the feature coding correction unit is used to encode the infrared image features and the visible light image features, and correct the encoded infrared image features and the encoded visible light image features to the same length; the feature fusion unit is used to fuse the corrected infrared image features and the corrected visible light image features to obtain fused features; the network training unit trains the cable quality detection model based on the fused features.

[0075] In this embodiment, the feature coding correction unit encodes the infrared image feature and the visible light image feature, and corrects the encoded infrared image feature and the encoded visible light image feature to the same length. Assume that feature x is composed of m1 infrared shortwave image feature sets {f v,1 (x), …, f v,m1 (x)}, the feature q is represented by m2 visible light image feature sets {f s,1 (q),…,f s,m2 (q)}; the two feature fusion blocks encode the infrared shortwave image features and the visible light image features into their d-dimensional cross-modal embeddings e(x) and e(q) respectively. Based on the two embeddings, the feature similarity s(x,q) can be measured:

[0076]

[0077] Among them, fusion v () indicates infrared shortwave image feature fusion, fusion s () represents the fusion of visible light image features, similarity() represents the function of calculating the similarity between two embedded vectors e(x) and e(q); without loss of generality, a set of m different features {f1, ..., f m}, with size {d1,…,d m Since the features are obtained by different extractors and are therefore incompatible, this embodiment uses a feature conversion layer to correct different features to the same length. The feature fusion unit fuses the corrected infrared image features and the corrected visible light image features to obtain fused features. In order to convert the i-th feature into a new d-dimensional feature, use:

[0078]

[0079] Among them, σ is a nonlinear activation function, Linear di×d represents a fully connected layer with an input size of d i , the output size is d. Each input feature has its own linear i is optional when equal to d; although the transformed features {fi ′} are comparable, but they are not equally important for representing infrared shortwave features and visible light features. Therefore, weighted fusion is used to fuse the corrected infrared image features and the corrected visible light image features:

[0080]

[0081] {a1,…,a i}=softmax(Linear d×1 {f′1,…,f′ n}))

[0082] in, represents the fused features, n represents the number of features, ai represents the weight, softmax represents the normalized activation function, Linear d×1 represents the linear transformation layer, which is a linear mapping from the d-dimensional feature space to the 1-dimensional space. When the weights in the equation are forced to be uniform, the attention-free feature fusion block is a special case, that is, a i =1 / n. The network training unit trains the cable quality detection model based on the fused features. Specifically, the triple ranking loss of hard negative mining is used as the base loss function. For a given feature q in a training batch, let x + and x - are features that are correlated and uncorrelated with q, and is the hard negation that most violates the ranking constraint, so we have:

[0083]

[0084] Among them, α is a positive hyperparameter that controls the magnitude of the ranking loss, and argmax x- represents s(x - ,q)-s(x + , q) takes the maximum value when x - When training a cross-modal network that generates multiple similarities, it is better to combine the losses of each similarity than to use a single loss with the combined similarities. Therefore, we follow this strategy and calculate the loss loss i (q), that is, by using s in the equation i Instead of s, calculate the loss in the i-th space and train the network to minimize the combined loss The network at this time is obtained, that is, the cable quality detection model.

[0085] The detection module obtains a real-time cable surface image, and performs cable quality detection on the real-time cable surface image based on a cable quality detection model.

[0086] Embodiment 2

[0087] In this embodiment, a cable quality detection method based on the fusion of infrared shortwave and visible light image features is provided. Figure 4 As shown, the following steps are included:

[0088] S1. Collect the cable surface image and grayscale the cable surface image to obtain the grayscale image, which includes: an initial infrared grayscale image and an initial visible light grayscale image. S2. Process the grayscale image to obtain an infrared grayscale image and a visible light grayscale image of the same size. S3. Extract the infrared image features and visible light image features of the infrared grayscale image and the visible light grayscale image, respectively. S4. Fuse the infrared image features and the visible light image features to obtain the fused features, and train the cable quality detection model based on the fused features. S5. Obtain the real-time cable surface image, and perform cable quality detection on the real-time cable surface image based on the cable quality detection model.

[0089] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. A cable quality detection system based on the fusion of infrared shortwave and visible light image features, characterized in that: include: Image acquisition module, image processing module, feature extraction module, model training module and detection module; The image acquisition module is used to acquire the cable surface image and grayscale the cable surface image to obtain a grayscale image, wherein the grayscale image includes: an initial infrared grayscale image and an initial visible light grayscale image; The image processing module is used to process the grayscale image to obtain an infrared grayscale image and a visible light grayscale image of the same size; The feature extraction module is used to extract infrared image features and visible light image features of the infrared grayscale image and the visible light grayscale image respectively; The model training module is used to fuse the infrared image features and the visible light image features to obtain fused features, and train the cable quality detection model based on the fused features; The detection module is used to obtain a real-time cable surface image, and perform cable quality detection on the real-time cable surface image based on the cable quality detection model.

2. The cable quality detection system based on infrared shortwave and visible light image feature fusion according to claim 1 is characterized in that: The image acquisition module includes: an infrared image acquisition unit, a visible light image acquisition unit and a grayscale unit; The infrared image acquisition unit is used to acquire an infrared image of the cable surface; The visible light image acquisition unit is used to acquire a visible light image of the cable surface; The grayscale unit is used to grayscale the infrared image and the visible light image to obtain the initial infrared grayscale image and the initial visible light grayscale image.

3. The cable quality detection system based on infrared shortwave and visible light image feature fusion according to claim 1 is characterized in that: The image processing module includes: an equalization unit, a filtering unit and a cropping unit; The equalization unit is used to perform histogram equalization processing on the grayscale image to obtain a equalized image; The filtering unit is used to perform high-pass filtering on the equalized image to obtain a filtered image; The cropping unit is used to crop the filtered image into the same size to obtain the infrared grayscale image and the visible light grayscale image of the same size.

4. The cable quality detection system based on infrared shortwave and visible light image feature fusion according to claim 1 is characterized in that: The feature extraction module includes: an infrared feature extraction unit and a visible light feature extraction unit; The infrared feature extraction unit extracts the infrared image features of the infrared grayscale image based on optimal threshold segmentation; The visible light feature extraction unit extracts the visible light image feature of the visible light grayscale image based on edge feature detection.

5. The cable quality detection system based on infrared shortwave and visible light image feature fusion according to claim 4 is characterized in that: The workflow of the infrared feature extraction unit includes: The OTSU algorithm is used to determine the optimal threshold segmentation, and the infrared grayscale image is converted into an infrared binary image; The infrared binary image is processed to reject false defects, and the infrared image features of the processed image are extracted.

6. The cable quality detection system based on infrared shortwave and visible light image feature fusion according to claim 4 is characterized in that: The workflow of the visible light feature extraction unit includes: Dividing the visible light grayscale image into a plurality of grayscale intervals by using threshold segmentation to generate a visible light binary image; Iteratively refolding the visible light binary image, and using structural elements to cover and replace interference factors in the image; The visible light image features of the replaced image are extracted.

7. The cable quality detection system based on infrared shortwave and visible light image feature fusion according to claim 1 is characterized in that: The model training module includes: a feature coding correction unit, a feature fusion unit and a network training unit; The feature coding correction unit is used to encode the infrared image feature and the visible light image feature, and correct the encoded infrared image feature and the encoded visible light image feature to have the same length; The feature fusion unit is used to fuse the corrected infrared image features and the corrected visible light image features to obtain fused features; The network training unit trains the cable quality detection model based on the fused features.

8. A cable quality detection method based on the fusion of infrared shortwave and visible light image features, the detection method being applied to the detection system according to any one of claims 1 to 7, characterized in that: The following steps are involved: Collecting a cable surface image, and graying the cable surface image to obtain a grayed image, wherein the grayed image includes: an initial infrared gray image and an initial visible light gray image; Processing the grayscale image to obtain an infrared grayscale image and a visible light grayscale image of the same size; extracting infrared image features and visible light image features of the infrared grayscale image and the visible light grayscale image respectively; fusing the infrared image features and the visible light image features to obtain fused features, and training a cable quality detection model based on the fused features; A real-time cable surface image is acquired, and cable quality detection is performed on the real-time cable surface image based on the cable quality detection model.

Images