6results about How to "Enhance edge information" patented technology

The invention relates to the field of steel belt monitoring, in particular to a steel belt automatic deviation correction method based on machine vision, and the method comprises the steps: obtaining an image when a steel belt works, calculating the self-adaptive standard deviation of each pixel point in the image in a bilateral filtering algorithm, and carrying out the denoising of the image through the bilateral filtering algorithm, so as to obtain an optimal image; performing edge detection on the optimal image to obtain the edge of the steel belt, calculating the distance between the edge of the steel belt and the standard position, and adjusting a guide roller according to the obtained distance to enable the steel belt to be located in the standard position range; the position identification accuracy of the steel belt can be improved, and deviation correction of the steel belt is facilitated.

The invention discloses an image restoration method based on spectrum guidance enhancement. The image restoration method comprises a diffusion model; the diffusion model comprises a forward noise adding process and a reverse denoising process; in the reverse denoising process, a U-Net neural network is adopted to carry out denoising restoration on the noise-added image to obtain a restored image; in the U-Net neural network, spectral decomposition is carried out on low-order features of an encoder through a spectrum guidance module to obtain high-frequency components and low-frequency components, weight distribution is carried out on the high-frequency components and the high-order features through a trans-attention mechanism, the high-frequency components and the high-order features are spliced with up-sampling features of a decoder, and local high-frequency features of an image are restored; fusing the low-frequency component with the up-sampling feature of the decoder, and repairing the global low-frequency feature of the image; training and testing the diffusion model introduced into the spectrum guidance module by adopting a training set and a test set divided by the image data set; inputting an image needing to be repaired into the diffusion model introduced into the frequency spectrum guidance module to obtain a high-resolution repaired image; and the restored image is clearer and more accurate.

The present invention provides a method for detecting gas and liquid leakage using infrared images based on deep learning, the method comprising the following steps: collecting infrared thermal image data in gas and liquid leakage scenarios; preprocessing the infrared thermal image data in gas and liquid leakage scenarios, marking gas and liquid leakage information on the infrared thermal image data, obtaining a training data set, and using the training data set to train a target detection network to obtain the trained target detection network weights; acquiring and preprocessing infrared thermal imaging data in a scene to be detected, loading the trained target detection network weights, and performing real-time detection on the infrared thermal imaging data in the scene to be detected input to the target detection network to obtain the detection results; and visually outputting the detection results. The present invention is based on a target detection algorithm based on deep learning, uses field data to train a neural network, and uses the characteristics of neural networks that are faster, more accurate, and more stable than traditional methods to improve the degree of automation and accuracy of detection.

The invention discloses a superpixel clustering method and device for an infrared image, and the method comprises the steps: collecting an original infrared image, converting the original infrared image into a Lab color space, and obtaining a Lab color mode image; extracting a region of interest from the Lab color mode image; calculating the gradient of each feature element of each pixel of the Lab color mode image by adopting a Sobel operator to obtain a gradient value of each pixel; setting an initial clustering number, and performing initial clustering on the Lab color mode image by adopting a non-iterative clustering method according to the gradient value and the initial clustering number to obtain an initial super-pixel clustering result; updating the clustering number according to the initial super-pixel clustering result; performing secondary clustering on the region of interest by adopting an iterative clustering method according to the gradient value of the pixels in the region of interest and the updated clustering number to obtain a fine super-pixel clustering result of the region of interest; and finally, fragmentary superpixel combination is carried out. According to the method, the accuracy of super-pixel clustering can be improved.

The utility model relates to the technical field of light source discloses a light source structure of coaxial light source and tunnel light source combination, including coaxial light source and tunnel light source, be provided with first shooting window on the coaxial light source, be provided with second shooting window on the tunnel light source, the coaxial light source sets up first opening in the one end with first shooting window opposite, the tunnel light source sets up second opening in the one end with second shooting window opposite, the coaxial light source with tunnel light source is connected, and first shooting window, first opening, second shooting window and second opening are on a straight line and sequentially communicate, this scheme integrates coaxial light source and tunnel light source, so that the user can realize the light switching between coaxial light source and tunnel light source in the same station, does not need to repeatedly assemble and disassemble coaxial light source or tunnel light source, improves the detection efficiency.

The present application relates to the technical field of image data processing, and more particularly to a kind of based on fractional order total variation GM-APD laser radar range image denoising algorithm.The algorithm includes the following steps: step S1, original data is estimated by maximum likelihood estimation algorithm pixel by pixel distance parameter, realize the extraction of GM-APD range image;Step S2, introduce fractional order differential operator to construct FOTV model, obtain the spatial relationship and similarity relationship between pixels using spatial kernel function and value domain kernel function to optimize fractional order differential operator, construct FOTVGM-APD laser radar denoising model based on spatial kernel function and value domain kernel function;Step S3, split Bregman algorithm is used for range image denoising.The present application realizes the suppression of GM-APD laser radar range image lost information and distance abnormal value noise, while retaining target details and contour information.