The invention discloses an image intelligent acquisition system and an image intelligent acquisition method for power transmission line UAV patrol inspection. The image intelligent acquisition methodcomprises the steps of: performing coarse positioning on a pole tower when a UAV patrol inspection system arrives at a hovering point along a planned track route so as to realize automatic adjustmentof a pod or a camera holder, aligning data acquisition equipment with a pole tower target to obtain a frame of pole tower image information, carrying out optimization and improvement on loss of a regional extraction network and a classification network of a convolutional neural network, and identifying typical appurtenances attached on the pole tower by utilizing an improved convolutional neural network algorithm; determining a position of the target relative to a whole image according to a target position obtained through identification, calculating a pixel-level deviation amount of the target away from an image center when the target position is not in the image center, and completing position adjustment of the target in the image through converting a pixel value into a camera rotation amount; and determining an area proportion of the target in the image, and performing zooming on the camera or pushing the position of a UAV away from the target forward for photographing if the proportion is less than a set value.

Image intelligent acquisition system and method for power transmission line UAV patrol inspection

The present invention discloses a deep learning-based insulator identification method. The insulator identification method comprises the steps of pre-processing an aerial image, and secondly, extending the data via the methods, such as the geometric transformation, the contrast enhancement, an analog noise adding method, etc.; acquiring the insulator samples, aiming at the insulators of different types, classifying to acquire; determining a to-be-trained model structure; inputting the samples in the to-be-trained model, and continuously adjusting the weights and the bias parameters by the forward propagation and backward propagation methods, and finally determining an optimal model parameter, based on the trained model, taking a to-be-detected image as an input signal, and by the network multi-layer convolution, pooling and full-connection operations, obtaining a final detection identification result. According to the present invention, by a deep learning method, the insulator characteristics are learned continuously, a learning network model is determined, the different insulators are identified under different background environments, and support is provided for the electric power maintenance decisions.

Deep learning-based insulator identification method

The invention belongs to the technical field of computer vision, and provides a training method and device for a deep learning network The method comprises the steps: segmenting an image in a training set into a plurality of different patches; enabling the different patches to be converted into an image set comprising a plurality of images in different scales; carrying out the scale normalization of the image set, and inputting the image set after normalization to a depth neural network system, so as to train the depth neural network system The method and device improve the extraction precision of local features in deep learning training

Training method and device for deep learning network

The invention relates to a power equipment defect intelligent identification method and system based on in-process check images obtained by an unmanned aerial vehicle. The method includes acquiring power transmission line image data in batches by adopting a data flow mode; extracting image features; performing integrated analysis on the image features to achieve automatic positioning and identification for critical components; performing corresponding defect analysis on the critical components according to set defect identification rules to achieve analysis and identification on common defects; summarizing and analyzing analysis and identification results; performing classification according to component types, defect types and the degree of defects so as to facilitate search by classification according to needs; and locally enlarging and displaying specific components. The method and the system can effectively excavate huge value of unstructured big data of in-process check of power grids, refine in-process check processes, and have significance effects on stable running of power transmission lines.

A power equipment defect intelligent identification method and system based on in-process check images obtained by an unmanned aerial vehicle

The invention belongs to the technical field of image processing, discloses a method for identifying and positioning power transmission line insulators in unmanned aerial vehicle aerial images, and solves the problems in the prior art that the detection precision of an identification algorithm of the insulators is not high, the robustness is low, and the identification algorithm is easy to be affected by sample number A group of Gabor wavelet basis with different sizes and different directions and training sample images are taken as convolutions so as to form a group of characteristic vectors which accurately describe sample image texture characteristics A random forest machine learning algorithm with a semi-supervised learning mode is used to train sample data sets of the known category and the unknown category so as to obtain an insulator identification model Through the mode from left to right and from top to bottom, a detection window with the same size as the training sample traverses the input images with different sizes The detection window combining the identification model detects and positions the positions of the insulators in the input images with different sizes And finally the accurate positions of the insulators in the input image with the original size are determined by using a non-maximum inhibition method

Method for identifying and positioning power transmission line insulators in unmanned aerial vehicle aerial images

The invention discloses an insulator identification method for an unmanned aerial vehicle polling an electric transmission line. The method comprises the steps: image collecting and processing: extracting sub-images for training from insulator images of the electric transmission line and initially processing the sub-images to form a training data set; packaging the extracted sub-images for training and adding labels corresponding to the sub-images; training the data by virtue of a convolutional neural network (CNN) algorithm in deep learning to obtain a detection model for insulators; insulator target region detection: detecting an electric transmission line image to obtain a candidate frame of the insulator target; carrying out non-maxima suppression on the candidate frame to obtain a final insulator candidate frame; and carrying out straight line fitting operation on the obtained final insulator candidate frame to obtain a central point and the angle and size information of the candidate frame and finally labeling on the insulator images of the electric transmission line. According to the method disclosed by the invention, images obtained by polling are screened, so that the burden of manual screening is alleviated and the method has a broad application prospect.

Insulator identification method for unmanned aerial vehicle polling electric transmission line

The invention discloses a multi-sensor fusion-based autonomous obstacle avoidance unmanned aerial vehicle system and a control method. The system includes an environment information real-time detection module which carries out real-time detection on surrounding environment through adopting a multi-sensor fusion technology and transmits detected information to an obstacle data analysis processing module, the obstacle data analysis processing module which carries out environment structure sensing construction on the received information of the surrounding environment so as to determine an obstacle, and an obstacle avoidance decision-making module which determines an obstacle avoidance decision according to the output result of the obstacle data analysis processing module, so as to achieve obstacle avoidance of an unmanned aerial vehicle through the driving of power modules which is performed by a flight control system. According to the multi-sensor fusion-based autonomous obstacle avoidance unmanned aerial vehicle system and the control method of the invention, binocular machine vision systems are arranged around the body of the unmanned aerial vehicle, so that 3D space reconstruction can be realized; and an ultrasonic device and a millimeter wave radar in an advancing direction are used in cooperation, so that an obstacle avoidance method is more comprehensive. The system has the advantages of high real-time performance of obstacle detection, long visual detection distance and high resolution.

Multi-sensor fusion-based autonomous obstacle avoidance unmanned aerial vehicle system and control method

The invention discloses an identification method for transmission line tower inspection by an unmanned aerial vehicle, which comprises the steps of acquiring an image of a to-be-inspected transmission line; extracting a linear image in the image of the transmission line by means of an LSD algorithm, storing finally obtained lines in Line, and recording the start point of each line; counting the number of the lines and the lengths of the lines, filtering the line image according to the lengths of the lines; blocking the filtered line image; counting the number of tower blocks in the image of the to-be-inspected transmission line, and according to the number of the tower blocks and the distribution area of the tower blocks, determining whether the tower image contains the tower. The identification method is beneficial in that a quick identification technique for the transmission line tower can effectively realize positioning to the tower in the inspection image and lays basis for subsequent defect analysis. The identification method furthermore has functions of screening the image which is obtained in inspection, reducing the load in manual screening, and realizing wide application prospect.

Identification method for transmission line tower inspection by unmanned aerial vehicle

The invention discloses an unmanned aerial vehicle (UAV) test bed system for inspection and detection, comprising a bearing UAV end, a ground supporting seat, a transmission mechanism, and a weight measuring end. The bearing UAV end is used for bearing an object to be tested, and is connected with one end of the transmission mechanism through a connecting shaft. The other end of the transmission mechanism is provided with the weight measuring end. The weight measuring end is provided with a mass block. The ground supporting seat is arranged on the transmission mechanism. During test, the angular speed of rotation of the transmission mechanism is kept consistent, and the transmission mechanism always moves in a translational manner, so that the test bed system does parallel and synchronous movement in the process of movement, and flexible and barrier-free movement of the UAV is achieved. According to the invention, a parallel four-bar mechanism is adopted to make level for the tested UAV, and a weight at the end is changed and adjusted in real time according to the weight of the tested object. The test bed does not need to be fixed to the ground, and universal wheels are adopted to make movement and transportation convenient.

Unmanned aerial vehicle test bed system for inspection and detection

The invention discloses a control system and a control method for a heavy-weight hydraulic small boom According to the control system, a remote controller is communicated with an industrial personal computer through an optical fibre transmitting-receiving module; the industrial personal computer is connected with a signal processing module; an analogue quantity output by the signal processing module is connected with a plurality of hydraulic servo valves through a servo amplifier; an angle sensor is arranged on the small boom, and connected with the signal processing module through a sensor bundling system; instructions of the remote controller are sent to the industrial personal computer through the optical fibre transmitting-receiving module; and the industrial personal computer sends a control instruction and a switch driving instruction to the small boom through the signal processing module The self-designed control system for the heavy-weight hydraulic small boom, which is disclosed by the invention, replaces a human arm to finish a task of live replacement for cross arms and transformer overloads of a 10kV power distribution station through experimental verification

Fu Mengchao

Papers

Insulator identification method for unmanned aerial vehicle polling electric transmission line

Multi-sensor fusion-based autonomous obstacle avoidance unmanned aerial vehicle system and control method

Identification method for transmission line tower inspection by unmanned aerial vehicle

Unmanned aerial vehicle test bed system for inspection and detection

Control system and control method for heavy-weight hydraulic small boom