Domain self-adaptive equipment operation inspection system and method
A domain-adaptive, equipment-based technology, applied in the field of domain-adaptive equipment inspection systems, can solve problems such as infeasibility, poor model performance, and expensive training samples
Active Publication Date: 2021-01-05
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 10 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Unfortunately, it is expensive and infeasible to collect enough annotated training samples from different geographical scenes or different weather
At the same time, different regional scene backgrounds and under rainy or foggy conditions, the edge and color features brought about by light, rain streaks, fog, and blur greatly cause significant differences between the feature distributions of inspection images under different weather conditions. Domain differences, such domain differences or domain shifts will cause poor performance of the model in the new domain, that is, the inspection model trained on sunny weather samples is difficult to generalize to cross-regional or other weather condition inspection tasks
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0056] In this embodiment, a domain adaptive equipment inspection system, such as figure 1 As shown, it includes an image acquisition processing module, a weather condition classification module, and a domain adaptive equipment inspection module;
[0057] The domain adaptive equipment inspection module is used to construct and preset a domain adaptive equipment inspection model. The domain adaptive equipment inspection model includes a layered feature extraction module, a fusion feature multi-alignment module, a region of interest generation module, a detection device and loss calculation module;
[0058] The image acquisition and processing module is used to acquire the transmission line equipment inspection image and preprocess the inspection image, and send the preprocessed inspection image to the weather condition classification module and the domain adaptive feature extraction module;
[0059]The weather condition classification module is used to construct and preset a w...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a domain self-adaptive equipment operation inspection system and method. An image acquisition processing module is used for acquiring a to-be-detected inspection image of a power transmission line and preprocessing the image; the to-be-detected inspection image is input into a preset weather condition classification model to identify weather conditions to which the to-be-detected inspection image belongs, and a weather condition classification result is obtained; a corresponding preset domain self-adaptive equipment operation inspection model is selected according to the weather condition classification result; and the to-be-detected inspection image is input into a preset domain self-adaptive equipment operation inspection model to obtain a detection result of theto-be-detected inspection image, wherein the detection result comprises one or a combination of equipment category, working condition and position information of a detection object in the to-be-detected inspection image. According to the invention, the to-be-detected sample of the high-voltage transmission line domain self-adaptive equipment operation detection system is not restricted by sample annotation and regional or weather conditions, and the equipment operation detection result of the target domain in the domain self-adaptive scene has the same detection performance as that of the source domain.
Description
technical field [0001] The invention relates to the technical fields of artificial intelligence, information processing technology, and grid operation inspection and maintenance, and in particular to a domain adaptive device operation inspection system and method. Background technique [0002] In recent years, artificial intelligence has played an increasingly important role in the field of power grid inspection and maintenance technology. The high-voltage transmission line equipment inspection system based on deep learning conducts supervised training on massively labeled inspection image data, which becomes a necessary means for power grid inspection, improves detection accuracy, and shortens fault handling time. [0003] In a specific high-voltage transmission line equipment inspection system for power grid operation inspection and maintenance, the inspection image to be detected is collected by the terminal equipment, input to the convolutional neural network for feature...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06Q10/00G06Q50/06G06K9/62G06N3/04G07C1/20
CPCG06Q10/20G06Q50/06G07C1/20G06N3/045G06F18/253Y04S10/50G05B23/0221G05B2219/2639G06V10/806G06V20/17G06V10/454G06V10/30G06N3/08G05B19/042
Inventor 周智恒张鹏宇黄俊楚李波
Owner SOUTH CHINA UNIV OF TECH