Real-time detection method for state of split knife switch
A real-time detection, split-type technology, applied in the field of image recognition, can solve the problem of low real-time detection accuracy of the knife switch status
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0045] Example 1: Such as figure 1 with figure 2 The method for real-time detection of the state of the split knife switch shown includes: collecting real-time monitoring video of the split knife switch, acquiring each frame of the video and establishing the model of the split knife switch based on any frame image The boundary line model of the knife arm is saved as a model file, and the midpoint and center line of the knife arm are calculated according to the model file; sample images of the split knife arm are obtained through various methods, and the sample images are obtained by deep learning. Train the model, use the training model to detect the first frame of the video, obtain all the knife gate area and the state of the knife in the first frame of image, and combine the model file to locate the knife in the first frame of image; according to the above positioning As a result, perform edge detection on the first frame of the video, obtain the edge line set, and calculate ...
Example Embodiment
[0047] Example 2: On the basis of Example 1, the center line is used to distinguish the updated edge line set from left to right. After obtaining the left knife arm edge line set and the right knife arm edge line set respectively, the weight is assigned, and the weighted The left knife arm edge line set and the right knife arm edge line set are paired symmetrically.
[0048] Embodiment 2 assigns weights to the edge line set of the left knife arm and the edge line set of the right knife arm on the basis of Example 1, and identifies the knife area based on the positioning of the knife area in the first frame of image. Then, the identified edge lines of the knife switch are first distributed through weights and then symmetrically paired to determine the final left and right knife arm edge lines of the knife switch. In the same way, when processing each frame of image, the knife area is identified based on the positioning of the knife area in the frame of image, and then the identifi...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap