Neural Network Spatial Position Feature Map for Battery Tab Defect Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing defect detection methods in industrial production processes, particularly for position-sensitive defects in products like power battery tabs and electrode plates, suffer from low detection efficiency due to the need for convolutional neural networks combined with logical post-processing.
Innovation Solution
The proposed method modifies the neural network structure for defect detection to enhance sensitivity to spatial positions by extracting a feature map of spatial position coordinate information, thereby improving the accuracy of detecting specific defect types.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If convolutional neural network detection is combined with logical post-processing to detect position-sensitive defects, then detection accuracy is improved, but detection efficiency deteriorates
Solution Approach 1:
The patent merges the defect detection function and spatial position sensitivity into a single neural network model. By integrating spatial position coordinate information directly into the feature map during the detection process, the system eliminates the need for separate logical post-processing steps, thereby maintaining high detection accuracy while significantly improving detection efficiency.
Solution Approach 2:
The patent introduces spatial position coordinate information as an additional dimension in the feature map. This dimensional enhancement allows the neural network to inherently understand spatial relationships and position sensitivity, enabling accurate detection of position-sensitive defects without requiring external logical processing, thus resolving the contradiction between accuracy and efficiency.
2Measurement precision
If spatial position sensitivity is enhanced in the neural network, then accuracy of detecting specific defect types is improved, but network complexity increases
Solution Approach 1:
The patent performs preliminary action by pre-processing the input image to extract spatial position coordinate information before feeding it into the neural network. This spatial information is then integrated into the feature map during the detection process, allowing the network to inherently understand spatial relationships without requiring complex architectural modifications, thus enhancing detection accuracy while controlling network complexity.
Data Source
AI summary
Provided are a defect detection method and apparatus, and a computer-readable storage medium. Specifically, the method includes: obtaining a to-be-detected image; obtaining a feature map of the to-be-detected image based on the to-be-detected image, where the feature map of the to-be-detected image includes a feature map of spatial position coordinate information; and performing defect detection on the to-be-detected image based on the feature map of the to-be-detected image. By modifying a neural network structure of defect detection and extracting the feature map of spatial position coordinate information during the detection, this application makes the neural network for use of defect detection sensitive to a spatial position, thereby enhancing sensitivity of a detection neural network to the spatial position, and in turn, increasing accuracy of detecting some specific defect types by the detection neural network, and increasing accuracy of defect detection.