Local Adaptive Clustering Based Image Matching for Automatic Visual Identification
This work addresses label drift in industrial monitoring systems, presenting an incremental improvement over existing image matching techniques.
The paper tackled the problem of label drift in real-time automatic equipment labeling from surveillance videos by introducing a Local Adaptive Clustering (LAC) method, which effectively curtails label drift as demonstrated in experiments.
Monitoring cameras are extensively utilized in industrial production to monitor equipment running. With advancements in computer vision, device recognition using image features is viable. This paper presents a vision-assisted identification system that implements real-time automatic equipment labeling through image matching in surveillance videos. The system deploys the ORB algorithm to extract image features and the GMS algorithm to remove incorrect matching points. According to the principles of clustering and template locality, a method known as Local Adaptive Clustering (LAC) has been established to enhance label positioning. This method segments matching templates using the cluster center, which improves the efficiency and stability of labels. The experimental results demonstrate that LAC effectively curtails the label drift.