Research on Visual Multiple-Object Tracking of Automobile Fastening Buckle
The production of auto parts requires workers to visually check whether the car fastening buckle is missing.This manual method is inefficient.To solve this problem,the space and channel attention mechanism is applied to YOLOv3-tiny net-work,which uses K-Means clustering to find the best Anchor Box.This algorithm has significantly improved detection accuracy in comparison with original YOLOv3 algorithm,and it's speed has increased by 3 times.Finally,the Lucas-Kanade optical flow method and the Delay-Precision mechanism are used to achieve the tracking and recognition of the car fastening buckle.In several video sequence experiments,the MOTA(Multiple-Object Tracking Accuracy)of this algorithm is about(3.7～7.5)％higher than other algorithms.In 200 experiments,the recognition accuracy of automotive plastic components and fastening buck-les reaches 100％.
NETL
NSTL
万方数据
维普
