In order to eliminate driving dangers caused by tire surface bubbles, the detection method of bubble defects on tire surfaces based on line lasers and machine vision is studied. Since it is difficult to recognize tire surfaces directly through images, line laser scanning is used to obtain tire images. The filtering method and morphology method are combined to preprocess these images. The gray centroid method is adopted to extract the center of the laser stripe, and then the algorithm to determine the positions of bubble defects on tire surfaces is proposed. According to the geometric characteristics of tire bubbles, the coordinates of starting points, ending points, and rough positions of vertices are determined. Then, the ordinates of the laser center with sub-pixel accuracy near bubble vertices are discretely magnified. The mask made of Gaussian function is convoluted with the magnified region, and the maximum value is obtained. Furthermore, the position of bubble vertices can be accurately extracted. The denoising effects of different methods for images are compared through experiments, and different positions of bubbles are detected. Experimental results show that the detection accuracy of this method is up to 93%, which is much higher than other methods. Experiments verify that the proposed method is effective for detecting tire surface bubbles.

In order to eliminate the hidden dangers caused by tire bubble defects, considering that the two-dimensional technology is sensitive to light, the 3D point cloud technology is used to obtain the tire surface morphology. This paper proposes a 3D point cloud network model named PointVotes, a point based target detection method. The designed structural framework includes: the fusion sampling layer, the voting layer and the proposal refinement layer. By observing the spatial characteristics of the detected target, a new point sampling method named C-farthest point sampling (C-FPS) is proposed. Combining with the fusion sampling strategy, the FPS and the C-FPS are sampled in a certain proportion. It solves the problem that the proposal box cannot be generated due to less available prospect information when generating suggestions for small targets. The network model uses Set Abstraction layers in multiple PointNet++ to extract features, arranges and combines features of different scales, forms high-dimensional features of points and votes, judges whether there are bubble defects through classification, and then generates proposals and regression to the prediction frame. Experiment results show that * Corresponding author PointVotes 1447 the mean average precision of the model can reach 82.8 % with a detection time of 0.12 s.

No abstract