Research on Vision of Intelligent Car Based on Broad Learning System

The broad learning system (BLS) of intelligent vehicle in different target environments is studied in this article. First, this article provides with the target recognition image data to be trained and detected through the automated guided vehicle (AGV) mobile platform, which can grab the recognition image of different angles and backgrounds. In order to avoid the data generalization phenomenon, the dataset can be expanded by the data normalization and data enhancement. Second, the data are input into the shared convolution layer to extract the feature image and maintain the image. The parameters of image height, width, and channel number are invariable, and the new feature image is obtained by further extraction. Furthermore, the region proposal network (RPN) prefiltering algorithm based on hierarchical clustering is used to filter the objects in the candidate box to determine the region image corresponding to the feature image. Then, the feature images of different sizes input into region of interest (ROI) pooling are used to keep the size of the image in the ROI consistent. Finally, the normalized image is input into the classifier module to obtain the category of the target recognition image to be detected. Through the simulation experiments of different groups, it can be seen that the target recognition system proposed in this design can not only accurately detect the objects but also stably recognize the objects in different environments. The target recognition accuracy for the optimized system is about 95%.

Automated summary

This article studies the broad learning system (BLS) of intelligent vehicles in different target environments. The target recognition image data is provided and training and detection are performed using an automated guided vehicle (AGV) mobile platform to capture recognition images from various angles and backgrounds. Data normalization and data enhancement are used to expand the dataset and avoid data generalization. The shared convolution layer is employed to extract feature images, and region proposal network (RPN) prefiltering algorithm is used to filter objects in the candidate box. The system achieves stable target recognition in different environmental conditions with an accuracy of about 95%.