The current state-of-the-art vehicle 3D surround view system can realistically display the 3D surround environment of the vehicle body, but it still causes display distortion of the 3D objects close to the vehicle body, greatly decreasing the display effect and the practicality. To solve this problem, an enhanced vehicle 3D surround view synthesis method was proposed. First, the You Only Look Once v4(YOLOv4) network was used to detect the positions of the vehicles and pedestrians in images. Then, based on the coordinate dimension-increasing inverse mapping, the positions of the detected objects were mapped to the world coordinate system with dimension increased. Finally, the 3D models were placed and rendered on the corresponding inverse mapping positions to replace 3D objects with distortion, so as to provide effective position information of the surround objects. Experimental results show that the enhanced vehicle 3D surround view generated by proposed method has good real-time performance and display effect, and can effectively solve the display defects of the current vehicle 3D surround view.

Focusing on the issue that most of existing approaches need sentiment lexicon annotated manually to extract sentiment features, a sentiment analysis method of product reviews based on Contrastive Divergence-Restricted Boltzmann Machine (CD-RBM) deep learning was proposed. Firstly, product reviews were preprocessed and represented as vectors using the bag-of-words. Secondly, CD-RBM was used to extract the sentiment features from product review vectors. Finally, the sentiment features were classified with Support Vector Machine (SVM) as the sentiment analysis result. Without any manually pre-defined sentiment lexicon, CD-RBM can automatically obtain the sentiment features of higher semantic relevance; combining with SVM, the correctness of the sentiment analysis result is guaranteed. The optimum training period of RBM was experimentally determined as 10. In the comparison experiments with methods including RBM, SVM, PCA+SVM and RBM+SVM, the combination method of CD-RBM feature extraction and SVM classification shows the best precision and best F-measure, as well as better recall.