Research on 3D Object Recognition Based on Feature Level Fusion

摘要

Target recognition has always been a hot research topic in computer image and pattern recognition. This paper proposes a target recognition method based on feature layer fusion. Using the 3D CAD model ModelNet as the object model to be identified, the features are extracted from the point cloud data and the multi-view 2D image of the model through the two-channel convolutional neural network (CNN), and the network fusion is completed in the feature layer. Representative three-dimensional features to complete the classification of objects. The experimental results show that the proposed method effectively improves the accuracy of object recognition.