Three-dimensional reconstruction method based on convolution neural network

Abstract

The invention provides a three-dimensional reconstruction method based on a convolution neural network, belonging to the technical field of computer vision. Three-dimensional features are more accurate and retrieval accuracy is higher. Compared with the popular feature extraction network, the network learning ability of the method is stronger, and the feature information of the object point cloudextracted through the network is richer. The algorithm has good real-time performance, whether modeling, feature extraction, database retrieval or final model registration can be completed in a shorttime. Moreover, the accuracy of the network model proposed in this method is better than that of other models based on depth learning, which shows that the network structure can learn the data distribution rules directly from the three-dimensional point cloud. Compared with the traditional feature extraction method, the proposed method based on convolution neural network can significantly reduce the computational time, and the Euclidean distance retrieval algorithm can also improve the retrieval efficiency.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to a method for reconstructing a three-dimensional scene based on a convolutional neural network. Background technique [0002] Scene modeling has always been a research hotspot in the field of computer vision. High-precision 3D scene modeling is the prerequisite for the realization of technologies such as robot perception and virtual reality. 3D reconstruction generally includes three parts. First, use a hand-held camera to scan the target to be reconstructed from multiple perspectives, then perform feature extraction, matching, and camera pose estimation on the scanned multi-frame images, and finally complete the two-dimensional reconstruction through stereo vision technology. The mapping of pixels to three-dimensional coordinate points obtains the final reconstructed model. However, in the previous work, there were objective conditions such as mutual occlusio...

AI Technical Summary

Problems solved by technology

[0010] Patent In order to solve the technical bottlenecks of inaccurate, incomplete, poor abstraction ability and long time-consuming technical bottlenecks in traditional 3D scene reconstruction methods, a 3D reconstruction framework and software platform based on convolutional neural network is designed

Images