Laser radar 3D real-time target detection method fusing multi-frame time sequence point cloud

Abstract

The invention discloses a laser radar 3D real-time target detection method fusing multi-frame time sequence point cloud. Complementing the known data set which contains the continuous frame point cloud and is incompletely labeled by the large-occlusion target by using a projection labeling complementing method; an MADet network structure is constructed; performing registration and voxelization onthe multiple frames of time sequence point clouds to generate multiple frames of aerial views; inputting the multiple frames of aerial views into a feature extraction module to generate multiple frames of initial feature maps; generating corresponding feature description for the multiple frames of initial feature maps, calculating a feature weight map, and performing weighted fusion to obtain a fused feature map; and fusing the multi-scale features of the fused feature map by using the feature pyramid, and returning the position, size and orientation of the target on the final feature map. According to the method, the problem of data sparseness of single-frame point cloud can be effectively solved, high accuracy is obtained in target detection under severe shielding and long distance, theprecision higher than that of single-frame detection is achieved, the network structure is simplified, the calculation cost is low, and the real-time performance is high.

Description

technical field [0001] The invention relates to a laser radar target detection method in the technical field of target detection, in particular to a laser radar 3D real-time target detection method which fuses multi-frame time series point clouds. Background technique [0002] Target detection refers to finding all existing objects in a perceivable environment and returning their size and position information. It is a vital part of the safe operation of complex systems such as unmanned driving and autonomous robots. Convolutional neural networks have achieved great progress in the field of image-based 2D object detection. These deep networks use 2D convolution, pooling, full connection and other operations to extract higher-level semantic information in the picture and better understand the content of the picture. Compared with traditional methods, the effect is remarkable, and it has quickly become the mainstream method in the field of target detection. But image-based 2D ...

AI Technical Summary

Problems solved by technology

The above methods need to use segmentation methods or point cloud layer alignment, which introduce a lot of additional computing requirements, weak real-time performance and low detection accuracy

Images