3D Target Detection Incorporating Point Cloud Columnarization and Attention Mechanisms in Intelligent Driving Systems

Abstract

One crucial problem with intelligent driving systems is 3D target detection. Point cloud data has several uses in the realm of perception and is a vital source of information. This study focuses on the problems of low TD accuracy and slow processing speed in complex scenes. Based on the PointPillars algorithm, a point cloud columnar network structure is designed. At the same time, the Swin Transformer algorithm is combined to further fully utilize the spatial information of point cloud data for more accurate detection and localization of 3D targets. The results indicated that the improved model predicted frames and real frames had smaller offset angles and smaller errors, and fit better compared to the PointPillars algorithm. The memory usage of the improved model graphics card was 1253MB, and the running speed was 0.033s, compared with the PointPillars algorithm the memory usage of the graphics card was reduced by 14MB, and the running speed was improved by 0.003s. The first 0.03s of the target detection of the PointPillars model had the most deviation, and the deviation was generally 0.03m. The reason was that PointPillars algorithm is not capable of handling occlusion, small or dense targets well enough to produce errors. The detection error distribution of the improved model was concentrated around 0.01s, and the average deviation was 0.018m, which reduced the deviation by nearly 55.7% compared to the PointPillars model. The enhanced technique enhances the driving system’s safety and perception capacity while precisely identifying target items on the road. This is of great significance to promote the development and practical application of intelligent driving systems.

Keywords

• Intelligent driving
• point cloud columnarization
• attention mechanism
• 3D target detection
• swin transformer