利用激光雷达扫描的连续性，只处理变化区域，实现实时3D目标检测。
SSCATeR: Sparse Scatter-Based Convolution Algorithm with Temporal Data Recycling for Real-Time 3D Object Detection in LiDAR Point Clouds
- 通过滑动时间窗追踪点云变化，仅对变动区域进行卷积计算。
- 相比传统方法，处理时间减少6.61倍，精度无损失。
- 适合需要低延迟的自动驾驶感知系统使用。
本研究利用激光雷达扫描的连续运动特性，将目标检测重点集中在前后帧间点数据发生变化的区域。通过采用短步长滑动时间窗，并在迭代间存储卷积结果，实现对时序维度的数据复用，从而忽略未变化区域，显著减少每轮前向传播的卷积操作次数，同时保持精度。该数据复用机制引入了极强的稀疏性。为利用这种稀疏性，我们扩展了先前基于散射卷积的工作，提出一种带时序数据回收的稀疏散射卷积算法（SSCATeR）。该操作将输入激光雷达数据视为连续流，仅作用于点云中变化部分。实验表明，该方法输出的特征图与传统稀疏卷积技术完全一致，但网络计算效率大幅提升，处理时间最多降低6.61倍。
原文摘要 · Abstract (English)
This work leverages the continuous sweeping motion of LiDAR scanning to concentrate object detection efforts on specific regions that receive a change in point data from one frame to another. We achieve this by using a sliding time window with short strides and consider the temporal dimension by storing convolution results between passes. This allows us to ignore unchanged regions, significantly reducing the number of convolution operations per forward pass without sacrificing accuracy. This data reuse scheme introduces extreme sparsity to detection data. To exploit this sparsity, we extend our previous work on scatter-based convolutions to allow for data reuse, and as such propose Sparse Scatter-Based Convolution Algorithm with Temporal Data Recycling (SSCATeR). This operation treats incoming LiDAR data as a continuous stream and acts only on the changing parts of the point cloud. By doing so, we achieve the same results with as much as a 6.61-fold reduction in processing time. Our test results show that the feature maps output by our method are identical to those produced by traditional sparse convolution techniques, whilst greatly increasing the computational efficiency of the network.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。