Exploiting Label Uncertainty for Enhanced 3D Object Detection From Point Clouds
Exploiting Label Uncertainty for Enhanced 3D Object Detection From Point Clouds
复制标题
DOI：
10.1109/tits.2023.3334873
复制
发表时间：
2024-06
影响因子：
8.5
通讯作者：
Yan Sun;Bin Lu;Yonghuai Liu;Zhenyu Yang;Ardhendu Behera;Ran Song;Hejin Yuan;Haiyan Jiang
中科院分区：
文献类型：
--
作者：
Yan Sun;Bin Lu;Yonghuai Liu;Zhenyu Yang;Ardhendu Behera;Ran Song;Hejin Yuan;Haiyan Jiang
从LiDAR点云中准确检测物体对于自动驾驶和环境建模至关重要。然而，由于遮挡、稀疏和截断而导致的地面真实标签的不确定性会阻碍模型训练和性能。本文介绍了两种解决这些问题的策略：1）软回归损失（SoRL）和2）离散量化采样（DQS）。SoRL利用高斯分布进行对象预测，基于这些分布中的地面真实标签的概率来测量不确定性。该方法有效地解决了对象位置和方向的偏差。同时，DQS引入了不确定度分数用于动态样本选择，旨在改进回归阳性样本的质量。在此基础上，我们设计了一个轻量级的多阶段目标检测框架。值得注意的是，这些模块可以增强现有的3D对象检测方法，而不会显著影响推理速度。在基准数据集上的实验表明了该方法的有效性，特别是对于稀疏点云中的汽车。
Accurate detection of objects from LiDAR point clouds is crucial for autonomous driving and environment modeling. However, uncertainties in ground truth labels due to occlusions, sparsity, and truncation can hinder model training and performance. This paper introduces two strategies to address these issues: 1) Soft Regression Loss (SoRL) and 2) Discrete Quantization Sampling (DQS). SoRL utilizes Gaussian distributions for object predictions, measuring uncertainty based on the probability of ground truth labels within these distributions. This method effectively accounts for deviations in object location and orientation. Meanwhile, DQS introduces uncertainty scores for dynamic sample selection, aiming to refine the quality of positive samples for regression. Based on the proposed modules, we design a lightweight multi-stage object detection framework. Notably, these modules can enhance existing 3D object detection methods without affecting significantly inference speeds. Experiments over benchmark datasets show the effectiveness of our method, especially for cars in sparse point clouds.