论文标题
在自动驾驶中利用不确定性进行深度多模式对象检测
Leveraging Uncertainties for Deep Multi-modal Object Detection in Autonomous Driving
论文作者
论文摘要
这项工作提出了一个概率的深神经网络，该网络结合了激光点云和RGB摄像机图像，以实现稳健，准确的3D对象检测。我们在分类和回归任务中明确对不确定性进行建模，并利用不确定性通过采样机制来训练融合网络。我们在三个数据集上验证我们的方法具有挑战性的现实驾驶场景。实验结果表明，预测的不确定性反映了复杂的环境不确定性，就像人类专家在标记对象的困难一样。结果还表明，与基线方法相比，我们的方法一致地提高了高达7％的平均精度。当传感器在时间上错位时，采样方法将平均精度提高了20％，显示出对噪声传感器输入的高鲁棒性。
This work presents a probabilistic deep neural network that combines LiDAR point clouds and RGB camera images for robust, accurate 3D object detection. We explicitly model uncertainties in the classification and regression tasks, and leverage uncertainties to train the fusion network via a sampling mechanism. We validate our method on three datasets with challenging real-world driving scenarios. Experimental results show that the predicted uncertainties reflect complex environmental uncertainty like difficulties of a human expert to label objects. The results also show that our method consistently improves the Average Precision by up to 7% compared to the baseline method. When sensors are temporally misaligned, the sampling method improves the Average Precision by up to 20%, showing its high robustness against noisy sensor inputs.
