School of Information Science and Engineering, Xinjiang University, Urumqi 830046, China.
Sensors (Basel). 2022 May 23;22(10):3935. doi: 10.3390/s22103935.
Three-dimensional object detection in the point cloud can provide more accurate object data for autonomous driving. In this paper, we propose a method named MA-MFFC that uses an attention mechanism and a multi-scale feature fusion network with ConvNeXt module to improve the accuracy of object detection. The multi-attention (MA) module contains point-channel attention and voxel attention, which are used in voxelization and 3D backbone. By considering the point-wise and channel-wise, the attention mechanism enhances the information of key points in voxels, suppresses background point clouds in voxelization, and improves the robustness of the network. The voxel attention module is used in the 3D backbone to obtain more robust and discriminative voxel features. The MFFC module contains the multi-scale feature fusion network and the ConvNeXt module; the multi-scale feature fusion network can extract rich feature information and improve the detection accuracy, and the convolutional layer is replaced with the ConvNeXt module to enhance the feature extraction capability of the network. The experimental results show that the average accuracy is 64.60% for pedestrians and 80.92% for cyclists on the KITTI dataset, which is 1.33% and 2.1% higher, respectively, compared with the baseline network, enabling more accurate detection and localization of more difficult objects.
点云中的三维目标检测可为自动驾驶提供更准确的目标数据。本文提出了一种名为 MA-MFFC 的方法，它使用注意力机制和具有 ConvNeXt 模块的多尺度特征融合网络来提高目标检测的准确性。多注意力（MA）模块包含点通道注意力和体素注意力，用于体素化和 3D 骨干网络。通过考虑点和通道，可以增强体素中关键点的信息，抑制体素化中的背景点云，提高网络的鲁棒性。体素注意力模块用于 3D 骨干网络中，以获得更稳健和有区别的体素特征。MFFC 模块包含多尺度特征融合网络和 ConvNeXt 模块；多尺度特征融合网络可以提取丰富的特征信息，提高检测精度，并用 ConvNeXt 模块替换卷积层，增强网络的特征提取能力。实验结果表明，在 KITTI 数据集上，行人的平均准确率为 64.60%，自行车的平均准确率为 80.92%，分别比基线网络提高了 1.33%和 2.1%，能够更准确地检测和定位更困难的目标。
