论文标题
PST：植物植物的3D点云的植物分割变压器在吊舱阶段
PST: Plant segmentation transformer for 3D point clouds of rapeseed plants at the podding stage
论文作者
论文摘要
植物点云的分割以获得高精度的形态特征对于植物表型至关重要。尽管深度学习的快速发展促进了对植物点云进行分割的大量研究，但先前的研究主要集中于基于硬素化或基于下采样的方法，这些方法仅限于细分简单的植物器官。对具有高空间分辨率的复杂植物点云进行分割仍然具有挑战性。在这项研究中，我们提出了一个深度学习的网络分割变压器（PST），以实现由手持式激光扫描（HLS）获得的Rapeseed植物点云的语义和实例分割，并具有很高的空间分辨率，可以将微小的硅晶状分辨率表征为主要特征。 PST由：（i）动态体素特征编码器（DVFE）组成，以通过原始空间分辨率汇总点特征； （ii）双窗口设置注意力块以捕获上下文信息； （iii）一个密集的特征传播模块，以获得最终的致密点特征图。结果证明，PST和PST-PointGroup（PG）在语义和实例分段任务中取得了出色的性能。对于语义细分，平均值，平均精度，平均召回率，平均F1得分和PST的总体准确性为93.96％，97.29％，96.52％，96.88％和97.07％，达到9.62％，3.28％，4.8％，4.8％，4.25％和3.88％的速度相比，达到了7.62％的增长。例如，与原始PG相比，与原始PG相比，PST-PG的PST-PG达到MCOV，MWCOV，MPERC90和MREC90的PST-PG达到89.51％，89.85％，88.83％和82.53％，与原始PG相比，提高了2.93％，2.93％，2.21％，1.99％和5.9％。这项研究证明，基于深度学习的点云分割方法具有巨大的潜力，可以通过具有复杂的形态性状来解决密集的植物点云。
Segmentation of plant point clouds to obtain high-precise morphological traits is essential for plant phenotyping. Although the fast development of deep learning has boosted much research on segmentation of plant point clouds, previous studies mainly focus on the hard voxelization-based or down-sampling-based methods, which are limited to segmenting simple plant organs. Segmentation of complex plant point clouds with a high spatial resolution still remains challenging. In this study, we proposed a deep learning network plant segmentation transformer (PST) to achieve the semantic and instance segmentation of rapeseed plants point clouds acquired by handheld laser scanning (HLS) with the high spatial resolution, which can characterize the tiny siliques as the main traits targeted. PST is composed of: (i) a dynamic voxel feature encoder (DVFE) to aggregate the point features with the raw spatial resolution; (ii) the dual window sets attention blocks to capture the contextual information; and (iii) a dense feature propagation module to obtain the final dense point feature map. The results proved that PST and PST-PointGroup (PG) achieved superior performance in semantic and instance segmentation tasks. For the semantic segmentation, the mean IoU, mean Precision, mean Recall, mean F1-score, and overall accuracy of PST were 93.96%, 97.29%, 96.52%, 96.88%, and 97.07%, achieving an improvement of 7.62%, 3.28%, 4.8%, 4.25%, and 3.88% compared to the second-best state-of-the-art network PAConv. For instance segmentation, PST-PG reached 89.51%, 89.85%, 88.83% and 82.53% in mCov, mWCov, mPerc90, and mRec90, achieving an improvement of 2.93%, 2.21%, 1.99%, and 5.9% compared to the original PG. This study proves that the deep-learning-based point cloud segmentation method has a great potential for resolving dense plant point clouds with complex morphological traits.
