PST：用于结荚期油菜植株3D点云的植株分割Transformer
PST: Plant segmentation transformer for 3D point clouds of rapeseed plants at the podding stage
AI总结：
提出PST网络，通过DVFE、双窗口集注意力和稠密特征传播实现高分辨率油菜点云语义与实例分割，性能显著优于PAConv和PG。
摘要：
分割植株点云以获取高精度形态性状对于植物表型分析至关重要。尽管深度学习的快速发展推动了大量关于植株点云分割的研究，但以往研究主要集中于基于硬体素化或基于下采样的方法，这些方法局限于分割简单的植物器官。以高空间分辨率分割复杂植株点云仍然具有挑战性。本研究提出了一个深度学习网络植株分割Transformer（PST），以实现由手持激光扫描（HLS）获取的高空间分辨率油菜植株点云的语义分割和实例分割，该网络能够表征作为目标主要性状的细小角果。PST由以下部分组成：（i）动态体素特征编码器（DVFE），以原始空间分辨率聚合点特征；（ii）双窗口集注意力块，用于捕获上下文信息；以及（iii）稠密特征传播模块，用于获得最终的稠密点特征图。结果证明，PST和PST-PointGroup（PG）在语义分割和实例分割任务中取得了优越性能。在语义分割方面，PST的平均IoU、平均精确率、平均召回率、平均F1分数和总体准确率分别为93.96%、97.29%、96.52%、96.88%和97.07%，与排名第二的最先进网络PAConv相比，分别提升了7.62%、3.28%、4.8%、4.25%和3.88%。在实例分割方面，PST-PG在mCov、mWCov、mPerc90和mRec90上分别达到89.51%、89.85%、88.83%和82.53%，与原始PG相比分别提升2.93%、2.21%、1.99%和5.9%。本研究证明，基于深度学习的点云分割方法在解决具有复杂形态性状的稠密植株点云方面具有巨大潜力。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
