计算机工程与应用 ›› 2024, Vol. 60 ›› Issue (10): 132-139.DOI: 10.3778/j.issn.1002-8331.2301-0129

• 模式识别与人工智能 • 上一篇    下一篇

使用中心预测-聚类的3D箱体实例分割方法

杨雨桐,和红杰   

  1. 1.西南交通大学 计算机与人工智能学院,成都 611756
    2.西南交通大学 信息科学与技术学院,成都 611756
  • 出版日期:2024-05-15 发布日期:2024-05-15

3D Box Instance Segmentation Method Using Center Prediction-Clustering

YANG Yutong, HE Hongjie   

  1. 1.School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611756, China
    2.School of Information Science and Technology, Southwest Jiaotong University, Chengdu 611756, China
  • Online:2024-05-15 Published:2024-05-15

摘要: 随着深度学习技术在工业领域的大量部署,应用于运输、装卸、包装、分拣等环节的自动化系统成为仓储物流行业的研究热点。针对机器人箱体拆垛场景提出一个点云中心预测-聚类网络(center prediction-clustering network,CPCN),对箱体垛进行实例分割,并计算每个箱体的上表面中心坐标。CPCN在传统的语义-实例联合分割结构的基础上,为实例分割分支设计了中心预测模块和中心强化模块。中心预测模块帮助定位实例中心以避免中心点分割错误,中心强化模块令属于同一实例的点在特征空间中向中心聚集,二者有效增强了实例特征的辨识能力。在实例特征处理部分设计的中心-实例聚类方法直接对实例特征进行距离度量来计算实例标签,大幅减少了计算时间。在箱体数据集上进行的实验表明,与现有方法相比CPCN在实例分割任务中的平均精确率最低提高了0.7个百分点,最高提高了17.2个百分点,预测实例中心的准确率达到94.4%,中心偏移量低至13.70?mm,且推理速度快于同类型的联合分割网络,对于箱体拆垛任务更有针对性,具有良好的应用价值。

关键词: 3D点云, 实例分割, 箱体拆垛, 中心预测, 聚类

Abstract: With the extensive deployment of deep learning technology in industry, automated systems applied in transportation, loading and unloading, packaging, sorting and other links have become a research hotspot in warehousing and logistics industry. Aiming at robot box unstacking scene, a point cloud center prediction-clustering network (CPCN) is proposed based on the deep learning method, which can segment the box stack and calculate the center coordinates of the upper surface of each box. Based on the traditional semantic-instance joint segmentation structure, CPCN designs a central prediction module and a central reinforcement module for the instance segmentation branch. The central prediction module avoids the error of central point segmentation by directly locating the instance center, and the central reinforcement module makes the points belonging to the same instance converge to the center in the feature space, both of which effectively enhance the identification ability of the instance features. In addition, the central-instance clustering method designed in the part of instance feature processing calculates the instance label by directly measuring the distance of the instance feature, which greatly reduces the computing time. Experiments on the box data set show that compared with the existing methods, the average accuracy of CPCN is improved by 0.7 percentage points at the lowest and 17.2 percentage points at the highest, the accuracy of instance center reaches 94.4%, the center offset is as low as 13.70?mm, and the reasoning speed is faster than that of the same type of joint division network. CPCN is more targeted for the box instance segmentation and has good application value.

Key words: 3D point cloud, instance segmentation, box unstacking, center prediction, clustering