微信扫一扫

教师简介

当前位置: 首页 >> 师资队伍 >> 教师简介 >> 正文

项彬彬

文章出处: 发表时间:2026-03-04

项彬彬

 

邮箱:binbinxiang@hnu.edu.cn

个人简介

湖南大学人工智能与机器人学院助理教授,研究方向是三维LiDAR点云深度学习作为核心骨干先后参与了国家重点研发项目专项课题服务机器人云服务平台201712-202011月)、瑞士创新机构PCobject - Automatic object recognition in geospatial point clouds项目(20203-20226月,经费223.84万元)、挪威研究委员会SmartForest: Bringing Industry 4.0 to the Norwegian forest sector项目(202010-20289月,经费16380万元)和欧盟地平线项目SingleTree: Optimizing multifunctional forest-based value chains with single tree information and application of digital technologies20249-20288月,经费4169万元)。

在森林、城市等复杂场景的机载与地面激光点云分割研究领域提出了语义与实例分割的深度学习新方法,相关的研究成果已在Remote Sensing of EnvironmentIF=11.4)、ISPRS Journal of Photogrammetry and Remote SensingIF=12.2)、IEEE International Conference on Computer Vision等国际期刊与顶级会议上发表论文13篇,其中第一作者7篇,已授权发明专利2

长期研究方向是结合多模态信息(点云、图像、语言等),构建具有跨场景泛化能力的三维智能感知模型,包括但不局限于城市、森林、植物育种场景等,以及与具身智能结合的空间表示学习。

 

招生与培养理念

        目前招收硕士研究生、本科毕业设计学生、参与各类竞赛学生、大创项目学生,以及对科研有兴趣的科研助理。研究兴趣主要集中在3D计算机视觉 、激光点云 、多模态和空间理解等方向。

希望你(1)对科研有热情和自驱力,认真对待科研。只要你愿意认真投入,我会非常真诚地对待你的成长。如果你对科研有基本的自我要求,也愿意投入时间思考问题,我们会是一个很好的合作关系。2)对自己的未来有比较明确的目标(继续深造读博/出国/就业等)。我会根据你的目标制定不同培养路线,每周能保证给你一次固定指导时间,帮助你梳理研究思路,避免方向跑偏。AI领域发展迅速,我也会持续学习和更新自己的知识体系,尽可能亲自参与核心研究,与你一起在科研前线解决问题。

 

教育背景

2019.09-2024.02,苏黎世联邦理工(ETH Zurich),遥感与摄影测量,博士 

2016.09-2019.06,武汉大学,摄影测量与遥感,硕士

2012.09-2016.06,武汉大学,遥感科学与技术,学士

 

工作经历

2025.11-至今,湖南大学,人工智能与机器人学院,助理教授

2024.05-2025.11,挪威生物经济研究所(NIBIO),博士后研究员

 

已发表的学术论文

· Binbin Xiang*, Maciej Wielgosz, Stefano Puliti, Kamil Král, Martin Krůček, Azim Missarov, Rasmus Astrup. 2025. ForestFormer3D: a unified framework for end-to-end segmentation of forest LiDAR 3D point clouds. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025. (ICCV oral)

· Binbin Xiang*, Maciej Wielgosz, Theodora Kontogianni, Torben Peters, Stefano Puliti, Rasmus Astrup, Konrad Schindler. 2024. Automated forest inventory: analysis of high-density airborne LiDAR point clouds with 3D deep learning. Remote Sensing of Environment, 305: 114078.

· Binbin Xiang*, Yuanwen Yue, Torben Peters, Konrad Schindler. 2023. A review of panoptic segmentation for mobile mapping point clouds. ISPRS Journal of Photogrammetry & Remote Sensing, 203: 373-391.

· Binbin Xiang*, Torben Peters, Theodora Kontogianni, Frawa Vetterli, Stefano Puliti, Rasmus Astrup, Konrad Schindler. 2023. Towards accurate instance segmentation in large-scale LiDAR point clouds. ISPRS Geospatial Week 2023. (Best Workshop Paper Award)

· Binbin Xiang, Jingmin Tu, Jian Yao*, Li Li. 2019. A novel octree-based 3D fully convolutional neural network for point cloud classification in road environment. IEEE Transactions on Geoscience and Remote Sensing, 57(10): 7799-7818.

· Binbin Xiang, Jian Yao*, Xiaohu Lu, Li Li, Renping Xie, Jie Li. 2018. Segmentation-based classification for 3D point clouds in the road environment. International Journal of Remote Sensing, 39(19): 6182-6212.

· Binbin Xiang, Jian Yao*, Xiaohu Lu, Li Li, Renping Xie. 2017. Segmentation-based classification for 3D urban point clouds. Proceedings of the IEEE International Conference on Information and Automation, 172-177.

· Binbin Xiang, Xu Li, Min Zhang, Lifei Lu, Fa Li, Binru Zhao, Zhipeng Gui*. 2016. An extensible simulation framework for diagnosing the execution of the distributed geospatial web services. IEEE International Conference on Geoinformatics, 1-5.

· Maciej Wielgosz*, Stefano Puliti, Binbin Xiang, Konrad Schindler, Rasmus Astrup. 2024. SegmentAnyTree: A sensor and platform agnostic deep learning model for tree segmentation using laser scanning data. Remote Sensing of Environment, 313: 114367.

· Jingmin Tu, Jian Yao, Li Li*, Wenjie Zhao, Binbin Xiang. 2021. Extraction of street pole-like objects based on plane filtering from mobile LiDAR data. IEEE Transactions on Geoscience and Remote Sensing, 59(1): 749-768.

· Kai Chen, Jingmin Tu, Binbin Xiang, Li Li, Jian Yao*. 2018. Multiple combined constraints for image stitching. IEEE International Conference on Image Processing, 1253-1257.

· Li Li, Jian Yao*, Renping Xie, Menghan Xia, Binbin Xiang. 2017. Superpixel-based optimal seamline detection via graph cuts for panoramic images. Proceedings of the IEEE International Conference on Information and Automation, 1484-1489.

上一条:钟富强

下一条:刘康丞