王 鑫特聘副研究员 Address: Institute of Photogrammetry and Remote Sensing, WuHan University, LuoYu Road 129, 430072, Wuhan, China; 武汉大学 信息学部2号楼 324室 Email: xwang@sgg.whu.edu.cn PS:个人兴趣爱好 架子鼓,有想组乐队的同学欢迎联系,一起ROCK!

学习(Education

·        本科阶段(Bachelor)2009.09 – 2013.06 武汉大学 (Wuhan Uni.) 测绘学院 (School of Geodesy and Geomatics) 测绘工程 (Geomatics Engineering)

·        硕士阶段(Master)2013.09 – 2016.06 武汉大学 (Wuhan Uni.) 测绘学院 (School of Geodesy and Geomatics) 大地测量与测量工程 (Geodesy and Geomatics Engineering)

   2016.05 经武汉大学测绘学院推荐 获得国家留学基金委公派德国名额

·        博士阶段(PhD Candidate): 2016.10 – 2021.05 德国汉诺威大学 摄影测量与地理信息研究所 (Institute of Photogrammetry and GeoInformation, Leibniz University Hannover, Germany)
导师: Prof. Dr.-Ing. habil. Christian Heipke (前任国际摄影测量与遥感协会主席, ISPRS President, 2016-2022).
博士研究课题(PhD Topic: Time and Robustness efficient method of image orientation for large scale of ordered and unordered images. More information can be found at www.ipi.uni-hannover.de/de/wang/, https://www.researchgate.net/profile/Xin-Wang-305

 

工作(Working

·   2019.01-2019.03, visiting researcherInstitute of computer graphic and Vision, TU Graz & Vexcel Imaging GmbH(国际最领先摄影测量公司之一,2006年曾被微软收购), 格拉茨 奥地利 访学 (co-supervisor: Dr. Michael Gruber, chief Photogrammetry Scientist)

·    From 2021.10 -, 武汉大学 (Wuhan Uni.) 测绘学院 (School of Geodesy and Geomatics) 摄影测量与遥感研究所 (Institute of Photogrammetry and Remote Sensing) 特聘副研究员 (Distinguished Associate Research Fellow).

主要获奖 (Awards):

   夏坚白优秀学生奖 二等奖 2013

   研究生国家奖学金 2015

   ASPRS (美国摄影测量与遥感协会) ESRI Awards for Best Scientific Paper in GIS  First Place  2020

   入选湖北省“百人计划  2022

   入选武汉市“英才”计划  2023


科研项目 (Research Projects):

·          《顾及空间三维信息隐私安全的影像定向技术方法研究》湖北省自然基金青年项目2023

·          ISPRS Scientific Initiatives 2023

·          《联合三元CNN与孪生MLP的大集合无序影像关联图快速稳健生成方法研究》 国家自然基金青年项目   2024

 

主要研究方向 (Research Interests):

   深度学习在传统摄影测量中的应用 Deep learning methods applied in traditional photogrammetry

   集合无序影像(众源影像数据)快速匹配(随机kd森林, 词袋树, 基于深度学习影像相似性计算)Efficient Image Matching for large unorder image dataset Such as, Crowdsourced Images

   快速且高鲁棒的影像定向算法研究(基于全局定向策略提高时间效率, 相对定向粗差检测以增强鲁棒性)Fast and Robust Image orientation

   高性能光束法平差研究(基于GPU技术的大型线性方程系统求解;针对大数据集的分布式光束法平差)Efficient Bundle Adjustment by integrating GPUs

   无人机及近景的实时定位和地图生成(SLAM)方法研究(单目和双目关键算法研究, 多源传感器融合算法)SLAM for UAV and Close-ranging applications

·   

论文 (Publications):

  Peer-reviewed Journals

Y Yue, Z Zhan, X Wang* (2023). Single-point Least Square Matching Embedded Method for Improving Visual SLAM. IEEE Sensors Journal, 23(14):16176-16188. (SCI, top)

Q B Hou, R Xia, J Zhang, Y Feng, Z Zhan, X Wang*(2023). Learning visual overlapping image pairs for SfM via CNN fine-tuning with photogrammetric geometry information. International Journal of Applied Earth Observation and Geoinformation,116, 103162. (SCI, top)

Ding J, Zhang J, Zhan Z, Tang X,Wang X.(2022). A Precision efficient method for collapsed building detection in post-earthquake UAV images based on the improved NMS Algorithm and Faster R-CNN. Remote Sensing,14,663. (SCI)

X Wang, T Xiao, Y Kasten. (2021). A Hybrid SfM method for synchronously estimating global rotations and global translations. ISPRS Journal of Photogrammetry and Remote sensing, 174:35-55. (SCI, top, impact factor: 8.979)

T Xiao, X Wang, F Deng, C Heipke. (2021). Sequential Inference in Structure from Motion for the elimination of Relative Orientations Stemming from Repetitive Structure. PFG-Journal of Photogrammetry, Remote Sensing and Geoinformation Science, 1-17. (SCI)

X Wang, C Heipke. (2020). An improved method of Refining Relative Orientations in Global Structure from Motion with a Focus on Repetitive Structure and Very Short Baselines. Photogrammetric Engineering & Remote Sensing, 85(5):299-315. (SCI)

X Wang, F Rottensteiner, C Heipke. (2019). Structure from Motion for Ordered and Unordered image sets based on random k-d forests and global pose estimation. ISPRS Journal of Photogrammetry and Remote sensing, 147: 19-41. (SCI, top, impact factor: 8.979)

X Wang, F Rottensteiner, C Heipke. (2019). Robust Structure from Motion Based on Relative Rotations and Tie Points. Photogrammetric Engineering & Remote Sensing, 85(196):347-359. (SCI)

Z Zhan, C Wang, X Wang, Y Liu. (2018). Optimization of Incremental Structure from motion combining a random kd forest and pHash for unordered images in a complex scene. Journal of Electronic Imaging, 27(1): 013024. (SCI)

Z Zhan, X Wang, M Wei. (2015). Fast method of constructing image correlations to build a free network based on image multivocabulary trees. Journal of Electronic Imaging, 24(3):00329. (SCI)

  Peer-reviewed Conference Publications

 

H Zhan, Y F YU, Y W XU, Q B Hou, R Xia, X Wang*, Y Feng, Z Q Zhan, M L Li, M Gruber, R Hänsch, C Heipke. (2023). BEDOI: BENCHMARKS FOR DETERMINING OVERLAPPING IMAGES WITH PHOTOGRAMMETRIC INFORMATION. ISPRS Arch. Photogramm. Remote Sens. Spatial Inf. Sci., GSW 2023, Egypt, Cairo. (Oral)

Z R Xiong, ZQ Zhan, X Wang. (2022). POSITION-SENSITIVE ATTENTION BASED ON FULLY CONVOLUTIONAL NEURAL NETWORKS FOR LAND COVER CLASSIFICATION. ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-3-2022, 281–288. (Oral)

X. Tang, X. Huang, Z. Xiong, X. Wang*, and Z. Zhan. (2022). AN ADAPTIVE SUPERPIXELS FOR VEGETATION DETECTION ON HIGH RESOLUTION IMAGES BASED ON MLP. ISPRS Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B3-2022, 187–195. (Oral)

R. Xia, K. Jiang, X. Wang*, and Z. Zhan. (2022). STRUCTURAL LINE FEATURE SELECTION FOR IMPROVING INDOOR VISUAL SLAM. ISPRS. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B4-2022, 327334.

Z. Wang, Z. Zhan, G. Zhou, and X. Wang. (2022). AN EFFICIENT HIERARCHICAL IMAGE RETRIEVAL METHOD FOR LARGE SET OF IMAGES USING LEARNING-BASED GLOBAL AND LOCAL IMAGE FEATURES. ISPRS. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2022, 649–656.

X Wang, T Xiao, Y Kasten. (2020). A Hybrid global image orientation method for simultaneously estimating global rotations and global translations. ISPRS Ann. Photogram. Remote Sens. Spatial Inf. Sci. V-2-2020, 95-114.

X Wang, T Xiao, M Gruber, C Heipke. (2019). Robustifying relative orientations with respect to repetitive structures and very short baselines for global SfM. In: Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 2896-2904. Long Beach, CA, USA. (Oral)

X Wang, F Rottensteiner, C Heipke. (2018). Robust image orientation based on relative rotations and tie Points. ISPRS Ann. Photogram. Remote Sens. Spatial Inf. Sci. IV-2, 295302. Riva del Garda, Italy. (Oral)

   X Wang, ZQ Zhan, C Heipke. (2017). An efficient method to detect mutual overlap of a large set of unordered images for structure-from-motion. ISPRS Ann. Photogram. Remote Sens. Spatial Inf. Sci. IV-1/W1, 191198. Hannover, Germany. (Oral)

 

  发明专利(Patent) 

詹总谦,王鑫. 全景影像拼接及量测系统及方法. 专利号: ZL 2013 1 0145582.8

 

科研活动(Scientific Activities):

德国摄影测量、遥感和地理信息学会(DGPF)会员。 Journal of Photogrammetry and Remote Sensing, Photogrammetric engineering & Remote Sensing, DPFG Journal, Photogrammetric Record, 测绘学报 等期刊审稿; 与专业领域熟知的多视重建开源库OpenMVS作者合作研发定向与空三接口.