Brief Introduction of VisionOnSky Co., Ltd.

Short Biography of the Founder


Brief Introduction of VisionOnSky Co., Ltd.


VisionOnSky Co., Ltd. is founded by scientific researcher, and is a startup company which is concentrating on the development of state-of-the-art technology, software realization of the new techniques and industrial applications in photogrammetry, remote sensing and computer vision.


The company independently developed a both effect and performance optimized semi-global matching (SGM) algorithm which is applied to dense stereo matching of aerial image (including oblique aerial image), satellite image and UAV image. It generates highly dense point clouds and digital surface model (DSM) through finding the point corresponding for each pixel. We also developed a multilevel triangle-based ground filtering algorithm, which can transform DSM to DTM (Digital Terrain Model) automatically, i.e., removing the height of building and tree, only remaining the height of pure ground. The algorithm can select different level of terrain details in the light of the requirements. The DSM transformed to DTM can be extracted from satellite image, aerial image, UAV image as well as LiDAR points. We presented a block-regression (BR) based pansharpening algorithm. The algorithm can combine a lower resolution multispectral image and a higher resolution panchromatic image both covering a same area, and produce a new higher resolution image, in which not only the color content are remained but also the spatial details are enhanced by adopting the higher resolution panchromatic image. BR algorithm can achieve a maximum enhancement of its spatial details at the expense of a minimum spectral distortion for the multispectral images. In the algorithm, the bands of the multispectral image used can not be limited and the algorithm is specially optimized for the pansharpening of very high resolution satellite image. We also developed a series of parallel techniques with different processing levels, which are suitable for different steps of image processing. Not only concurrently processing of multiple tasks but also parallel processing in a single task is supported. The series of parallel techniques can be used either on multi-core computer or on cluster computer.


The above innovative techniques are realized by the form of software and we also developed several additional software modules. These functional modules can compose a whole flowchart. We developed modules of stereo matching, automatic DSM extraction, DSM2DTM, orthorectification, pansharpening of satellite image, the automatic orientation for a stereo / triplet of satellite images, change detection of surface height for aerial, satellite and UAV images, respectively. The whole flowcharts for aerial, satellite and UAV images, respectively, are fulfilled. After the abovementioned flowcharts, dense point clouds, DSM, DTM, nDSM, orthorectified image, pansharpened image and difference of surface height are produced. The software supports Windows OS and Linux OS, and can run on multi-core computer and cluster computer. The parallel techniques with different processing levels can leverage computational resources of the two types of computing platforms to the maximum extent.


The developed cutting-edge techniques and software can be applied to these aspects: (1) generation of mapping products (point clouds, DSM, DTM, orthorectified image, and pansharpened image); (2) automatically finding of new buildings, the buildings breaking the planning, and removed buildings, and estimating their corresponding accurate height; (3) monitoring the construction progress of new city, big residential district and huge engineering project; (4) testimony of land expropriation and housing demolition; (5) estimating the exploited volume of ores located on surface; (6) digital city and reconstruction of 3D scene; (7) collection of commercial and military intelligence; (8) accurate estimation of height of buildings and trees.


VisionOnSky Co., Ltd. can provide different channels through which the capacity of different customers is enhanced. For companies with the data-intensive production, we promote their processing efficiency by optimizing their procedure and offering them the methods with high efficiency. For application-oriented companies, we help them to engage new and more profitable applications by means of technical updating. For software companies, we help them to improve their own software system by licensing them our technical modules. For companies providing cloud service, we as software provider offer them our professional software. For the users in academic research and education, we provide them the rapid realization of techniques and experiments in the course of research study by offering them our software and services.


The mission of VisionOnSky Co., Ltd is to promote capacity of our customers. We cordially welcome any form of cooperation.


Short Biography of the Founder


The founder of VisionOnSky Co., Ltd ( is Dr. Jinghui Yang. Formerly he was a postdoc at German Aerospace Center (DLR) and an associate professor at Institute of Photogrammetry and Remote Sensing, Chinese Academy of Surveying and Mapping (CASM), China. He received PhD degree at Wuhan University, master degree at Northeastern University, and bachelor degree at Northeastern University in 2014, 2005 and 2002, respectively. Dr. Jinghui Yang has more than 18 years’ experiences in the scientific research and software development of automatic and high performance processing for photogrammetry and remote sensing, image fusion. He published more than 20 scientific papers in some premier journals of this field, such as Photogrammetric Engineering& Remote Sensing, International Journal of Remote Sensing, Remote Sensing, Acta Geodaetica et Cartographica Sinica, the Journal of Geomatics and Information Science of Wuhan University. In 2009, he won Chinese National Science and Technology Progress Award because of the participation of development of remote sensing software.


In 2017, Dr. Jinghui Yang left academic institute and founded a startup company in order to promote technical innovation and accelerate industrial applications of cutting-edge technology. The founded startup, namely VisionOnSky Co., Ltd., is concentrating on the development of state-of-the-art technology, software realization of the new techniques and industrial applications.


Published papers by the founder in recent years:

1.       Yang Jinghui*, and Zhang Jixian. Parallel Performance of Typical Algorithms in Remote Sensing based Mapping on a Multi-core Computer [J]. Photogrammetric Engineering & Remote Sensing. 2015, 81(5): 373-385. DOI: 10.14358/PERS.81.5.373

2.       Yang J H*, Zhang J X, Huang G M. A Parallel Computing Paradigm for Pan-Sharpening Algorithms of Remotely Sensed Images on a Multi-Core Computer [J]. Remote Sensing. 2014, 6(7): 6039-6063. DOI:10.3390/rs6076039

3.       Yang J H*, Zhang J X. Pansharpening: From a Generalized Model Perspective [J]. International Journal of Image and Data Fusion. 2014, 5(4): 285-299.

4.       Zhang J X, Yang J H*, Zhao Z, et al. Block-Regression-based Fusion of Optical and SAR Imagery for Feature Enhancement [J]. International Journal of Remote Sensing. 2010, 31(9): 2325-2345.

5.       YANG Jinghui*. The Generalized Model and Parallel Computing Methods for Pixel-level Remote Sensing Image Fusion [J]. Acta Geodaetica et Cartographica Sinaca, 2015, 44(8): 943-943 [杨景辉*. 遥感影像像素级融合通用模型及其并行计算方法[J]. 测绘学报, 2015, 44(8): 943-943.]

6.       Yang J H*, Cheng C Q, Zhang J X, Huang G M. GPU supported massively parallel processing for geometric correction of SAR imagery [J]. Journal of Image and Graphics, 2015, 20(3): 374-385. DOI: 10.11834/jig.20150309 [杨景辉*, 程春泉, 张继贤, 黄国满. GPU支持的SAR影像几何校正大规模并行处理[J]. 中国图象图形学报, 2015, 20(3): 374-385. ]

7.       YANG Jinghui*, ZHANG Jixian. The parallel decorrelation stretching with multiple decomposition tactics for remotely sensed imagery [J]. Geomatics and Information Science of Wuhan University, 2016,41(3): 402-407. [杨景辉*, 张继贤, 结合多种分解策略的遥感影像去相关拉伸并行处理方法[J]. 武汉大学学报信息科学版, 2016,41(3): 402-407 ]

8.       YANG Jinghui*, ZHANG Jixian. GPU-based acceleration for pansharpening algorithms and performance analysis [J]. Journal of Chinese Computer Systems, 2016, 37 (3): 603-607. [杨景辉*, 张继贤. 遥感影像融合的GPU加速及性能分析[J]. 小型微型计算机系统, 2016, 37 (3): 603-607 ]

9.       J. X. Zhang, J. H. Yang*, P. Reinartz. The Optimized Block-Regression-based Fusion Algorithm for Pansharpening of Very High Resolution Satellite Imagery, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XLI-B7, 2016 XXIII ISPRS Congress, 12–19 July 2016, Prague, Czech Republic, pp.739 – 746

10.   Yang Jinghui*, Zhang Jixian“A Parallel Implementation Framework for Remotely Sensed Image Fusion,” ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume I-7, pp.329-334, 2012 XXII ISPRS Congress, 25 August – 01 September 2012, Melbourne, Australia.

11.   Yang Jinghui*, Zhang Jixian, et al, Pixel Level Fusion Methods for Remote Sensing Images: A Current Review, ISPRS Technical Commission VII Symposium, Vienna, Austria, July 2010

12.   Yang Jinghui*, Zhang Jixian, and Li Haitao. Generalized Model for Remotely Sensed Data Pixel-level Fusion and its Implementation Technology [J]. Journal of Image and Graphics, 2009, 14(4): 604-614. [杨景辉*, 张继贤, 李海涛. 遥感数据像素级融合统一模型及实现技术[J]. 中国图象图形学报, 2009, 14(4): 604-614. ]

13.   Yang Jinghui* (2012). The Parallel Processing Framework for Remotely Sensed Imagery. In Shan J, Zhang J (Eds.), Proceedings of the 18th China Symposium on Remote Sensing, pp. 8-12, Wuhan, China. [杨景辉*. 遥感影像算法级并行处理框架. 单杰, 张继贤主编, 第十八届中国遥感大会论文集, 科学出版社, pp. 8-12, 201210, 会议地点: 湖北, 武汉. ]

14.   YANG Jinghui*, AI Haibin, ZHANG Li (2011). Emergency Response Oriented Processing Flow of Remotely Sensed Imagery and Applications. A symposium on emergency response and risk management using surveying and mapping, Tianjin, China. [杨景辉*, 艾海滨, . 面向应急响应的遥感影像处理流程及应用, 第十三届中国科协年会第12学术交流分会测绘服务灾害与应急管理学术研讨会, 20119, 会议地点: 天津. ]

15.   Yang Jinghui*, Li Haitao. High performance computing techniques for remotely sensed imagery. In Advances of earth-observed data processing and analysis, Gong Jianya, Ed., Wuhan University press, Wuhan, China, 2007, pp.136-148. [杨景辉*, 李海涛. 遥感影像高性能处理方法. 龚健雅主编,对地观测数据处理与分析研究进展,武汉: 武汉大学出版社, 2007, pp.136-148. ]

16.   Zhang Jixian, Yang Jinghui*, “Satellite data fusion techniques”, a chapter of the book, Advanced Remote Sensing: Terrestrial Information Extraction and Applications, Edited by Liang Shunlin et al, Elsevier, 2012,  pp.91-110

17.   Zhang J X, Yang J H*, Li H T, et al. Generalized Model for Remotely Sensed Data Pixel-Level Fusion, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Beijing, China, 2008, Vol. XXXVII, Part B7: 1051-1056.

18.   Shao Long, Yang Jinghui, and Hong Youtang. Segmentation for remote sensing image based on heterogeneity and watershed transformation [J]. Science of Surveying and Mapping, 2014, 39(3): 19-22. [邵龙, 杨景辉, 洪友堂. 结合异质性及分水岭变换的遥感影像分割方法[J]. 测绘科学, 2014, 39(3): 19-22. ]

19.   Pan Yuan, Yang Jinghui, Wu Wenbo. Neural network based on rough sets reduction and its application to remote sensing image classification [J]. Remote Sensing Information, 2012, 27(4): 86-90. DOI: 10.3969/j.issn.1000-3177.2012.04.015 [潘远, 杨景辉, 武文波. 粗糙集约简的神经网络遥感分类应用[J]. 遥感信息, 2012, 27(4): 86-90. ]

20.   Li Haitao, Shi Yuanli, Yang Jinghui, and Han Yanshun (2009). A cluster-based parallel processing system for HJ-1 satellites data. Proc. SPIE 7497, MIPPR 2009: Medical Imaging, Parallel Processing of Images, and Optimization Techniques, 749714 (October 30, 2009). DOI:10.1117/12.833224

21.   Jia Weijie, Zhang Jixian, and Yang Jinghui (2009). Automatic registration of SAR and optics image based on multi-features on suburban areas. Urban Remote Sensing Event, 2009 Joint, pp.1-7, 20-22 May 2009. DOI: 10.1109/URS.2009.5137610


(*: Corresponding author)