Home »People » Huimin Ma
HuiminMa

Prof. HuiMin Ma

Education Background
  • Department of Mechanical Electronic Engineering, Beijing Institute of Technology, Beijing, China, 2001. Doctor of Mechanical Electronic Engineering
  • School of Medicine, Department of Neurological Surgery, University of Pittsburgh, Pittsburgh, PA, U.S.A. Visiting Scholar
Experience
    Department of Electronic Engineering, Tsinghua University, Beijing, China
  • Assistant Professor (2001 –2006)
  • Associate Professor (2006 – present)
Concurrent Academic
  • Organizing Chair, the 4th International Symposium on Bioelectronics and Bioinformatics, 2015
  • Organizing Committee Chair, Image and Graphics Technology and Application, 2013, 2014,2015
  • Conference Chair, International Conference on Modeling, Simulation and Identification, Beijing, China, October 9-12, 2009
  • Conference Chair, Asia Modeling and Simulation, Beijing, China, October 12-14, 2007
Social Service
  • 2016 – present, Secretary-General and executive fellow of the Chinese Society of Image and Graphics
  • 2016 – present, Chief Supervisor of the Beijing Society of Image and Graphics
  • 2012 – present, Committee of Beijing Association for Science and Technology
  • 2011 – present, IEEE member
  • 2007-2016, Secretary-General of the Beijing Society of Image and Graphics
  • 2004-2016, Director of the Youth Work Committee in the Chinese Society of Image and Graphics
Areas of Research Interests
  • Research on 3-D image cognition, mainly focus on the interdisciplinary research of psychology and pattern recognition, to realize 3D object detection and recognition with multi-task, multi-modal and multi-view methods in complex scenes.
  • Research on complex scenes simulation and navigation decision, mainly focus on dynamic environment simulation, reinforcement learning and intelligent decision, to realize 3D object recognition and tracking in complex environment.
Research Status
  • 3-D Image Cognition Theory and Technology
  • As data-driven machine learning methods are difficult to achieve accurate recognition under dynamic complex scenes, we made a breakthrough based on the psychologically stable prior of cognitive subjects, put forward the thought of Subject-Data Bidirectional Driven Learning, and established the three-dimensional image Gestalt Cognitive Computing Theory. The proposed theory significantly improved the accuracy under dynamic complex scene.
    3-D Image Cognition Theory and Technology
    Image-based Psychological System
  • Image Cognition-based Psychological Evaluation and Intervention System
  • We built the first psychological image database based on MMPI, and designed a set of psychological paradigms based on emotional image cognition. We put forward an objective and rapid psychological characteristic extraction method based on image cognition, which changed the traditional scale-based psychological evaluation model,. This system won the Wu Wenjun Artificial Intelligence Science and Technology Innovation Award (First Class) and Silver Award of Geneva International Exhibition of Inventions.
    Image Cognition-based Psychological Evaluation and Intervention System
    Image-based Psychological System
  • 3D Image Cognition and Visual Navigation
  • We proposed 3D image cognition computing theory, defined general cognition characters, such as structure and scene prior. We introduced multi-task, multi-modal and multi-view cognitive subject priors into machine learning, realize Subject-Data Bidirectional Driven Learning, and applied them in 3D object detection and localization under complex autonomous driving scenes. Our method won 4 first place on 6 tasks of KITTI dataset, which is the largest autonomous driving benchmark, and achieves accuracy at 90% for the first time.
    3D Image Cognition and Visual Navigation
    Results on autonomous driving dataset: KITTI and Cityscapes
  • Complex Environment Simulation and Navigation Decision
  • Multi-object interactional system in real world is too complex to be reconstructed by computer. In our research, an imaging based virtual reality system of object tracking and anti-tracking was established. We have built a photoelectric confrontation simulation system including both seeker and interference to realize 3D object recognition in jamming environment. Our simulation system can provide training samples, testing platform and reinforcement learning environment for visual navigation. The complex environment confrontation simulation system as well as anti-interference recognition and tracking system serves as a core technology in intelligent unmanned system, and has played an important role in applications of multiple areas such as aeronautics, automatic driving, and ships.
    Complex Environment Simulation and Navigation Decision
    Complex Scene Simulation and Reinforcement Learning Framework
Main Research Projects
  • Vision-based Techniques for Semi-Autonomous Driving (1/2016-12/2020) supported by the China Ministry of Science and Technology & Zongmu Technology Company.
  • The objective of this project is studying object detection and road information extraction to realize reliable (semi-)autonomous driving.
  • 3-D Complex Scene Simulation and Navigation Decision ( 12/02-present ), supported by a series of the National Special Projects
  • The objective of this project is establishing an imaging based virtual reality system of object detection, recognition, navigation, etc.
  • Psychological Characteristics Extraction Based on Image Cognition (1/2011-12/2015) supported by the National Natural Science Foundation.
  • The objective of this project is developing human’s psychology characterization by the experiments of image cognition.
  • The Aspect Graph Theory and Method Investigation in 3-D Target Recognition( 1/06-12/2008), supported by the National Natural Science Foundation.
  • The objective of this project is expanding the theory of 3D object recognition from arbitrary view, establishing a real-world 3D recognition system with single image, it is useful in computer vision especial for huge database searching and automatic navigating tasks.
  • The Design of Image Signal Processor( 2/08-6/10), supported by two National Special Projects
  • The objective of this project is converting the algorithm of 3D recognition and simulation into hardware to applying in real world.
Teaching Experience
  • Undergraduate
    • Digital Logic and CPU, in Spring, 2012-present
    • Principles of Computer, in Fall, 2007 – 2011
  • Graduate
    • Digital Image Technology and Application, in Fall, 2002 – present
Academic Achievement
  • Awards
    • Wu-Wen-Jun Artificial Intelligence Scientific and Technological Innovation Award, First Class, 2016
    • Silver Medal of Geneva International Inventions, 2017
    • International Evaluation of Object Detection for Autonomous Driving on KITTI Benchmark, First Place, 2015
Journal Papers:
  1. Xiaozhi Chen, Kaustav Kunku, Yukun Zhu, Huimin Ma, Sanja Fidler, Raquel Urtasun. 3D Object Proposals using Stereo Imagery for Accurate Object Class Detection. TPAMI, 2017. [pdf]

  2. Xiaoqin Zhang, Huimin Ma and Jinghuan Wen. "Stochastic Approximation for Expensive One-Bit Feedback Systems." Tsinghua Science and Technology 22.3 (2017): 317-327.

  3. Chen Hu, Xuedan Zhang, Huimin Ma. Shape-adaptive virtual hand grasping method, Journal of Image and Graphics.

  4. Xiaozhi Chen, Huimin Ma, Chenzhuo Zhu, Xiang Wang, Zhichen Zhao. Boundary-aware Box Refinement for Object Proposal Generation, Neurocomputing, Volume 219, 5 January 2017, Pages 323-332.[pdf]

  5. Zhichen Zhao, Huimin Ma, Xiaozhi Chen. Generalized Symmetric Pair Model for Action Classification in Still Images, Pattern Recognition, Volume 64, 1 April 2017, Pages 347 - 360. [pdf]

  6. Zhichen Zhao, Huimin Ma, Xiaozhi Chen. Semantic Parts based Top-Down Pyramid for Action Recognition, Pattern Recognition Letters, Volume 84, 1 December 2016, Pages 134–141. [pdf]

  7. Xiang Wang, Huimin Ma, Xiaozhi Chen. Geodesic Weighted Bayesian Model for Saliency Optimization, Pattern Recognition Letters, Volume 75, 1 May 2016, Pages 1–8. [pdf] [project page] [bibtex]

  8. Jinghuan Wen, Huimin Ma, Xiaoqin Zhang. Optimization of the occlusion strategy in visual tracking, Tsinghua Science and Technology, 2016.

  9. Tong Chu, Huimin Ma. Study of Infrared Anti-Jamming Tracking Agorithm, Journal of Image and Graphics, 2013, 18(10): 1354-1363. [pdf]

  10. Shaodi You, Huimin Ma. Manifold topological multi-resolution analysis method, Pattern Recognition, 2011.1.6, pp1629-1648. [pdf]

  11. Huimin Ma, Tiantian Huang, Yanzhi Wang. Multi-resolution recognition of 3D object based on visual resolution limit, Pattern Recognition Letter, Volume 31, Issue 3, 1 February 2010, pp. 259-266 [pdf]

  12. Yuchen Guo, Huimin Ma, Qingmin Liao. Analysis on Shape Features for 2D Projective Image Based 3D Object Recognition, Journal of Tsinghua University (SCi & Tech), Vol.49, No.10, pp1646-1650, October 2009. [pdf]

  13. Wenyun Huang, Huimin Ma, Shengjin Wang. A Recognition Algorithm for Sea Background Infrared Target, Journal of Tsinghua University (SCi & Tech), Vol.49, No.10, pp1609-1613, October 2009. [pdf]

  14. Xiaoliang Yu, Huimin Ma, Jian Xiao. Real-time Target Recognition System Simulation Based on Laser Near-field Detection, Optoelectronics Letters, Vol.5, No.4, pp0299-0303, July 2009. [pdf]

  15. Chenye Wu, Huimin Ma. Computing EEE Events Based on Conicoid Theory in 3D Object Recognition Application, Tsinghua Science and Technology, Vol.14, No.2, pp264-270, April 2009. [pdf]

  16. Jie Sun, Huimin Ma, Fengting Li. Viewpoint Space Partition Based on Affine Invariant Feature, Journal of Tsinghua University (SCi & Tech), Vol.49, No.1, pp53-56, January 2009. [pdf]

  17. Miao Su, Huimin Ma, Fengting Li. Catastrophe Theory and Clustering Algorithm Based Viewpoint Space Partition Algorithm, Journal of Tsinghua University (SCi & Tech), Vol.48, No.4, pp518-521, April 2008. [pdf]

  18. Huimin Ma, Ruke Huang. Multi-hierarchical Algorithms for Fast Fingerprint Identification, Chinese Journal of Eelectronics, Vol.14, No.4, pp625-630, October 2005.

  19. Huajian Wang, Aiwu Zhang, Huimin Ma, Fengting Li. Hole Filling in Range Image Processing Based on Statistical Model, Journal of Optoelectronics Laser, Vol.15, No.10, pp.1234-1237, November 2004. [pdf]

  20. Huimin Ma, Yan Wang. Parallel Feature Extraction System, Chinese Journal of Electronics,Vol.12 No.4, pp598-601, October 2003.

  21. Huimin Ma, Guangda Su. High Speed Recognition System of Plane Infrared Image, Journal of Infrared and Millimeter Waves, Vol.21, No.5, pp367-371, October 2002. [pdf]

  22. Huimin Ma. Gray Image Feature Extraction Base on Projection, Optical Technique, VOL.28, NO.6, pp.561-563, 2002.

Conference Papers:
  1. Xiaozhi Chen, Huimin Ma, Ji Wan, Bo Li, Tian Xia. Multi-View 3D Object Detection Network for Autonomous Driving, International Conference on Computer Vision and Pattern Recognition (CVPR), 2017. [pdf]

  2. Xiang Wang, Huimin Ma, Xiaozhi Chen. Salient Object Detection via fast R-CNN and Low-level Cues, International Conference on Image Processing (ICIP), 2016. [pdf] [project page] [bibtex]

  3. Zhichen Zhao, Huimin Ma, Xiaozhi Chen. Multi-scale Region Candidate Combination for Action Recognition, International Conference on Image Processing (ICIP), 2016. [pdf]

  4. Dazhao Shi, Huimin Ma. A Robust Object Tracking Algorithm in Complex Environment, International Conference on Digital Image Processing (ICDIP), 2016. [pdf]

  5. Xiaozhi Chen, Kaustav Kunku, Ziyu Zhang, Huimin Ma, Sanja Fidler, Raquel Urtasun. Monocular 3D Object Detection for Autonomous Driving, International Conference on Computer Vision and Pattern Recognition (CVPR), 2016. [pdf]

  6. Xiaozhi Chen, Kaustav Kunku, Yukun Zhu, Andrew Berneshawi, Huimin Ma, Sanja Fidler, Raquel Urtasun. 3D Object Proposals for Accurate Object Class Detection, Annual Conference on Neural Information Processing Systems(NIPS), 2015. [Paper] [Demo][KITTI Results][BibTex]

  7. Yidong Wang, Huimin Ma. Identification Differences among People under Context of Complex Images, International Symposium on Bioelectronics and Bioinformatics (ISBB), 2015. [pdf]

  8. Xiang Wang, Huimin Ma, Xiaozhi Chen. Geodesic Weighted Bayesian Model for Salient Object Detection, International Conference on Image Processing (ICIP), 2015. [pdf] [project page] [BibTex]

  9. Xiaozhi Chen, Huimin Ma, Xiang Wang, Zhichen Zhao. Improving Object Proposals with Multi-Thresholding Straddling Expansion, International Conference on Computer Vision and Pattern Recognition (CVPR), 2015. [pdf] [project page] [BibTex]

  10. Jun Cao, Huimin Ma. Regression-based Parameter Optimization for Binary Output Systems, 2015 3rd International Conference on Information and Communication Technology (ICoICT), 2015. [pdf]

  11. Boqiang Fan, Huimin Ma, Xiang Wang. The Analysis of Frequency Domain Characteristics of Emotional Images in Eye-tracking Experiment, Seventh International Conference on Digital Image Processing(ICDIP) 2015.

  12. Wenyu Li, Huimin Ma, Xiang Wang, Dazhao Shi. Features Derived From Behavioral Experiments To Distinguish Mental Healthy People From Depressed People, The 11th IASTED International Conference on Biomedical Engineering (BioMed) 2014. [pdf]

  13. Huimin Ma, Luyao Zhou. Humanoid-eye Imaging System Model with Ability of Resolving Power Computing. Advances in Image and Graphics Technologies(IGTA), 2014.[pdf]

  14. Xiaozhi Chen, Huimin Ma. Learning a Compact Latent Representation of the Bag-of-Parts Model. International Conference on Image Processing (ICIP), 2014. [pdf]

  15. Zhichen Zhao, Huimin Ma, Xiaozhi Chen. Protected Pooling Method of Sparse Coding in Visual Classification. International Conference on Computer Vision and Graphics (ICCVG), 2014. [pdf]

  16. Shurui Bao, Huimin Ma. ThuPIS: A New Affective Image System for Psychological Analysis. International Symposium on Bioelectronics and Bioinformatics (ISBB), 2014. [pdf]

  17. Shurui Bao, Huimin Ma, Wenyu Li, Xiang Wang. Discrimination of Positive Facial Expressions is More Susceptible to Affective Background Scenes. International Conference on Culture, Knowledge and Society (ICCKS), 2014. [pdf]

  18. Luyao Zhou, Huimin Ma. Accurate and fast simulation of laser scanning imaging. International Conference on Multimedia Technology (ICIG), 2013.[pdf]

  19. Huimin Ma, Xiaozhi Chen. Simplification Computing for Visual Events Based on Distinct Silhouette and View-Independent Pruning Algorithm. Advances in Image and Graphics Technologies (IGTA), 2013.[pdf]

  20. Yu Zhang, Huimin Ma. The Electronic Countermeasures Optimization Based on PCA and Multiple Regression Analysis. Advances in Image and Graphics Technologies (IGTA), 2013.[pdf]

  21. Shangfu Ouyang, Huimin Ma. Cognitive impact differs from relationship of scene and facial expression. The 2012 International Conference on Biomedical Engineering and Biotechnology (ICBEB), 2012. [pdf]

  22. Juan Li, Huimin Ma, Luyao Zhou. Implementation of a Progressive Target Recognition System for All the Angles. The International Conference on Automatic Control and Artificial Intelligence (ICACAI), 2012 [pdf]

  23. Yu Hou, Huimin Ma. Analysis of an infrared interference antagonizing window tracking algorithm. International Conference on Automatic Control and Artificial Intelligence, (ICACAI), 2012. [pdf]

  24. Guanhua Su, Huimin Ma, Yu Hou. A Robust Approach for Anti-Jamming Target Tracking in Forward Looking Infrared Imagery, International Conference on Image and Graphics, (ICIG), 2011 [pdf]

  25. Bo Pang, Huimin Ma. An Effective Way of 3D Model Representation in Recognition System, International Conference on Multimedia and Signal Processing (CMSP),2011. [pdf]

  26. Lifeng Liu, Huimin Ma, Mingquan Lu. A FPGA and Zernike Moments Based Near-field Laser Imaging Detector Multi-scale Real-time Target Recognition Algorithm , Third International Symposium on Information Science and Engineering (ISISE), 2010. [pdf]

  27. Xiao Yu, Huimin Ma, Ze Yuan. A Solution to Efficient Viewpoint Space Partition in 3D Object Recognition, International Conference on Image and Graphics (ICIG), 2009. [pdf]

  28. Xu Zhang, Huimin Ma, Yushu Liu, Chunxiao Gao. An Extension of Locally Linear Embedding for Pose Estimation of 3D Object, International Conference on Machine Learning and Cybernetics (ICMLC), 2007. [pdf]

  29. Tiantian Huang, Huimin Ma, Fengting Li. Segmentation and Recognition of 3D Objects in Automatic Navigation, The 4rd International Conference on Natural Computation (ICNC), 2008. [pdf]

  30. Chenye Wu, Huimin Ma. Efficiently Pruning for Visual Events in 3D Object Recognition Application, Proceeding of 14th National Conference of Image and Graphics(NCIG), 2008. [pdf]

  31. Yibo Zhang, Huimin Ma, Peng Cui. Manifold Characteristic Analysis of 3-D Object, Proceeding of 2008 Conference of Image and Graphics (ICIG), 2008.

  32. Luo Yuan, Huimin Ma, Fengting Li. An Improved Algorithm of Viewpoint Space Partition in 3D Object Recognition Application, Proceedings of the Seventh IASTED International Conference on Signal and Image Processing (SIP), 2006.[pdf]

  33. Yuan Luo, Huimin Ma, Fengting Li. 3D Object Recognition Technique Based on Muti-Resolution Aspect Graph, 2005 International Conference on Neural Networks and Brain (ICNNB), 2005. [pdf]

  34. Wei Lin, Huimin Ma, Fengting Li. Accurate Tracking Based on Interest Points in The Infrared Imaging Guidance, 2005 International Conference on Neural Networks and Brain (ICNNB), 2005. [pdf]

  35. Huimin Ma, Ruke Huang. A New Fingerprint Translation Finding Algorithm, IEEE I nternational Conference on Machine Learning and Cybernetics , 2004. [pdf]

  36. Huimin Ma, Guangda Su, Ruke Huang. A Classification Agorithm for Fingerprint Matching in Large Database, Proceedings of The 13th National Conference on Neural Network (NCNN), 2003.

  37. Huimin Ma, Guangda Su, Junyan Wang. A Glass Bottle Defect Detection System Without Touching, IEEE International Conference on Machine Learning and Cybernetics (ICMLC), 2002. [pdf]

Books:
  1. Huimin Ma, Associate Editors-in-Chief of Digital Image Processing, Higher Education Press, China, 2007
  2. Huimin Ma, Associate Editors-in-Chief of Digital Image Processing, Peiking University Press, China, 2007