PSIVT2017 Wuhan, China
Workshop on Computer Vision and Modern Vehicles

Autonomous vehicles are arriving. Computer vision is a core technology for this imminent revolution in local transport. Modern vehicles learn to see.

The workshop will focus on new and improved methods, techniques, and applications of computer vision and modern vehicles. A previous issue of this workshop has been held at PSIVT 2015 in Auckland, New Zealand. This second issue is being held at Wuhan, China.

The aim of this workshop is to bring together engineers and scientists from academia, industry and government to exchange results and ideas for future applications of computer vision and modern vehicles, for the benefit of safe efficient local transport systems, with enhanced comfort.

Proceedings will be part of the workshop volume(s) for PSIVT 2017, published in Springer’s LNCS.


Please be aware that this program is subject to changes as we finalize it in the coming days.

Tuesday, November 21, 2017
9:00 – 9:40 Jian Yao (Wuhan University)
9:40 – 10:00 Energy Efficient Facial Expression Recognition based on Improved Deep Residual Networks (J. Du, Y. Chen and Y. Luo)
10:00 – 10:20 Context-Awareness Based Adaptive Gaussian Mixture Background Modeling (H. Xie, J. Xiao and J. Lei)
10:20 – 10:40 A systematic scheme for automatic airplane detection from high-resolution remote sensing images (J. Zhao, J. Han, C. Feng and J. Yao)
10:40 -10:55 Coffee break
10:55 – 11:15 Image Mixed Noise Removal Algorithm Based on Convolutional Neural Network (L. Ding, H. Zhang, J. Xiao, B. Li and W. Gu.)
11:15 – 11:35 Local Fast R-CNN Flow for Object-centric Event Recognition in Complex Traffic Scenes (Q. Gu, J. Yang, W. Yan, Y. Li and R. Klette)
11:35 – 11:40 Concluding remarks


Topics include, but not limited, to:

  • • Impacts of deep learning on vehicle control
  • • Combinations of data-driven and model-based approaches
  • • Low-level vision and image processing, image/video denoising, image enhancement, image super-resolution
  • • Vehicle localization and autonomous navigation
  • • Vehicle to vehicle to infrastructure communication; the internet of vehicles
  • • The stixel world and 6D vision
  • • Stereo vision for traffic scene understanding
  • • Semantic segmentation, object grouping, and shape representation
  • • Object recognition: detection, categorization, indexing and matching, motion and tracking
  • • Statistical methods
  • • Video: events, activities and surveillance
  • • Automated vehicles with and without pilot/driver, partial vehicle automation
  • • Driver or passenger monitoring
  • • Driver human factors and personalization
  • • Multisensor integration (LiDAR, radar, GPS/IMU, …)
  • • Sensing, detection and actuation
  • • Advanced vehicle safety systems, lane change and merging
  • • Vision and environment perception, vision based ADAS
  • • Performance evaluation of vision in a traffic context
  • • Vehicle test beds: Testing sensor and control modules under various conditions

Important points for sensor and platform description are calibration standards, testing standards, or image quality assurance procedures.


Computer vision for modern vehicle has allowed researcher access the camera technology for wide-ranging applications in automotive industry. Computer vision-based driver assistance is an emerging technology, in both the automotive industry and academia. Despite the existence of some commercial safety systems such as night vision, adaptive cruise control, and lane departure warning systems, we are at the beginning of a long research pathway towards a future generation of intelligent vehicles.

Modern vehicles learned to see in recent years. Vision-based driver assistance moves towards autonomous driving. Controlled environments, especially with a mild climate or indoor environment, are the expected cases where autonomous driving will become a standard first, within the next 4-7 years. Modern camera and vision technology supports a wide-range of applications in the traditional and emerging automotive industry. Initial solutions for night vision, adaptive cruise control, or lane departure warning paved the way towards future generations of intelligent vehicles, using already existing or totally novel sensor and vision technologies.

Important Dates

  • Workshop call for papers: June 5st, 2017
  • Workshop paper submission deadline: September 1st, 2017  October 11th, 2017
  • Workshop paper acceptance notification: September 15th, 2017  October 15th, 2017
  • Workshop paper camera-ready deadline: October 21st, 2017
  • Workshop duration: 21th November, 2017

Program Co-Chairs

Atsushi Imiya, Chiba University, Japan
Jinsheng Xiao, Wuhan University, Wuhan, China

Program Committee

A B M Shawkat Ali, The University of Fiji, Suva, Fiji
Ales Prochazka, UCT & CTU, Prague, Czech Republic
Alfred M. Bruckstein, Technion, Haifa, Israel, and NTU, Singapore
Anko Boerner, German Aerospace Center, Berlin, Germany
Asaad Hakeem, JDX Silicon Valley Research Center, Santa Clara, USA
Bijun Li, Wuhan University, Wuhan, China
Changxin Gao, Huazhong University of Science and Technology, Wuhan, China
Ching-Hsien (Robert) Hsu, Chung Hua University, Taiwan
Eduardo Destefanis, UTN National University of Technology, Córdoba, Argentina
George Azzopardi, University of Malta, Malta
Hui Chen, Shandong University, Jinan, China
John Barron, University of Western Ontario, London, Canada
Junli Tao, AUT, Auckland, New Zealand
Konstantin Schauwecker, Nerian Vision Technologies, Stuttgart, Germany
Leszek Chmielewski, Warsaw University of Life Sciences, Poland
Mahdi Rezaei, QIAU, Qazvin, Iran
Mutsuhiro Terauchi, Osaka, Japan
Reinhard Klette, AUT, Auckland, New Zealand
Sandino Morales, Terrabotics, Mexico City, Mexico
Steven Beauchemin, Western University, Canada
Wang Han, NTU, Singapore
Waqar Khan, WelTec, Wellington, New Zealand
Yanqiang Li, Shandong Academy of Science, Jinan, China
Yanyan Xu, MIT, Boston, USA
Yuan-Fang Wang, University of California, Santa Barbara, USA

Prof. Atsushi Imiya
Atsushi Imiya is a professor at the Institute of Management and Information Technologies, Chiba University, Japan. His research interests include computer vision and pattern recognition and vision-based advanced driver assistant systems. He has published more than 100 papers in international journals or international conferences.

Porf. Jinsheng Xiao
Jinsheng Xiao is a professor at the School of Electronic Information, Wuhan University, China. His research interests include computer vision and pattern recognition and vision-based advanced driver assistant systems. He has published more than 60 papers in international journals or international conferences.

Invited Talks

Jian Yao, Wuhan University, China


For any related inquiry, please contact Prof. Dr. J. Xiao

 Supporters and Sponsors