Hello! This is Haihan, a PhD. Student from University of Tsukuba in the Computer Vision and Media Lab. I received my Master's Degree in University of Tsukuba and my Bechelor Degree was in Jilin University. My current research topic is to create a large-scale dynamic city map for autonomous driving. I am interested in exploring the solutions for ADAS by using cheap sensors on the vehicle. Image processing, SLAM and VR display are all related to my research. If you are interested in my projects, please feel free to contact me.
2021.03 Master of Engineering, University of Tsukuba (Japan).
2017.07 Bachelor of Engineering, Jilin University (China).
Image processing
3D Scene Understanding
SLAM
Sensor fusion
Virtual Reality
○Maxwell Kernard, Haihan Zhang, Yuki Akimoto, Masakazu Hirokawa, Kenji Suzuki, “Effects of Visual Biofeedback on Competition Performance Using an Immersive Mixed Reality System”, 2020 IEEE International Conference on Systems, Man, and Cybernetics. (SMC2020), Oral
Ying Zhong, ○Haihan Zhang, “Analysis of Imitating Behavior on Social Media”, HUMAN-COMPUTER INTERACTION (HCI2020), Oral
○Haihan Zhang, Hidehiko Shishido, Itaru Kitahara,” Superimposition of 3D Dynamic Objects on a Static Environment for Driver Assistance System “,2021 IEEE 10th Global Conference on Consumer Electronics (GCCE2021), Oral
○Haihan Zhang, Hidehiko Shishido, Itaru Kitahara, “3D Dynamic Scene Generation for Advanced Driver Assistance System by Integrating RGB-D and Aerial Multi-View Images”, Dynamic Image processing for real Application workshop 2021, (DIA2021), Oral
○Haihan Zhang, Hidehiko Shishido, Itaru Kitahara, “3D Dynamic Objects Localization in a Static Environment for Advanced Driver Assistance System”, APMAR 2021, Apr.2021. 8 pages. Oral.
○Haihan Zhang, Hidehiko Shishido, Itaru Kitahara, “空撮映像に基づく建物群三次元復元と階層化点群補完”, 2022年度第50回画像電子学会年次大会, 2022年8月, 4 pages. no. 8607. Oral
○Haihan Zhang, Chun Xie, Hisatoshi Toriya, Hidehiko Shishido, Itaru Kitahara, "Vehicle Localization in a Completed City-Scale 3D Scene Using Aerial Images and an On-Board Stereo Camera", Remote Sensing, 2023.08. Journal.
PhD. Student of Empowerment Informatics program, in University of Tsukuba.
Master Student of Empowerment Informatics program, in University of Tsukuba.
Research Student of Human Engineered Environment Studies, in University of Tokyo
Bechelor Student of Mechanical Engineering, in Jilin University
Power wheelchair Sports have been becoming widespread, especially for disabled people. We developed a system that could spread Power Wheelchair Tennis into virtual spaces with good force feedback and a more authentic experience. Tennis game development in VR is based on Unity, a 3D game engine. Operation from a joystick interface helped control the movement of the wheelchair both in virtual space and reality. To enhance the immersive realism by feeding motion in the VR space back to reality. The force feedback comes from a real racket on the side of the power wheelchair. The system presented vibration feedback when hitting the ball through a joystick, and a 6DoF Electric suspension platform that can tilt the seat surface when moving or rotating. The project is supported by EMP Challenge Grant.
With the development of sensor accuracy and optimization algorithms, the Advanced Driver Assistance System (ADAS) has been widely used on vehicles to achieve level 3 of automatic driving. Vision-based dense mapping is one of the most essential solutions in ADAS to help vehicles sense surroundings. However, traditional methods could only reconstruct a 3D map of a static environment because of the occlusion of dynamic objects on the environment map. Moreover, a dynamic environment is hard to be 3D modeled in real time because of the limitation of computing power and algorithm complexity. To make the dynamic scene visible in a 3D point cloud, we propose a system that superimposes dynamic objects on a static environment in real-time. The static environment is reconstructed by aerial multi-view images from the unmanned aerial vehicle (UAV) in advance to reduce the required computing power. Dynamic objects point cloud is generated from disparity maps generated by a consumer stereo-camera frame by frame.
This project investigates the effects of real time visual biofeedback for improving sports performance using a large scale immersive mixed reality system in which users are able to play a simulated game of curling. The users slide custom curling stones across the floor onto a projected target whose size is dictated by the user's stress-related physiological measure; heart rate (HR). The higher HR the player has, the smaller the target will be, and vice-versa. In the experiment participants were asked to compete in three different conditions: baseline, with and without the proposed biofeedback. The results show that when providing a visual representation of the player's HR or "choking" in competition, it helped the player understand their condition and improve competition performance.
Connection
email: zhang.haihan@image.iit.tsukuba.ac.jp