Ishikawa Group Laboratory

Our lab's annual report "Recognition and Behavior in Smart Systems 2024" has been uploaded to the following site. The report includes abstracts of researches (142 subjects), list of published papers, etc. in English and Japanese.
http://ishikawa-vision.org/Booklet/index-e.html

Although a part of our research activities was carried out at the University of Tokyo due to a research project, all of our research activities have moved to Tokyo University of Science (TUS) from April 1, 2024. Along with this, Lecturer Sueishi and a few administrative staffs moved to TUS Katsushika campas. We look forward to your continued support.

A new video “Accurate and Robust Inter-vehicle Distance Estimation with Stereo High-speed Vision” has been uploaded to YouTube. The task is to recognize, track, suck, and line up moving beads with high-speed vision. We use a rotating table, but the same task can be done with a conveyor belt. Also, the robot arm can be swaying with inaccuracy. It shows the power of high-speed visual feedback, but the latest three videos are difficult to understand just by watching the videos. It is aimed at those who are looking for a better solution with a similar system.

Fully Automated Beads Art Assembly based on Dynamic Compensation Approach Towards the goal of realizing next-generation manufacturing, we demonstrate the implementation of made-to-order bead art as a simplified scenario of smart ma...

A new video “A sealant dispensing robot for applications with moving targets” has been uploaded to YouTube. It is a robot that applies adhesive to the default position of the hard disk case. It can perform tasks even if the object is moving and the direction of the target is different by using high-speed visual feedback. It is expected to improve the total throughput of a production line.

A sealant dispensing robot for applications with moving targets Towards the goal of realizing next-generation smart manufacturing, we developed a sealant dispensing robot to deal with moving targets of no prior knowledge ...

A new video “Accurate and Robust Inter-vehicle Distance Estimation with Stereo High-speed Vision” has been uploaded to YouTube. This is a method of accurately and robustly measuring the distance to the vehicle in front using high-speed stereo vision without using laser ranging.　The effect of low-frequency mechanical vibrations lower than 500 fps can be easily eliminated and the accuracy is high, so it is possible to calculate speed and acceleration from a distance.

Accurate and Robust Inter-vehicle Distance Estimation with Stereo High-speed Vision We propose an accurate and robust inter-vehicle distance estimation method using high-speed stereo vision. The framework involves two driving mechanisms. The...

Our lab was selected by Worldwide Market Reports as one of the five major key players in the world in Real-time Tracking Projection Mapping and featured in a June 19 article on the Digital Journal site. The other four players are companies (three companies are ventures or start-ups and one company is big company), so we were the only one chosen by the university. Of these five organizations' technologies, I think our technology has the lowest latency and can follow the fastest-moving target.
Also, although it is titled "Real-time Tracking Projection Mapping" here, I think our system is the only system that tracks deformation of 3D shapes in real-time as well as tracking.
We call it "Dynamic Projection Mapping", and we are finally aware of the market. I am looking forward to the future.

Real-time Tracking Projection Mapping System Market Region Wise Analysis of Top Players and Changing Growth Factor in Industry, Forecast by 2023-2030: Hexogon Solution, Modulo Pi, Quince Imaging WMR has announced the addition of Real-time Tracking Projection Mapping System Market 2023 Forecast Analysis by Types, Applications, Size, Share, Key Players, and Regions. a new research report to its market research archive. The Real-time Tracking Projection Mapping System Market has been thoroughl...

Our labo's annual report "Recognition and Behavior in Smart Systems 2023" has been uploaded to the following site. The report includes abstracts of researches (135 subjects), list of published papers, etc. in English and Japanese. The cover design has been changed to a color close to the color of the Tokyo University of Science.
http://ishikawa-vision.org/Booklet/index-e.html

From April 1, 2023, most of our research activities have moved to Tokyo University of Science (TUS). At the same time that Professor Ishikawa's research activities have been transferred to TUS, the research activities of our laboratory were transferred to TUS. The Ishikawa Group Laboratory was established at the Katsushika Campus of TUS. Along with this, Associate Professor Hayakawa, Associate Professor Miyash*ta, Lecturer Huang, and Assistant Professor Tabata became the main duties of TUS. Our laboratory will remain on the Hongo Campus of the University of Tokyo (UTokyo), and Associate Professor Hayakawa will also serve part-time at UTokyo as a project associate professor. 末石The research activities of our laboratory at UTokyo will be transferred to TUS when there is no reason for the project to be carried out. Many of the administrative staff have moved to TUS, and only some of them work at UTokyo.
As a result, in FY2023, the Ishikawa Group Laboratory is divided into TUS (Ishikawa, Hayakawa, Miyash*ta, Huang, Tabata) and UTokyo (Hayakawa, Sueishi), but as the Ishikawa Group Laboratory, we are carrying out research activities in an integrated manner as before. Therefore, the laboratory name and homepage URL are the same as before. We look forward to your continued support.

Our recent YouTube Video “Robot System for Manipulating a Randomly Placed Towel-like Object” has been briefly introduced in IEEE Spectrum “Video Friday” page.
https://spectrum.ieee.org/video-friday-robot-soccer-finals

Video Friday: Robot Soccer Finals Your weekly selection of awesome robot videos

A new video “Robot System for Manipulating a Randomly Placed Towel-like Object” has been uploaded to YouTube. The video shows a manipulation of flexible object like a towel. This video is so sober and muddy, and it's mainly for those who know how difficult it is. The task was realized at a university 10 years ago in 15 minutes ~ 20 minutes. We have realized it in about 30 seconds this time.
https://www.youtube.com/watch?v=F_pK5iVvz-k

Robot System for Manipulating a Randomly Placed Towel-like Object In recent years, there has been an increasing demand for robotic handling of towel-like objects in linen and laundry services. One such task involves picking...

Our labo's annual report "Recognition and Behavior in Smart Systems 2022" has been uploaded to the following site. The report includes abstracts of researches (134 subjects), list of published papers, etc. in English and Japanese.
http://ishikawa-vision.org/Booklet/index-e.html

Ishikawa Group Laboratory - Booklet on Researches The report of 254 page booklet (pdf file) includes brief descriptions of research subjects (134 themes), publication lists of papers, and a list of awards in English and Japanese. It can be downloaded freely.

A new video “1 Millisecond Vision Pioneers a New Era” has been uploaded to YouTube. Our laboratory in the University of Tokyo moved from Graduate School of Information Science and Technology (IST) to Information Technology Center (ITC) in April 2020. The video shows a history and recent progress of our high-speed vision research until March 2020 as well as basic concept and active attitude of our research.
https://www.youtube.com/watch?v=CO0ChaAccPM

1 Millisecond Vision Pioneers a New Era Our laboratory in the University of Tokyo moved from Graduate School of Information Science and Technology (IST) to Information Technology Center (ITC) in Ap...

Our labo's annual report "Recognition and Behavior in Smart Systems 2021" has been uploaded to the following site. The report includes abstracts of researches (129 subjects), list of published papers, etc. in English and Japanese.
http://ishikawa-vision.org/Booklet/index-e.html

Our recent YouTube Video “VarioLight 2: Wide Dynamic Projection Mapping in Rhythmic Gymnastics” has been briefly introduced in IEEE Spectrum “Video Friday” page.
https://spectrum.ieee.org/automaton/robotics/robotics-hardware/video-friday-robotic-eyeball-camera

A new video “VarioLight 2: Wide Dynamic Projection Mapping in Rhythmic Gymnastics” has been uploaded to YouTube. The video shows a new dynamic projection mapping onto a ball in rhythmic gymnastics. It can be applied to various sports or dance performances even if the target moves so quickly. Although a gray scale high-speed projector is used in this video, a color expression can be implemented by using a new color high-speed projector we have developed　recently.
https://www.youtube.com/watch?v=9X66YZTb_hA

VarioLight 2: Wide Dynamic Projection Mapping in Rhythmic Gymnastics We have realized the combination of wide dynamic projection mapping and rhythmic gymnastics performance. "VarioLight 2" system can realize dynamic projection...

Our recent YouTube Video “High-speed color projector toward the world of 1,000fps vision” has been briefly introduced in IEEE Spectrum “Video Friday” page.
https://spectrum.ieee.org/automaton/robotics/robotics-hardware/video-friday-shadow-plays-jenga-and-more

A new video “High-speed color projector toward the world of 1,000fps vision” has been uploaded to YouTube. The video shows a new 24bit color high-speed projector and a dynamic projection mapping (DPM) system. Beautiful expression onto moving or deforming 3D objects can be implemented by using combination of the 24bit high-speed color projector and a high-speed 3D shape measurement. Last demo of cats is also 24 bit color. The projector will be commercialized by companies in near future. I hope DPM system will be transferred to commercial companies.
https://www.youtube.com/watch?v=bQ8XMey-leM

High-speed color projector toward the world of 1,000fps vision 1,000fps sensing, image processing, and projection enable real-time overwriting of objects.We, humans, will know the world of 1,000fps vision and how slow ou...