LAB LOGA page on LabLog, a review site (not the lab's official page)
Takahashi Lab
Machine-translated · View original
The lab studies image and video processing, reading sign language and human movement from video.
AboutAbout the lab
Reading human movement from video to support communication.
Takahashi Lab studies how computers process and recognize images and video.
The lab works on technology that supports communication between deaf and hearing people, including research on recognizing sign language from video.
It also studies human pose and hand motion estimation, analysis of sports and surveillance camera footage, and generating avatars from text.
Key terms
- Sign language recognition
- Technology in which a computer reads hand and body movements from video of a person signing and determines which words or sentences they express
- Pose estimation
- Technology that estimates the positions of a person's joints and other body parts from images or video to capture their body posture
- Generative adversarial network
- A machine learning method that trains a model by pitting one side that generates images or other data against another side that judges whether they are real. Also called a GAN
ResearchResearch themes
The lab studies technology that reads the movements of the human body and hands from images and video captured by cameras. Centered on supporting communication through sign language recognition, it also works on analyzing sports video and generating avatars from text.
*Illustrative imageSign language recognition and communication support
The lab studies methods for recognizing continuous sign language from video, and translation of Japanese Sign Language using YouTube videos. It also builds tools that support annotating sign language video with features such as non-hand movements and the use of signing space.
*Illustrative imageHuman pose and hand motion estimation
The lab studies 2D and 3D pose estimation, which captures the positions of human joints from images, as well as hand gesture recognition. It also works on computationally lightweight hand detection methods that can run on embedded devices.
Analysis of sports and surveillance video
The lab is conducting research on classifying pitch types by capturing players' skeletal movements from baseball broadcast video, and on detecting anomalies in surveillance camera footage and identifying their type.
Automatic generation of avatars and puzzles
The lab studies generating anime-style avatars that match a given skeleton, and 3D avatars of people with upper-limb differences, from text instructions. It also studies solving tangram puzzles using generative adversarial networks.
MembersFaculty
- ProfessorHiroki Takahashi
VoicesStudent voices
Ratings and reviews reflect the experiences of individual current or former students, not the lab's official views. Whether a lab has reviews, or how many, says nothing about the lab itself.
Students who take part in an interview may receive a thank-you gift worth ¥1,000, regardless of what they say.
Student ratings (0 students)
--
--
--
--
--
--
Student voices answer questions like these
- What's great about this lab?
- What did you learn after joining?
- What's the vibe, and what is the professor like?
- Who is this lab for?
- Where do graduates go?
Your experience can help younger students choose their lab. Your name won't be shown.
Write a lab reviewAnonymous · Your draft is saved if you stopRelatedLabs similar to Takahashi Lab
Takagi LabSchool of Informatics and Engineering, Class I (Informatics)Spoken language information processing / pattern recognition…
Shono LabSchool of Informatics and Engineering, Class I (Informatics)Machine learning / Deep learning / Image processing
Hirota-Nojima LabSchool of Informatics and Engineering, Class I (Informatics)Image recognition / user interfaces / VR / AR
Nakashika LabSchool of Informatics and Engineering, Class I (Informatics)Speech recognition / speech synthesis / image recognition / …The information on this page is compiled by the LabLog team from the lab's public information and interviews. For corrections or removal requests, please contact LabLog, not the lab.
Report an errorAbout the images
The top and research theme images are illustrative and were not taken at the lab. They are cropped from Wikimedia Commons images. Cropped CC BY-SA images are provided under the same CC BY-SA license as the original (version shown on each line).
- Top image: “Peyman Majidi Prototyping a dimensioning system via image processing” پیمان مجیدی معین / CC BY-SA 4.0 (cropped)
- Sign language recognition and communication support: “Ghanaian sign language interpreter working at University of Education Winneba” Uprising Man / CC BY-SA 4.0 (cropped)
- Human pose and hand motion estimation: “MotionCapture” T-tus at English Wikipedia / CC BY-SA 3.0 (cropped)
- Related lab (Takagi Lab): “Utaco recording with Blue Snowball Microphone 20111101” Danny Choo / CC BY-SA 2.0 (cropped)
- Related lab (Shono Lab): “Convolutional Neural Network” Irisbox / CC BY 4.0 (cropped)
- Related lab (Hirota-Nojima Lab): “HAPTION Virtuose 6 Degrees of Freedom Force-Feedback in Immersive Simulation” HAPTION / CC BY-SA 3.0 (cropped)
- Related lab (Nakashika Lab): “Siemens Studio for Electronic Music - Console, Signal generator, Tape recorders - Deutsches Museum, 2010” pixabay: Stefan Schweihofer / CC0 (cropped)
About LabLog
LabLog is a lab review app for students only. Student members at each university interview students in labs and publish what they say. Student voices can only be read by students who sign up with a university email address. Operated by bestiee Inc.
Learn more about LabLog ↗Search engines and AI may reference the basic lab info and rating summaries on this page and the description of LabLog. Student voices are for student members only. Automated collection by programs (scraping, or input to or training of AI) is prohibited under Article 8 of the Terms of Service. If you need data for research or analysis, please contact us.