LAB LOGA page on LabLog, a review site (not the lab's official page)
Human-Centered Vision Lab
Machine-translated · View original
A computer vision lab that studies how to make computers understand images and video.
AboutAbout the lab
Recognizing and understanding images and video with computers.
The Human-Centered Vision Lab studies computer vision and image recognition and understanding.
Areas of interest listed include image recognition and understanding, video recognition, pattern recognition, machine learning, and 3D image acquisition and processing.
As a cooperative graduate school program with the University of Tsukuba, the lab accepts master's and doctoral students, who can earn a University of Tsukuba degree while studying in the advanced research environment of AIST (the National Institute of Advanced Industrial Science and Technology).
On the lab's website, it is introduced under the name "Satoh Lab."
Key terms
- Cooperative graduate school
- A form of graduate school in which a university and a research institution collaborate. Here, students can earn a University of Tsukuba degree while studying in AIST's research environment.
- Pre-training
- Training a model in advance on other data before training it on the target task
- Background subtraction
- An image processing method that removes the unchanging background from video to find moving objects
ResearchResearch themes
The lab studies technologies that let computers recognize and understand images and video, from the angles of deep learning and 3D image acquisition and processing. Representative papers are listed for each research theme.
*Illustrative imageImage and Video Analysis with Deep Learning
Still images and video are analyzed with deep neural networks. Topics listed include pre-training without natural images, action recognition, and research on detecting traffic near-miss incidents from driving video.
*Illustrative imageImage Processing with Special Cameras such as RGB-D
Image processing using RGB-D cameras, light field cameras, and hyperspectral cameras. Topics include 3D measurement under direct sunlight and 3D reconstruction with omnidirectional cameras. The papers on the website date up to around 2018.
*Illustrative imageBackground Subtraction and Image Matching Robust to Illumination Changes
Robust pattern matching using a method called Statistical Reach Features. Topics listed include background subtraction that is robust to extreme illumination changes and template matching that matches reliably even under difficult lighting. The papers on the website date up to around 2018.
*Illustrative imageDetecting Abnormal Motion in Video
Research on automatically detecting abnormal motion in camera video using CHLAC (cubic higher-order local auto-correlation). Development of software for real-time detection and application to video surveillance are listed. The website entries date from around 2007.
MembersFaculty
- Professor (Cooperative Graduate School)Yutaka Satoh
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 Human-Centered Vision Lab
Intelligent Informatics Lab (Kobayashi)Graduate School of Science and Technology, Degree Programs in Systems and Information Engineering, Degree Program in Information Science and Technology, Intelligence and Information EngineeringStatistical pattern recognition and machine learning: deep l…
Pattern Recognition and Machine Learning Lab (Souza)Graduate School of Science and Technology, Degree Programs in Systems and Information Engineering, Degree Program in Information Science and Technology, Intelligence and Information EngineeringPattern recognition, machine learning, feature representatio…
Parallel Distributed Storage Lab (Tanimura)Graduate School of Science and Technology, Degree Programs in Systems and Information Engineering, Degree Program in Information Science and Technology, Computer EngineeringParallel distributed storage, large-scale data processing, c…
Fujii Lab (Field Robotics)Graduate School of Science and Technology, Degree Programs in Systems and Information Engineering, Degree Program in Information Science and Technology, Intelligent SoftwareField robotics: sensing technologies for natural disaster si…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: “3D Scanner perspective” Alange6373 / CC BY-SA 3.0 (cropped)
- Image and Video Analysis with Deep Learning: “Banana Plant Flask by Max Gruber” Max Gruber / CC BY 4.0 (cropped)
- Image Processing with Special Cameras such as RGB-D: “3D scanning of a historic temple chariot at the National Crafts Museum, Delhi” Niranjan Ramamurthy / CC BY-SA 4.0 (cropped)
- Background Subtraction and Image Matching Robust to Illumination Changes: “Template Matching” Laserlicht and Benjamin Watson / CC BY 4.0 (cropped)
- Detecting Abnormal Motion in Video: “Security camera” Wikideas1 / CC0 (cropped)
- Related lab (Intelligent Informatics Lab (Kobayashi)): “S4000 Image Sensor” Glosome / CC BY-SA 4.0 (cropped)
- Related lab (Pattern Recognition and Machine Learning Lab (Souza)): “LSST Camera Imaging Sensors First Digital Photos (rubin-romanesco4)” Rubin Obs/NOIRLab/NSF/AURA / CC BY 4.0 (cropped)
- Related lab (Parallel Distributed Storage Lab (Tanimura)): “35-Desktop-Hard-Drive” Evan-Amos / CC BY-SA 3.0 (cropped)
- Related lab (Fujii Lab (Field Robotics)): “12.26 Vice President attends "2025 Tainan Pioneering Industry-Government-Academia-Research Collaboration Drone Disaster Relief Resilience Demonstration"” Taiwan Presidential Office / CC BY 4.0 (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.