LAB LOGA page on LabLog, a review site (not the lab's official page)
Deguchi Lab
Machine-translated · View original
The lab studies pattern recognition, focusing on recognizing and understanding video and images.
AboutAbout the lab
Taking on the new era opened up by pattern recognition.
The Deguchi Lab researches pattern recognition, centered on recognizing and understanding video and images.
With the major goal of augmenting and supporting human visual function, the lab is divided into a human sensing group, which targets people, and an environment sensing group, which targets the environment around vehicles.
The human sensing group studies ways to make daily life more convenient through person detection, action recognition, and similar technologies. The environment sensing group studies how to use vehicle sensors to support safe and comfortable driving.
On the lab's website, it is introduced under the name "Chair of Fundamental Intelligent Informatics (Deguchi)."
Key terms
- Pattern recognition
- Technology for identifying the objects and features shown in data such as video and images
- Semantic segmentation
- Technology that assigns an attribute label, such as "car" or "pedestrian," to each pixel of what appears in an image
- Pose estimation
- Using image sensors to estimate not only what an object is but also in what pose it is placed
ResearchResearch themes
The lab aims to augment and support human visual function through the recognition and understanding of video and images. Research is carried out by two groups: one working on recognition that targets people, and one working on understanding the environment using sensors mounted on vehicles.
*Illustrative imageObject recognition using a variety of sensors
In recent years, sensors have appeared that detect light levels humans cannot perceive, as well as sensors for non-visible light such as infrared. By developing methods that use these sensors efficiently, the lab expects to be able to propose monitoring systems for looking after elderly people.
*Illustrative imageObject pose estimation
As robots are developed for industrial and everyday use, it is becoming important for robots to carry objects. To this end, the lab studies methods that use image sensors not only to recognize objects but also to estimate their pose.
*Illustrative imagePerson recognition based on behavior
To reduce accidents in which visually impaired people fall from station platforms, the lab studies how to recognize from surveillance camera video whether a person is visually impaired, using cues such as the white cane, how it is used, and the person's posture. The lab also works on automatically finding a target person among a large number of images.
*Illustrative imageSemantic segmentation
Autonomous driving requires accurate recognition of the surrounding environment. Applying this technology, which assigns labels to images from in-vehicle cameras, the lab studies further subdividing pedestrian attributes, automatically acquiring drivable paths, and recognizing equipment along railway lines.
MembersFaculty
The members of the Deguchi Lab consist of faculty, collaborating faculty and researchers, doctoral, master's, and undergraduate students, and secretarial staff.
- Associate ProfessorDaisuke Deguchi
- Project ProfessorHiroshi Murase
- Assistant ProfessorNaoki Akai
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 Deguchi Lab
Ide Lab (Contents Science Lab)School of Informatics, Department of Computer ScienceEducation and research on analysis of images, speech signals…
Fujii LabSchool of Informatics, Department of Computer ScienceEducation and research on analysis of images, speech signals…
Toda Lab (Speech and Audio Information Processing)School of Informatics, Department of Computer ScienceEducation and research on analysis of images, speech signals…
Komamizu LabSchool of Informatics, Department of Computer ScienceEducation and research on analysis of images, speech signals…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: “Unmarked Nissan Rogue - Possible Test Autonomous Vehicle - San Francisco, May 2025 05” 9yz / CC BY 4.0 (cropped)
- Object recognition using a variety of sensors: “Leicester Square, London, in Thermal Infrared ( )” David Skinner / CC BY 2.0 (cropped)
- Object pose estimation: “Tour4 Spoetzl Brewery Shiner Texas 2024” Larry D. Moore / CC BY 4.0 (cropped)
- Person recognition based on behavior: “CamTech surveillance camera, Copenhagen Central Station” YosemiteYamper / CC BY-SA 4.0 (cropped)
- Semantic segmentation: “Moscow, Yandex self-driving Hyundai Sonata, Aug 2025 roof unit 02” Retired electrician / CC0 (cropped)
- Related lab (Ide Lab (Contents Science Lab)): “Video editing color keyboard with Yamaha AW4416 Recording Workstation ( by Ben2742) pixabay - 660070” Ben2742 / CC0 (cropped)
- Related lab (Fujii Lab): “Bones Studio hala” Gabriela Cybulska / CC BY-SA 4.0 (cropped)
- Related lab (Toda Lab (Speech and Audio Information Processing)): “Studio microphone with pop-shield crop” Galak76 / CC BY-SA 3.0 (cropped)
- Related lab (Komamizu Lab): “Wikimedia Foundation Servers-8055 01” Victorgrigas / CC BY-SA 3.0 (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.