LAB LOGA page on LabLog, a review site (not the lab's official page)
Kawakami Lab
Machine-translated · View original
A computer vision lab that tackles the “seeing” problem for autonomous systems.
AboutAbout the lab
Solving the vision problem for systems that move around.
The Kawakami Lab studies computer vision, image processing, and machine learning.
The lab aims to solve the vision problems faced by autonomous systems that move around in open environments.
Such systems face many challenges, including sensing, planning, responding to abnormal events, and updating their knowledge of the environment.
The lab encourages those who want to take the graduate entrance exam for the Kawakami Lab to attend the department’s admissions information session.
Key terms
- Computer vision
- Technology that enables computers to understand the objects and scenes in camera images and video
- Anomaly detection
- Technology that automatically finds unusual events or objects that differ from ordinary data
- Open-set recognition
- Recognition that can identify kinds of objects not seen during training as unknown
NewsLab news
Paper accepted to CVPR 2026, an international conference on computer vision
Photometric stereo paper presented at AAAI 2026
Paper on a robot inserting pegs into holes accepted to ICRA 2026
Object detection paper presented at ACM MM Asia 2025
Paper on object rearrangement and peg insertion accepted to IROS 2025
ResearchResearch themes
The lab aims to solve vision problems for autonomous systems that move around in open environments. The four themes below follow the categories in the Selected publication list of Associate Professor Kawakami, which is linked from the research introduction page; they mainly cover work done before the lab was founded in April 2022.
*Illustrative imageLearning features that are robust to differing conditions
The lab has studied how to train neural networks that extract features from images so that they also work on data whose conditions differ from those of the training data.
*Illustrative imageAnomaly detection and open-set recognition
The lab has worked on anomaly detection that uses the temporal flow of video as a cue, and on open-set recognition that can identify kinds of objects never seen in training. Applications include images of wind turbine blades taken by drones.
*Illustrative imagePredicting motion from sports video
This includes research that predicts the receiver of a pass from soccer video and player trajectories, and research that predicts fencers’ movements by taking their interaction with the opponent into account.
*Illustrative imageObject detection and classification
The lab has worked on detecting small flying objects in high-resolution video, detecting and counting cattle in drone images, and detecting birds and classifying their species from images taken around wind farms.
MembersFaculty
The Kawakami Lab consists of faculty members and doctoral, master’s, and undergraduate students.As of 2026
- Associate ProfessorRei KawakamiPublications ↗
VoicesStudent voices
Compiled from answers by students who were in the lab. Ratings and reviews reflect individual students' experiences, not the lab's official views.
Students who take part in an interview may receive a thank-you gift worth ¥1,000, regardless of what they say.
On a 4-point scale, ● marks where students' answers fall
Who is this lab for?
What's great about this lab?
What did you learn after joining?
What's the vibe, and what is the professor like?
Where do graduates go?
RelatedLabs similar to Kawakami Lab
Okutomi-Monno LabSchool of Engineering, Department of Systems and Control EngineeringComputer vision, computational imaging, image sensing
Tsukagoshi LabSchool of Engineering, Department of Systems and Control EngineeringRescue robots, medical and nursing care robots, biological a…
Amaya LabSchool of Engineering, Department of Systems and Control EngineeringInverse problems, electrochemical simulation, computational …
Sato LabSchool of Engineering, Department of Systems and Control EngineeringExhaust aftertreatment, alternative fuels, and enginesThe 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: “PIA16239 High-Resolution Self-Portrait by Curiosity Rover Arm Camera” NASA/JPL-Caltech/Malin Space Science Systems Derivative work including grading, distortion correction, minor local adjustments and rendering from tiff-file: Julian Herzog / Public domain (cropped)
- Learning features that are robust to differing conditions: “Artificial Neural Network with Chip” mikemacmarketing / original posted on flickr Liam Huang / clipped and posted on flickr / CC BY 2.0 (cropped)
- Anomaly detection and open-set recognition: “Profile of turbine blade at Whitelee Windfarm - geograph.org.uk - 1582261” Gordon Brown / CC BY-SA 2.0 (cropped)
- Predicting motion from sports video: “Billiards table 2” MarkBuckawicki / CC0 (cropped)
- Object detection and classification: “Demoiselle cranes flying past wind turbines, Gujarat” Dr. Raju Kasambe / CC BY-SA 4.0 (cropped)
- Related lab (奥富・紋野研究室): “Monmouth castle point cloud, created with Photosynth 01” John Cummings / CC BY-SA 3.0 (cropped)
- Related lab (塚越研究室): “Amoeba proteus locomotive form” SmallRex / CC BY-SA 4.0 (cropped)
- Related lab (天谷研究室): “Electrode protecting a screw” Rémi Kaupp / CC BY-SA 3.0 (cropped)
- Related lab (佐藤研究室): “Automobile exhaust gas” Ruben de Rijcke / 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.