Close

Takuma Kaneko

About Me

I'm a second-year graduate student at Tokyo Denki University.
My research field is machine learning. I belong to Visual Perception & Recognition Laboratory(VPRL) advised by Yuko Ozasa(小篠 裕子).

Publications

路面状態分類におけるハイパースペクトル画像の導入

Takuma Kaneko, Junkei Okada, Yuko Ozasa

Information Processing Society of Japan (IPSJ-AVM), 2024

ハイパースペクトルデータを用いた路面状態分類における汎化性能の評価

Takuma Kaneko, Junkei Okada, Yuko Ozasa

Institute of Electronics, Information and Communication Engineers (IEICE), 2024

Evaluation of Generalization Performance in Road Surface Condition Classification with Hyperspectral Images

Yuri Otsuka, Junkei Okada, Takuma Kaneko, Yuko Ozasa

Sensing, Actuation, Motion Control, and Optimization (SAMCON), 2024

Reflectance and Illumination Estimation from An Known Reflectance for Classification

Yuma Mabuchi, Takuma Kaneko, Yuko Ozasa

Frontiers of Computer Vision (FCV), 2025

ハイパースペクトルデータに対する分光測光ラベリング

Takuma Kaneko, Naoko Enami, Yuko Ozasa

Meeting on Image Recognition and Understanding (MIRU), 2025

Education

Tokyo Denki University, Japan

Apr. 2020 - Mar. 2024

School of System Design and Technology

Tokyo Denki University, Japan

Apr. 2024 - Present

Graduate School of System Design and Technology

Research

Hyperspectral Imaging

Hyperspectral Imaging is a new analytical technique based on spectroscopy. It collects hundreds of images at different wavelengths for the same spatial area. While the human eye has only three color receptors in the blue, green and red, hyperspectral imaging measures the continuous spectrum of the light for each pixel of the scene with fine wavelength resolution, not only in the visible but also in the near-infrared.

Road Surface Condition Recognition

"Road Surface Condition Recognition" is a technology that recognizes the condition of road surfaces. This technology uses devices such as cameras and sensors to analyze the features and conditions of road surfaces, allowing for the identification of factors such as wetness, freezing conditions, and dirtiness. This information can then be used to provide data for safe driving, enabling vehicles such as cars and autonomous vehicles to operate at appropriate speeds and control.

Material Recognition

"Material Recognition is a technology that identifies and classifies the types of materials that objects are made of, such as metal, plastic, wood, glass, or fabric. Unlike simple object detection, which focuses on shapes and categories, material recognition analyzes surface properties like texture, reflectance, and spectral characteristics. This enables a deeper understanding of how objects interact with light and their environment. By recognizing material properties, this technology can support applications such as robotics, autonomous driving, augmented reality, and quality inspection in manufacturing, contributing to safer and more efficient systems.

Key workds