activity
20192022
collaborators

6 papers

cs.CV2022

Domain Invariant Siamese Attention Mask for Small Object Change Detection via Everyday Indoor Robot Navigation

Koji Takeda, Kanji Tanaka, Yoshimasa Nakamura

The problem of image change detection via everyday indoor robot navigation is explored from a novel perspective of the self-attention technique. Detecting semantically non-distinct…

cs.CV2022

Exploring Self-Attention for Visual Intersection Classification

Haruki Nakata, Kanji Tanaka, Koji Takeda

In robot vision, self-attention has recently emerged as a technique for capturing non-local contexts. In this study, we introduced a self-attention mechanism into the intersection…

cs.CV2021

TaylorMade VDD: Domain-adaptive Visual Defect Detector for High-mix Low-volume Production of Non-convex Cylindrical Metal Objects

Kyosuke Tashiro, Koji Takeda, Kanji Tanaka +1

Visual defect detection (VDD) for high-mix low-volume production of non-convex metal objects, such as high-pressure cylindrical piping joint parts (VDD-HPPPs), is challenging becau…

cs.CV2020

Dark Reciprocal-Rank: Boosting Graph-Convolutional Self-Localization Network via Teacher-to-student Knowledge Transfer

Koji Takeda, Kanji Tanaka

In visual robot self-localization, graph-based scene representation and matching have recently attracted research interest as robust and discriminative methods for selflocalization…

cs.CV2019

Place-specific Background Modeling Using Recursive Autoencoders

Yamaguchi Kousuke, Tanaka Kanji, Sugimoto Takuma +2

Image change detection (ICD) to detect changed objects in front of a vehicle with respect to a place-specific background model using an on-board monocular vision system is a fundam…

cs.CV2019

Use of First and Third Person Views for Deep Intersection Classification

Koji Takeda, Kanji Tanaka

We explore the problem of intersection classification using monocular on-board passive vision, with the goal of classifying traffic scenes with respect to road topology. We divide…