6 papers
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…
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…
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…
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…
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…
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…