no code implementations • 10 May 2024 • Koji Takeda, Kanji Tanaka, Yoshimasa Nakamura, Asako Kanezaki
To regularize this problem, we apply the conceptof self-supervised learning to achieve efficient DoI estimationscheme and investigate its generalization to diverse datasets. Specifically, we tackle the challenging issue of obtaining self-supervision cues for semantically non-distinctive unseen smallobjects and show that novel "oversegmentation cues" from openvocabulary semantic segmentation can be effectively exploited. When applied to diverse real datasets, the proposed DoI modelcan boost state-of-the-art change detection models, and it showsstable and consistent improvements when evaluated on real-world datasets.
no code implementations • 13 Mar 2024 • Kenta Tsukahara, Kanji Tanaka, Daiki Iwata
Rather than relying on the availability of private data of teachers as in existing methods, we propose to exploit an assumption that holds universally in self-localization tasks: "The teacher model is a self-localization system" and to reuse the self-localization system of a teacher as a sole accessible communication channel.
no code implementations • 26 Dec 2023 • Kenta Tsukahara, Kanji Tanaka
A typical assumption in state-of-the-art self-localization models is that an annotated training dataset is available for the target workspace.
no code implementations • 24 Oct 2023 • Ryogo Yamamoto, Kanji Tanaka
Cross-view self-localization is a challenging scenario of visual place recognition in which database images are provided from sparse viewpoints.
no code implementations • 30 Sep 2023 • Jonathan Tay Yu Liang, Kanji Tanaka
The emerging ``Floor plan from human trails (PfH)" technique has great potential for improving indoor robot navigation by predicting the traversability of occluded floors.
no code implementations • 28 Jun 2023 • Koji Takeda, Kanji Tanaka, Yoshimasa Nakamura
The recently emerging research area in robotics, ground view change detection, suffers from its ill-posed-ness because of visual uncertainty combined with complex nonlinear perspective projection.
no code implementations • 19 Jun 2023 • Shogo Hanada, Kanji Tanaka
The tasks also include an online map matching attempt to efficiently find correspondence between the part-based maps.
no code implementations • 10 May 2023 • Tomoya Iwasaki, Kanji Tanaka, Kenta Tsukahara
Visual place classification from a first-person-view monocular RGB image is a fundamental problem in long-term robot navigation.
no code implementations • 10 May 2023 • Mitsuki Yoshida, Kanji Tanaka, Ryogo Yamamoto, Daiki Iwata
Semantic localization, i. e., robot self-localization with semantic image modality, is critical in recently emerging embodied AI applications (e. g., point-goal navigation, object-goal navigation, vision language navigation) and topological mapping applications (e. g., graph neural SLAM, ego-centric topological map).
no code implementations • 3 Aug 2022 • Ryogo Yamamoto, Kanji Tanaka
The use of relative attribute (e. g., beautiful, safe, convenient) -based image embeddings in visual place recognition, as a domain-adaptive compact image descriptor that is orthogonal to the typical approach of absolute attribute (e. g., color, shape, texture) -based image embeddings, is explored in this paper.
no code implementations • 22 Apr 2022 • Kanya Kurauchi, Kanji Tanaka, Ryogo Yamamoto, Mitsuki Yoshida
The OLC is available at the output layer of the CNN model and aims to estimate the state of the robot (e. g., the robot viewpoint) with respect to the world-centric view coordinate system.
no code implementations • 29 Mar 2022 • Koji Takeda, Kanji Tanaka, Yoshimasa Nakamura
Experiments, in which an indoor robot aims to detect visually small changes in everyday navigation, demonstrate that our attention technique significantly boosts the state-of-the-art image change detection model.
no code implementations • 26 Mar 2022 • Haruki Nakata, Kanji Tanaka, Koji Takeda
In this study, we introduced a self-attention mechanism into the intersection recognition system as a method to capture the non-local contexts behind the scenes.
no code implementations • 9 Sep 2021 • Mitsuki Yoshida, Ryogo Yamamoto, Kanji Tanaka
In this paper, we address the problem of image sequence-based self-localization from a new highly compressive scene representation called sequential semantic scene graph (S3G).
no code implementations • 9 Apr 2021 • Kyosuke Tashiro, Koji Takeda, Kanji Tanaka, Tomoe Hiroki
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 because subtle difference in domain (e. g., metal objects, imaging device, viewpoints, lighting) significantly affects the specular reflection characteristics of individual metal object types.
no code implementations • 23 Feb 2021 • Kanji Tanaka
Pole-like landmark has received increasing attention as a domain-invariant visual cue for visual robot self-localization across domains (e. g., seasons, times of day, weathers).
no code implementations • 1 Nov 2020 • 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.
no code implementations • 22 Jan 2019 • 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.
no code implementations • 16 Sep 2017 • Xiaoxiao Fei, Kanji Tanaka, Yichu Fang, Akitaka Takayama
This paper addresses the problem of cross-season visual place classification (VPC) from a novel perspective of long-term map learning.
no code implementations • 6 Aug 2016 • Kanji Tanaka
Furthermore, we consider the general incremental setting of loop closure detection, in which the system must update both the set of VPR constraints and that of loop closure hypotheses when new constraints or hypotheses arrive during robot navigation.
no code implementations • 6 Aug 2016 • Tomoya Murase, Kanji Tanaka
Formulation as an image comparison task, which operates on a given pair of query and reference images is common to many existing approaches to this problem.
no code implementations • 25 Sep 2015 • Kanji Tanaka
Loop closure detection, the task of identifying locations revisited by a robot in a sequence of odometry and perceptual observations, is typically formulated as a combination of two subtasks: (1) bag-of-words image retrieval and (2) post-verification using RANSAC geometric verification.
no code implementations • 25 Sep 2015 • Taisho Tsukamoto, Kanji Tanaka
In this study, we aim to solve the single-view robot self-localization problem by using visual experience across domains.
no code implementations • 25 Sep 2015 • Enfu Liu, Kanji Tanaka
The main contribution of this paper is an extension of the bag-of-words map retrieval method to enable the use of spatial information from local features.
no code implementations • 24 Jun 2015 • Kanji Tanaka, Eiji Kondo
Vehicle relocation is the problem in which a mobile robot has to estimate the self-position with respect to an a priori map of landmarks using the perception and the motion measurements without using any knowledge of the initial self-position.