Filters








213 Hits in 0.92 sec

Rare Event Detection using Disentangled Representation Learning [article]

Ryuhei Hamaguchi, Ken Sakurada, Ryosuke Nakamura
2018 arXiv   pre-print
This paper presents a novel method for rare event detection from an image pair with class-imbalanced datasets. A straightforward approach for event detection tasks is to train a detection network from a large-scale dataset in an end-to-end manner. However, in many applications such as building change detection on satellite images, few positive samples are available for the training. Moreover, scene image pairs contain many trivial events, such as in illumination changes or background motions.
more » ... ese many trivial events and the class imbalance problem lead to false alarms for rare event detection. In order to overcome these difficulties, we propose a novel method to learn disentangled representations from only low-cost negative samples. The proposed method disentangles different aspects in a pair of observations: variant and invariant factors that represent trivial events and image contents, respectively. The effectiveness of the proposed approach is verified by the quantitative evaluations on four change detection datasets, and the qualitative analysis shows that the proposed method can acquire the representations that disentangle rare events from trivial ones.
arXiv:1812.01285v1 fatcat:culwl26pffcvjl4s4c25jk5xdu

Privacy Preserving Visual SLAM [article]

Mikiya Shibuya, Shinya Sumikura, Ken Sakurada
2020 arXiv   pre-print
This study proposes a privacy-preserving Visual SLAM framework for estimating camera poses and performing bundle adjustment with mixed line and point clouds in real time. Previous studies have proposed localization methods to estimate a camera pose using a line-cloud map for a single image or a reconstructed point cloud. These methods offer a scene privacy protection against the inversion attacks by converting a point cloud to a line cloud, which reconstruct the scene images from the point
more » ... . However, they are not directly applicable to a video sequence because they do not address computational efficiency. This is a critical issue to solve for estimating camera poses and performing bundle adjustment with mixed line and point clouds in real time. Moreover, there has been no study on a method to optimize a line-cloud map of a server with a point cloud reconstructed from a client video because any observation points on the image coordinates are not available to prevent the inversion attacks, namely the reversibility of the 3D lines. The experimental results with synthetic and real data show that our Visual SLAM framework achieves the intended privacy-preserving formation and real-time performance using a line-cloud map.
arXiv:2007.10361v2 fatcat:hju3ns23fzhzzha6uguc7pfllm

Heterogeneous Grid Convolution for Adaptive, Efficient, and Controllable Computation [article]

Ryuhei Hamaguchi, Yasutaka Furukawa, Masaki Onishi, Ken Sakurada
2021 arXiv   pre-print
This paper proposes a novel heterogeneous grid convolution that builds a graph-based image representation by exploiting heterogeneity in the image content, enabling adaptive, efficient, and controllable computations in a convolutional architecture. More concretely, the approach builds a data-adaptive graph structure from a convolutional layer by a differentiable clustering method, pools features to the graph, performs a novel direction-aware graph convolution, and unpool features back to the
more » ... volutional layer. By using the developed module, the paper proposes heterogeneous grid convolutional networks, highly efficient yet strong extension of existing architectures. We have evaluated the proposed approach on four image understanding tasks, semantic segmentation, object localization, road extraction, and salient object detection. The proposed method is effective on three of the four tasks. Especially, the method outperforms a strong baseline with more than 90% reduction in floating-point operations for semantic segmentation, and achieves the state-of-the-art result for road extraction. We will share our code, model, and data.
arXiv:2104.11176v1 fatcat:4lkbvzvkgzadfe7dgqm6ah4sgq

SOIC: Semantic Online Initialization and Calibration for LiDAR and Camera [article]

Weimin Wang, Shohei Nobuhara, Ryosuke Nakamura, Ken Sakurada
2020 arXiv   pre-print
Sakurada are with National Institute of Advanced Industrial Science and Technology (AIST), Tokyo, 135-0064, Japan (email: weimin.wang@aist.go.jp; r.nakamura@aist.go.jp; k.sakurada@aist.go.jp). S.  ... 
arXiv:2003.04260v1 fatcat:co7nubfmkrfyrou2ahuaf7dyua

TriDepth: Triangular Patch-based Deep Depth Prediction [article]

Masaya Kaneko, Ken Sakurada, Kiyoharu Aizawa
2020 arXiv   pre-print
We propose a novel and efficient representation for single-view depth estimation using Convolutional Neural Networks (CNNs). Point-cloud is generally used for CNN-based 3D scene reconstruction; however it has some drawbacks: (1) it is redundant as a representation for planar surfaces, and (2) no spatial relationships between points are available (e.g, texture and surface). As a more efficient representation, we introduce a triangular-patch-cloud, which represents the surface of the 3D structure
more » ... using a set of triangular patches, and propose a CNN framework for its 3D structure estimation. In our framework, we create it by separating all the faces in a 2D mesh, which are determined adaptively from the input image, and estimate depths and normals of all the faces. Using a common RGBD-dataset, we show that our representation has a better or comparable performance than the existing point-cloud-based methods, although it has much less parameters.
arXiv:1905.01312v2 fatcat:zxvg5shejrdoznonqb22b5jdca

Epipolar-Guided Deep Object Matching for Scene Change Detection [article]

Kento Doi, Ryuhei Hamaguchi, Shun Iwase, Rio Yokota, Yutaka Matsuo, Ken Sakurada
2020 arXiv   pre-print
This paper describes a viewpoint-robust object-based change detection network (OBJ-CDNet). Mobile cameras such as drive recorders capture images from different viewpoints each time due to differences in camera trajectory and shutter timing. However, previous methods for pixel-wise change detection are vulnerable to the viewpoint differences because they assume aligned image pairs as inputs. To cope with the difficulty, we introduce a deep graph matching network that establishes object
more » ... ence between an image pair. The introduction enables us to detect object-wise scene changes without precise image alignment. For more accurate object matching, we propose an epipolar-guided deep graph matching network (EGMNet), which incorporates the epipolar constraint into the deep graph matching layer used in OBJCDNet. To evaluate our network's robustness against viewpoint differences, we created synthetic and real datasets for scene change detection from an image pair. The experimental results verified the effectiveness of our network.
arXiv:2007.15540v1 fatcat:6kdhngwdyzhjvcndhonnk2esni

Scale Estimation of Monocular SfM for a Multi-modal Stereo Camera [article]

Shinya Sumikura, Ken Sakurada, Nobuo Kawaguchi, Ryosuke Nakamura
2018 arXiv   pre-print
This paper proposes a novel method of estimating the absolute scale of monocular SfM for a multi-modal stereo camera. In the fields of computer vision and robotics, scale estimation for monocular SfM has been widely investigated in order to simplify systems. This paper addresses the scale estimation problem for a stereo camera system in which two cameras capture different spectral images (e.g., RGB and FIR), whose feature points are difficult to directly match using descriptors. Furthermore,
more » ... number of matching points between FIR images can be comparatively small, owing to the low resolution and lack of thermal scene texture. To cope with these difficulties, the proposed method estimates the scale parameter using batch optimization, based on the epipolar constraint of a small number of feature correspondences between the invisible light images. The accuracy and numerical stability of the proposed method are verified by synthetic and real image experiments.
arXiv:1810.11856v1 fatcat:2bht26id6bbx5boeurumgea3fy

Weakly Supervised Silhouette-based Semantic Scene Change Detection [article]

Ken Sakurada, Mikiya Shibuya, Weimin Wang
2020 arXiv   pre-print
As mentioned in Sec.II, Sakurada et al.  ...  [21] , [22] , and Sakurada et al. [7] might be the closest to our research.  ... 
arXiv:1811.11985v2 fatcat:w6qaimllmvcc5ivxfxb7y2yfae

An Epistemic Approach to Compositional Reasoning about Anonymity and Privacy [article]

Yasuyuki Tsukada, Hideki Sakurada, Ken Mano, Yoshifumi Manabe
2013 arXiv   pre-print
In this paper, we present an epistemic logic approach to the compositionality of several privacy-related informationhiding/ disclosure properties. The properties considered here are anonymity, privacy, onymity, and identity. Our initial observation reveals that anonymity and privacy are not necessarily sequentially compositional; this means that even though a system comprising several sequential phases satisfies a certain unlinkability property in each phase, the entire system does not always
more » ... joy a desired unlinkability property. We show that the compositionality can be guaranteed provided that the phases of the system satisfy what we call the independence assumptions. More specifically, we develop a series of theoretical case studies of what assumptions are sufficient to guarantee the sequential compositionality of various degrees of anonymity, privacy, onymity, and/or identity properties. Similar results for parallel composition are also discussed.
arXiv:1310.6441v1 fatcat:z642mjcgtffopblru6zppctggm

Dense Optical Flow based Change Detection Network Robust to Difference of Camera Viewpoints [article]

Ken Sakurada, Weimin Wang, Nobuo Kawaguchi, Ryosuke Nakamura
2017 arXiv   pre-print
This paper presents a novel method for detecting scene changes from a pair of images with a difference of camera viewpoints using a dense optical flow based change detection network. In the case that camera poses of input images are fixed or known, such as with surveillance and satellite cameras, the pixel correspondence between the images captured at different times can be known. Hence, it is possible to comparatively accurately detect scene changes between the images by modeling the
more » ... of the scene. On the other hand, in case of cameras mounted on a moving object, such as ground and aerial vehicles, we must consider the spatial correspondence between the images captured at different times. However, it can be difficult to accurately estimate the camera pose or 3D model of a scene, owing to the scene changes or lack of imagery. To solve this problem, we propose a change detection convolutional neural network utilizing dense optical flow between input images to improve the robustness to the difference between camera viewpoints. Our evaluation based on the panoramic change detection dataset shows that the proposed method outperforms state-of-the-art change detection algorithms.
arXiv:1712.02941v1 fatcat:wiibbn2wgbgenaeqz3bj6wedj4

TriDepth: Triangular Patch-Based Deep Depth Prediction

Masaya Kaneko, Ken Sakurada, Kiyoharu Aizawa
2019 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)  
We propose a novel and efficient representation for single-view depth estimation using Convolutional Neural Networks (CNNs). Point-cloud is generally used for CNNbased 3D scene reconstruction; however it has some drawbacks: (1) it is redundant as a representation for planar surfaces, and (2) no spatial relationships between points are available (e.g, texture and surface). As a more efficient representation, we introduce a triangular-patch-cloud, which represents the surface of the 3D structure
more » ... sing a set of triangular patches, and propose a CNN framework for its 3D structure estimation. In our framework, we create it by separating all the faces in a 2D mesh, which are determined adaptively from the input image, and estimate depths and normals of all the faces. Using a common RGBD-dataset, we show that our representation has a better or comparable performance than the existing point-cloud-based methods, although it has much less parameters.
doi:10.1109/iccvw.2019.00466 dblp:conf/iccvw/KanekoSA19 fatcat:wmtb4qol3jdnda2dghhxwco6oa

Rare Event Detection Using Disentangled Representation Learning

Ryuhei Hamaguchi, Ken Sakurada, Ryosuke Nakamura
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
This paper presents a novel method for rare event detection from an image pair with class-imbalanced datasets. A straightforward approach for event detection tasks is to train a detection network from a large-scale dataset in an end-to-end manner. However, in many applications such as building change detection on satellite images, few positive samples are available for the training. Moreover, scene image pairs contain many trivial events, such as in illumination changes or background motions.
more » ... ese many trivial events and the class imbalance problem lead to false alarms for rare event detection. In order to overcome these difficulties, we propose a novel method to learn disentangled representations from only low-cost negative samples. The proposed method disentangles different aspects in a pair of observations: variant and invariant factors that represent trivial events and image contents, respectively. The effectiveness of the proposed approach is verified by the quantitative evaluations on four change detection datasets, and the qualitative analysis shows that the proposed method can acquire the representations that disentangle rare events from trivial ones.
doi:10.1109/cvpr.2019.00955 dblp:conf/cvpr/HamaguchiSN19 fatcat:5dopbpkugbbw3llx7xfddgg4yq

Benchmarking Cameras for Open VSLAM Indoors

Kevin Chappellet, Guillaume Caron, Fumio Kanehiro, Ken Sakurada, Abderrahmane Kheddar
2021 2020 25th International Conference on Pattern Recognition (ICPR)  
HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.
doi:10.1109/icpr48806.2021.9413278 fatcat:bwmczxt6ffbxjo7xmmovwfehky

Massive City-Scale Surface Condition Analysis Using Ground and Aerial Imagery [chapter]

Ken Sakurada, Takayuki Okatani, Kris M. Kitani
2015 Lecture Notes in Computer Science  
Automated visual analysis is an effective method for understanding changes in natural phenomena over massive city-scale landscapes. However, the view-point spectrum across which image data can be acquired is extremely wide, ranging from macro-level overhead (aerial) images spanning several kilometers to micro-level front-parallel (streetview) images that might only span a few meters. This work presents a unified framework for robustly integrating image data taken at vastly different viewpoints
more » ... o generate large-scale estimates of land surface conditions. To validate our approach we attempt to estimate the amount of post-Tsunami damage over the entire city of Kamaishi, Japan (over 4 million square-meters). Our results show that our approach can efficiently integrate both micro and macro-level images, along with other forms of meta-data, to efficiently estimate city-scale phenomena. We evaluate our approach on two modes of land condition analysis, namely, city-scale debris and greenery estimation, to show the ability of our method to generalize to a diverse set of estimation tasks.
doi:10.1007/978-3-319-16865-4_4 fatcat:2bnho5vzn5fffcfjiydq55xsai

Investigation of Medicines Used in Inpatients

AKIYOSHI OHIZUMI, KEN SAKURADA, HIDEKI NORO, MAKIKO MIURA, SHOKO OZAKI, AKIHIKO FURUKOHRI, KO FUJITA
1982 Japanese Journal of Hospital Pharmacy  
The number of the used medicines and their prescription frequency were investigated using
doi:10.5649/jjphcs1975.8.304 fatcat:ccqt4stsofdifadod45ibi6nu4
« Previous Showing results 1 — 15 out of 213 results