Preprints

1. Learning to Drop Points for LiDAR Scan Synthesis

   Kazuto Nakashima, and Ryo Kurazume

   arXiv:2102.11952 (accepted to IROS 2021), 2021

   Abs Paper Code

   3D laser scanning by LiDAR sensors plays an important role for mobile robots to understand their surroundings. Nevertheless, not all systems have high resolution and accuracy due to hardware limitations, weather conditions, and so on. Generative modeling of LiDAR data as scene priors is one of the promising solutions to compensate for unreliable or incomplete observations. In this paper, we propose a novel generative model for learning LiDAR data based on generative adversarial networks. As in the related studies, we process LiDAR data as a compact yet lossless representation, a cylindrical depth map. However, despite the smoothness of real-world objects, many points on the depth map are dropped out through the laser measurement, which causes learning difficulty on generative models. To circumvent this issue, we introduce measurement uncertainty into the generation process, which allows the model to learn a disentangled representation of the underlying shape and the dropout noises from a collection of real LiDAR data. To simulate the lossy measurement, we adopt a differentiable sampling framework to drop points based on the learned uncertainty. We demonstrate the effectiveness of our method on synthesis and reconstruction tasks using two datasets. We further showcase potential applications by restoring LiDAR data with various types of corruption.

Journal Articles

1. Lifelogging Caption Generation via Fourth-Person Vision in a Human–Robot Symbiotic Environment

   Kazuto Nakashima, Yumi Iwashita, and Ryo Kurazume

   ROBOMECH Journal, 2020

   Abs Paper

   Automatic analysis of our daily lives and activities through a first-person lifelog camera provides us with opportunities to improve our life rhythms or to support our limited visual memories. Notably, to express the visual experiences, the task of generating captions from first-person lifelog images has been actively studied in recent years. First-person images involve scenes approximating what users actually see; therein, the visual cues are not enough to express the user’s context since the images are limited by his/her intention. Our challenge is to generate lifelog captions using a meta-perspective called “fourth-person vision”. The “fourth-person vision” is a novel concept which complementary exploits the visual information from the first-, second-, and third-person perspectives. First, we assume human–robot symbiotic scenarios that provide a second-person perspective from the camera mounted on the robot and a third-person perspective from the camera fixed in the symbiotic room. To validate our approach in this scenario, we collect perspective-aware lifelog videos and corresponding caption annotations. Subsequently, we propose a multi-perspective image captioning model composed of an image-wise salient region encoder, an attention module that adaptively fuses the salient regions, and a caption decoder that generates scene descriptions. We demonstrate that our proposed model based on the fourth-person concept can greatly improve the captioning performance against single- and double-perspective models.

2. Virtual IR Sensing for Planetary Rovers: Improved Terrain Classification and Thermal Inertia Estimation

   Yumi Iwashita, Kazuto Nakashima, Joseph Gatto, Shoya Higa, Norris Khoo, Ryo Kurazume, and Adrian Stoica

   IEEE Robotics and Automation Letters (RA-L with IROS presentation), 2020

   Abs Paper

   Terrain classification is critically important for Mars rovers, which rely on it for planning and autonomous navigation. On-board terrain classification using visual information has limitations, and is sensitive to illumination conditions. Classification can be improved if one fuses visual imagery with additional infrared (IR) imagery of the scene, yet unfortunately there are no IR image sensors on the current Mars rovers. A virtual IR sensor, estimating IR from RGB imagery using deep learning, was proposed in the context of a MU-Net architecture. However, virtual IR estimation was limited by the fact that slope angle variations induce temperature differences within the same terrain. This paper removes this limitation, giving good IR estimates and as a consequence improving terrain classification by including the additional angle from the surface normal to the Sun and the measurement of solar radiation. The estimates are also useful when estimating thermal inertia, which can enhance slip prediction and small rock density estimation. Our approach is demonstrated in two applications. We collected a new data set to verify the effectiveness of the proposed approach and show its benefit by applying to the two applications.

3. Fukuoka Datasets for Place Categorization

   Oscar Martinez Mozos, Kazuto Nakashima, Hojung Jung, Yumi Iwashita, and Ryo Kurazume

   International Journal of Robotics Research (IJRR), 2019

   Abs Paper Project

   This paper presents several multi-modal 3D datasets for the problem of categorization of places. In this problem. a robotic agent should decide on the type of place/environment where it is located (residential area, forest, etc.) using information gathered by its sensors. In addition to the 3D depth information, the datasets include additional modalities such as RGB or reflectance images. The observations were taken in different indoor and outdoor environments in Fukuoka city, Japan. Outdoor place categories include forests, urban areas, indoor parking, outdoor parking, coastal areas, and residential areas. Indoor place categories include corridors, offices, study rooms, kitchens, laboratories, and toilets. The datasets are available to download at http://robotics.ait.kyushu-u.ac.jp/kyushu_datasets.

4. Learning Geometric and Photometric Features from Panoramic LiDAR Scans for Outdoor Place Categorization

   Kazuto Nakashima, Hojung Jung, Yuki Oto, Yumi Iwashita, Ryo Kurazume, and Oscar Martinez Mozos

   Advanced Robotics, 2018

   Abs Paper Project Code

   Semantic place categorization, which is one of the essential tasks for autonomous robots and vehicles, allows them to have capabilities of self-decision and navigation in unfamiliar environments. In particular, outdoor places are more difficult targets than indoor ones due to perceptual variations, such as dynamic illuminance over 24 hours and occlusions by cars and pedestrians. This paper presents a novel method of categorizing outdoor places using convolutional neural networks (CNNs), which take omnidirectional depth/reflectance images obtained by 3D LiDARs as the inputs. First, we construct a large-scale outdoor place dataset named Multi-modal Panoramic 3D Outdoor (MPO) comprising two types of point clouds captured by two different LiDARs. They are labeled with six outdoor place categories: coast, forest, indoor/outdoor parking, residential area, and urban area. Second, we provide CNNs for LiDAR-based outdoor place categorization and evaluate our approach with the MPO dataset. Our results on the MPO dataset outperform traditional approaches and show the effectiveness in which we use both depth and reflectance modalities. To analyze our trained deep networks, we visualize the learned features.

Conference Proceedings

1. 2V-Gait: Gait Recognition Using 3D LiDAR Robust to Changes in Walking Direction and Measurement Distance

   Jeongho Ahn, Kazuto Nakashima, Koki Yoshino, Yumi Iwashita, and Ryo Kurazume

   In IEEE/SICE International Symposium on System Integration (SII), 2022

   Abs Paper

   Gait recognition, which is a biometric identifier for individual walking patterns, is utilized in many applications, such as criminal investigation and identification systems, because it can be applied at a long distance and requires no explicit cooperation of the subjects. In general, cameras are used for gait recognition, and several methods in previous studies have used depth information captured by RGB-D cameras. However, RGB-D cameras are limited in terms of their measurement distance and are difficult to access outdoors. In recent years, real-time multi-layer 3D LiDAR, which can obtain 3D range images of a target at ranges of over 100 m, has attracted significant attention for use in autonomous mobile robots, serving as eyes for obstacles detection and navigation. Compared with cameras, such 3D LiDAR has rarely been used for biometrics owing to its low spatial resolution. However, considering the unique characteristics of 3D LiDAR, such as the robustness of the illumination conditions, long measurement distances, and wide-angle scanning, the approach has the potential to be applied outdoors as a biometric identifier. The present paper describes a gait recognition system, called 2V-Gait, which is robust to variations in the walking direction of a subject and the distance measured from the 3D LiDAR. To improve the performance of gait recognition, we leverage the unique characteristics of 3D LiDAR, which are not included in regular cameras. Extensive experiments on our dataset show the effectiveness of the proposed approach.

2. Gait Recognition using Identity-Aware Adversarial Data Augmentation

   Koki Yoshino, Kazuto Nakashima, Jeongho Ahn, Yumi Iwashita, and Ryo Kurazume

   In IEEE/SICE International Symposium on System Integration (SII), 2022

   Abs Paper

   Gait recognition is a non-contact person identification method that utilizes cameras installed at a distance. However, gait images contain person-agnostic elements (covariates) such as clothing, and the removal of covariates is important for identification with high performance. Disentanglement representation learning, which separates gait-dependent information such as posture from covariates by unsupervised learning, has been attracting attention as a method to remove covariates. However, because the amount of gait data is negligible compared to other computer vision tasks, such as image recognition, the separation performance of existing methods is insufficient. In this study, we propose a gait recognition method to improve the separation performance, which augments the training data by adversarial generation based on identity features, separated by disentanglement representation learning. The proposed method first separates gait-dependent features (pose features) and appearance-related covariate features (style features) from gait videos based on disentanglement representation learning. Then, synthesized gait images are generated by exchanging pose features between gait images of the person under different walking conditions, followed by adding them to the training data. The experiments indicate that our method can improve the separation performance, and generate high-quality gait images that are effective for data augmentation.

3. Learning to Drop Points for LiDAR Scan Synthesis

   Kazuto Nakashima, and Ryo Kurazume

   In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021

   Abs arXiv Paper Code

   3D laser scanning by LiDAR sensors plays an important role for mobile robots to understand their surroundings. Nevertheless, not all systems have high resolution and accuracy due to hardware limitations, weather conditions, and so on. Generative modeling of LiDAR data as scene priors is one of the promising solutions to compensate for unreliable or incomplete observations. In this paper, we propose a novel generative model for learning LiDAR data based on generative adversarial networks. As in the related studies, we process LiDAR data as a compact yet lossless representation, a cylindrical depth map. However, despite the smoothness of real-world objects, many points on the depth map are dropped out through the laser measurement, which causes learning difficulty on generative models. To circumvent this issue, we introduce measurement uncertainty into the generation process, which allows the model to learn a disentangled representation of the underlying shape and the dropout noises from a collection of real LiDAR data. To simulate the lossy measurement, we adopt a differentiable sampling framework to drop points based on the learned uncertainty. We demonstrate the effectiveness of our method on synthesis and reconstruction tasks using two datasets. We further showcase potential applications by restoring LiDAR data with various types of corruption.

4. Virtual IR Sensing for Planetary Rovers: Improved Terrain Classification and Thermal Inertia Estimation

   Yumi Iwashita, Kazuto Nakashima, Joseph Gatto, Shoya Higa, Norris Khoo, Ryo Kurazume, and Adrian Stoica

   In IEEE Robotics and Automation Letters (RA-L with IROS presentation), 2020

   Abs Paper

   Terrain classification is critically important for Mars rovers, which rely on it for planning and autonomous navigation. On-board terrain classification using visual information has limitations, and is sensitive to illumination conditions. Classification can be improved if one fuses visual imagery with additional infrared (IR) imagery of the scene, yet unfortunately there are no IR image sensors on the current Mars rovers. A virtual IR sensor, estimating IR from RGB imagery using deep learning, was proposed in the context of a MU-Net architecture. However, virtual IR estimation was limited by the fact that slope angle variations induce temperature differences within the same terrain. This paper removes this limitation, giving good IR estimates and as a consequence improving terrain classification by including the additional angle from the surface normal to the Sun and the measurement of solar radiation. The estimates are also useful when estimating thermal inertia, which can enhance slip prediction and small rock density estimation. Our approach is demonstrated in two applications. We collected a new data set to verify the effectiveness of the proposed approach and show its benefit by applying to the two applications.

5. MU-Net: Deep Learning-Based Thermal IR Image Estimation From RGB Image

   Yumi Iwashita, Kazuto Nakashima, Sir Rafol, Adrian Stoica, and Ryo Kurazume

   In IEEE Workshop on Perception Beyond the Visible Spectrum (in conjunction with CVPR), 2019

   Abs Paper Project

   Terrain imagery collected by satellite remote sensing or by rover on-board sensors is the primary source for terrain classification used in determining terrain traversibility and mission plans for planetary rovers. Mapping models between RGB and IR for terrain classes are learned from real RGB and IR data examples in the same or similar terrain. This paper adds a new class of deep learning architectures called MU-Net (Multiple U-Net) and shows its efficiency in deriving better RGB-to-IR mapping models, improving over past work the estimation of thermal IR images from incoming RGB images and learned RGB-IR mappings.

6. TU-Net and TDeepLab: Deep Learning-based Terrain Classification Robust to Illumination Changes, Combining Visible and Thermal Imagery

   Yumi Iwashita, Kazuto Nakashima, Adrian Stoica, and Ryo Kurazume

   In IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), 2019

   Abs Paper Project

   In this paper we propose two novel deep learning-based terrain classification methods robust to illumination changes. The use of cameras is challenged by a variety of factors, of most importance being the changes in illumination. On the other hand, since the temperature of various types of terrains depends on the thermal characteristics of the terrain, the terrain classification can be aided by utilizing the thermal information in addition to visible information. Thus we propose ’TU-Net (Two U-Net)’ based on the U-Net and ’TDeepLab (Two DeepLab)’ based on DeepLab, which combine visible and thermal images and train the network robust to illumination changes implicitly. To improve the network’s learning capability, we expand the proposed methods to the Siamese-based method, which explicitly trains the network to be robust to illumination changes. We also investigate multiple options to fuse the visible and thermal images at at the bottom layer, middle layer, or the top layer of the network. We evaluate the proposed methods with a challenging new dataset consisting of visible and thermal images, which were collected from 10 am till 5 pm (after sunset), and we show the effectiveness of the proposed methods.

7. Fourth-person Captioning: Describing Daily Events by Uni-supervised and Tri-regularized Training

   Kazuto Nakashima, Yumi Iwashita, Akihiro Kawamura, and Ryo Kurazume

   In IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2018

   Abs Paper

   We aim to develop a supporting system which enhances the ability of human’s short-term visual memory in an intelligent space where the human and a service robot coexist. Particularly, this paper focuses on how we can interpret and record diverse and complex life events on behalf of humans, from a multi-perspective viewpoint. We propose a novel method named "fourth-person captioning", which generates natural language descriptions by summarizing visual contexts complementarily from three types of cameras corresponding the first-, second-, and third-person viewpoint. We first extend the latest image captioning technique and design a new model to generate a sequence of words given the multiple images. Then we provide an effective training strategy that needs only annotations supervising images from a single viewpoint in a general caption dataset and unsupervised triplet instances in the intelligent space. As the three types of cameras, we select a wearable camera on the human, a robot-mounted camera, and an embedded camera, which can be defined as the first-, second-, and third-person viewpoint, respectively. We hope our work will accelerate a cross-modal interaction bridging the human’s egocentric cognition and multi-perspective intelligence.

8. Virtual Sensors Determined Through Machine Learning

   Yumi Iwashita, Adrian Stoica, Kazuto Nakashima, Ryo Kurazume, and Jim Torresen

   In World Automation Congress, 2018

   Abs Paper

   We propose a method that increases the capability of a conventional sensor, transforming it into an enhanced virtual sensor. This paper focuses on a virtual thermal Infrared Radiation (IR) sensor based on a conventional visual (RGB) sensor. The estimation of thermal IR images can enhance the ability of terrain classification, which is crucial for autonomous navigation of rovers. The estimate in IR from visual band has inherent limitations, as these are different bands, yet correlations between visual RGB and thermal IR images exist, as different terrains, which visually may appear different, also have different thermal inertia. This paper describes the developed deep learning-based algorithm that estimates thermal IR images from RGB images of terrains, providing the feasibility of the idea with average 1.21 error [degree Celsius].

9. Recognizing Outdoor Scenes by Convolutional Features of Omni-Directional LiDAR Scans

   Kazuto Nakashima, Seungwoo Nham, Hojung Jung, Yumi Iwashita, Ryo Kurazume, and Oscar M Mozos

   In IEEE/SICE International Symposium on System Integration (SII), 2017

   Abs Paper

   We present a novel method for the outdoor scene categorization using 2D convolutional neural networks (CNNs) which take panoramic depth images obtained by a 3D laser scanner as input. We evaluate our approach in two outdoor scene datasets including six categories: coast, forest, indoor parking, outdoor parking, residential area, and urban area. Our results on both datasets (over 94%) outperform previous approaches and show the effectiveness of this approach for outdoor scene categorization using depth images. To analyze our trained networks we visualize the learned features by using two visualization methods.

10. Previewed Reality: Near-Future Perception System

    Yuta Horikawa, Asuka Egashira, Kazuto Nakashima, Akihiro Kawamura, and Ryo Kurazume

    In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2017

    Abs Paper

    This paper presents a near-future perception system named “Previewed Reality”. The system consists of an informationally structured environment (ISE), an immersive VR display, a stereo camera, an optical tracking system, and a dynamic simulator. In an ISE, a number of sensors are embedded, and information such as the position of furniture, objects, humans, and robots, is sensed and stored in a database. The position and orientation of the immersive VR display are also tracked by an optical tracking system. Therefore, we can forecast the next possible events using a dynamic simulator and synthesize virtual images of what users will see in the near future from their own viewpoint. The synthesized images, overlaid on a real scene by using augmented reality technology, are presented to the user. The proposed system can allow a human and a robot to coexist more safely by showing possible hazardous situations to the human intuitively in advance.

11. Feasibility Study of IoRT Platform “Big Sensor Box”

    Ryo Kurazume, Yoonseok Pyo, Kazuto Nakashima, Akihiro Kawamura, and Tokuo Tsuji

    In IEEE International Conference on Robotics and Automation (ICRA), 2017

    Finalist of Best Service Robotics Paper Award

    Abs Paper Project Code

    This paper proposes new software and hardware platforms named ROS-TMS and Big Sensor Box, respectively, for an informationally structured environment. We started the development of a management system for an informationally structured environment named Town Management System (TMS) in the Robot Town Project in 2005. Since then we have been continuing our efforts to improve performance and to enhance TMS functions. Recently, we launched a new version of TMS named ROS-TMS, which resolves some critical problems in TMS by adopting the Robot Operating System (ROS) and utilizing the high scalability and numerous resources of ROS. In this paper, we first discuss the structure of a software platform for the informationally structured environment and describe in detail our latest system, ROS-TMS version 4.0. Next, we introduce a hardware platform for the informationally structured environment named Big Sensor Box, in which a variety of sensors are embedded and service robots are operated according to the structured information under the management of ROS-TMS. Robot service experiments including a fetch-and-give task and autonomous control of a wheelchair robot are also conducted in Big Sensor Box.

12. Automatic Houseware Registration System for Informationally-Structured Environment

    Kazuto Nakashima, Julien Girard, Yumi Iwashita, and Ryo Kurazume

    In IEEE/SICE International Symposium on System Integration (SII), 2016

    Abs Paper

    To provide daily-life assistance appropriately by a service robot, the management of houseware’s information in a room or a house is an indispensable function. Especially, the information about what and where objects are in the environment are fundamental and critical knowledge. We can track housewares with high reliability by attaching markers such as RFID tags to them, however, markerless housewares management system is still useful since it is easy-to-use and low cost. In this work, we present an object management system using an egocentric vision and a region-based convolutional neural network (R-CNN) to automatically detect and register housewares. The proposed system consists of smart glasses equipped with a wearable camera, a cloud database which manages object information, and a processing server for detecting and registering housewares to the cloud database. We perform two experiments. First, we train the R-CNN on a newly-constructed dataset to detect various housewares and configure a houseware-specific detector. All systems are composed of ROS packages. Second, we conduct experiments for automatic housewares registration using the proposed system. We demonstrate that the proposed system can detect, recognize, and register housewares approximately in real time.

13. Fourth-Person Sensing for a Service Robot

    Kazuto Nakashima, Yumi Iwashita, Pyo Yoonseok, Asamichi Takamine, and Ryo Kurazume

    In IEEE Sensors, 2015

    Abs Paper

    This paper proposes a new concept named "fourth-person sensing" for a service robot. The proposed concept combines wearable sensors (the first-person viewpoint), sensors mounted on robots (the second-person viewpoint), and sensors embedded in the environment (the third-person viewpoint), and the disadvantages in individual sensors are compensated by combining sensory information from the first, second, and third-person viewpoints. The fourth-person sensing is effective to understand a user’s intention and a context of the scene, thus it enables to provide a proper service by a service robot. As one of applications of the fourth-person sensing, we develop a HCI system combining the first-person and the third-person sensing, and show the effectiveness of the proposed concept through robot service experiments.

14. Fourth-Person Sensing for Pro-active Services

    Yumi Iwashita, Kazuto Nakashima, Yoonseok Pyo, and Ryo Kurazume

    In International Conference on Emerging Security Technologies (EST), 2014

    Abs Paper

    Service robots, which co-exist with humans to provide various services, obtain information from sensors placed in an environment and/or sensors mounted on robots. In this paper we newly propose the concept of fourth-person sensing which combines wearable cameras (first-person sensing), sensors mounted on robots (second-person sensing), and distributed sensors in the environment (third-person sensing). The proposed concept takes advantages of all three sensing systems, while removing disadvantage of each of them. The first-person sensing can analyze what a person wearing a camera is doing and details around him/her, so the fourth-person sensing has chance to provide pro-active services, which are triggered by predicted human intention and difficult with the second- and third-person systems, by estimating his intention/behavior. We introduce an example scenario using the fourth-person sensing and show the effectiveness of the proposed concept through experiments.

Workshops

1. Multi-perspective Image Captioning for Human-Robot Symbiotic Scenes

   Kazuto Nakashima, and Ryo Kurazume

   In Joint Workshop on Machine Perception and Robotics, 2019
2. CNN based Beach Litter Classification using LiDAR

   Beomjoon Lee, Kazuto Nakashima, and Ryo Kurazume

   In Joint Workshop on Machine Perception and Robotics, 2019
3. Describing Daily Events in Intelligent Space via Fourth-person Perspective Images

   Kazuto Nakashima, and Ryo Kurazume

   In Joint Workshop on Machine Perception and Robotics, 2018

   Best Poster Presentation Award
4. A CNN-based Gait Recognition Robust to Low Resolution Images using Inter-image Difference

   Naoki Setoguchi, Kazuto Nakashima, Wu Tong, Yumi Iwashita, and Ryo Kurazume

   In Joint Workshop on Machine Perception and Robotics, 2018
5. Previewed Reality: Near-Future Perception System

   Yuta Horikawa, Asuka Egashira, Kazuto Nakashima, Akihiro Kawamura, and Ryo Kurazume

   In Joint Workshop on Machine Perception and Robotics, 2017
6. Navigation System of Personal Mobility in Informationally Structured/Unstructured Environments

   Yuuta Watanabe, Akio Shigekane, Kohei Matsumoto, Yongjin Jung, Kazuto Nakashima, Akihiro Kawamura, and Ryo Kurazume

   In Joint Workshop on Machine Perception and Robotics, 2017
7. Houseware Detection using Wearable Camera

   Kazuto Nakashima, Yumi Iwashita, and Ryo Kurazume

   In Joint Workshop on Machine Perception and Robotics, 2016
8. Gait Recognition using Convolutional Neural Networks

   Tong Wu, Kazuto Nakashima, Yumi Iwashita, and Ryo Kurazume

   In Joint Workshop on Machine Perception and Robotics, 2016

Domestic Conferences (in Japanese)

1. レトロフィット型バックホウ遠隔操縦システムの開発

   西浦 悠生, 中嶋 一斗, and 倉爪 亮

   In 日本機械学会ロボティクスメカトロニクス講演会, 2022
2. 転圧地盤評価のための分散型センサポッドの開発 -第2 報多点同期振動データの波形歪みに基づく地盤剛性の定量化-

   福田 健太郎, 中嶋 一斗, and 倉爪 亮

   In 日本機械学会ロボティクスメカトロニクス講演会, 2022
3. 陰的画像表現を用いた3D LiDARデータの深層生成モデリング

   中嶋 一斗, 岩下 友美, and 倉爪 亮

   In ロボティクスシンポジア, 2022
4. 転圧地盤評価のための分散型センサポッドの開発

   福田 健太郎, 中嶋 一斗, and 倉爪 亮

   In 計測自動制御学会システムインテグレーション部門講演会, 2021
5. 多層3D LiDARとLSTMを用いた距離・点群密度変化に頑健な歩容認証（第2報）

   安 正鎬, 山田 弘幸, 中嶋 一斗, and 倉爪 亮

   In 日本ロボット学会学術講演会, 2021
6. 同一人物間の歩容特徴交換によるデータ拡張を用いた歩容認証

   吉野 弘毅, 中嶋 一斗, 岩下 友美, and 倉爪 亮

   In 日本ロボット学会学術講演会, 2021
7. ユマニチュードによる立ち上がり動作介助における介助者と被介助者の身体にかかる反力の解析

   田中 彰人, 安 琪, 中嶋 一斗, and 倉爪 亮

   In 日本ロボット学会学術講演会, 2021
8. 確率的欠損表現を用いたLiDARデータの生成モデリング

   中嶋 一斗, and 倉爪 亮

   In 画像の認識理解シンポジウム, 2021
9. 多層3D LiDARとLSTMを用いた距離・点群密度変化に頑健な歩容認証

   Jeongho Ahn, 山田 弘幸, 中嶋 一斗, and 倉爪 亮

   In 日本ロボット学会学術講演会, 2020
10. LiDAR点群アップサンプリングのための欠損と反射率を考慮した深度マップ超解像

    Qiongyu Li, 中嶋 一斗, and 倉爪 亮

    In 画像の認識理解シンポジウム, 2020
11. 同一人物間の歩容特徴交換によるデータ拡張を用いた歩容認証

    吉野 弘毅, 中嶋 一斗, 岩下 友美, and 倉爪 亮

    In 画像の認識理解シンポジウム, 2020
12. レーザ反射画像を用いた機械学習による路面判別

    Beomjoon Lee, 中嶋 一斗, and 倉爪 亮

    In 計測自動制御学会システムインテグレーション部門講演会, 2019
13. 第四人称視点に基づく情報構造化空間の状況説明文生成 第2報 顕著領域クラスタリングによる視点間アテンションの統合

    中嶋 一斗, and 倉爪 亮

    In 日本ロボット学会学術講演会, 2019
14. 第四人称視点に基づく情報構造化空間の状況説明文生成

    中嶋 一斗, and 倉爪 亮

    In 日本ロボット学会学術講演会, 2018
15. 異なる画像間差分を入力とするCNNを用いた低解像度画像に頑強な歩容認証

    瀬戸口 直輝, 中嶋 一斗, 呉 桐, 岩下 友美, and 倉爪 亮

    In 画像の認識理解シンポジウム, 2018
16. 画像間差分とCNNを用いた低解像度画像による歩容認証

    瀬戸口 直輝, 中嶋 一斗, 呉 桐, 岩下 友美, and 倉爪 亮

    In 日本機械学会ロボティクスメカトロニクス講演会, 2018
17. レーザ反射画像を用いた機械学習による路面判別

    南 承佑, 中嶋 一斗, 倉爪 亮, and 関口 正一

    In 計測自動制御学会システムインテグレーション部門講演会, 2017
18. マルチモーダル全方位画像の共起性と循環性を考慮した畳込み特徴学習による一般屋外環境識別

    中嶋 一斗, 河村 晃宏, and 倉爪 亮

    In 日本ロボット学会学術講演会, 2017
19. 第四人称キャプショニング：相補性を有する分散視覚を用いたヒト-ロボット共生空間の状況記述

    中嶋 一斗, 岩下 友美, 河村 晃宏, and 倉爪 亮

    In 画像の認識理解シンポジウム, 2017

    MIRU学生奨励賞
20. 正負フレーム間差分を用いた深層学習による歩容認証

    呉 桐, 中嶋 一斗, 瀬戸口 直輝, 岩下 友美, and 倉爪 亮

    In 画像の認識理解シンポジウム, 2017
21. Previewed Reality 情報構造化空間における近未来可視化システム ―没入感ディスプレイを用いたシステム構築と実験―

    堀川 雄太, 中嶋 一斗, 河村 晃宏, and 倉爪 亮

    In 日本機械学会ロボティクスメカトロニクス講演会, 2017
22. 全周距離画像を入力とするConvolutional Neural Networkを用いた屋外環境の種別推定

    中嶋 一斗, Oscar Martinez Mozos, and 倉爪 亮

    In ロボティクスシンポジア, 2017
23. 情報構造化環境におけるスマートグラスとFaster R-CNNを用いた日常物品登録システムの開発

    中嶋 一斗, 岩下 友美, 高嶺 朝理, and 倉爪 亮

    In 日本機械学会ロボティクスメカトロニクス講演会, 2016
24. サービスロボットのための第4人称センシングの提案

    中嶋 一斗, 岩下 友美, ピョ ユンソク, 高嶺 朝理, and 倉爪 亮

    In 画像の認識理解シンポジウム, 2015
25. サービスロボットのための第4人称センシングの提案

    中嶋 一斗, 岩下 友美, ピョ ユンソク, 高嶺 朝理, and 倉爪 亮

    In 日本機械学会ロボティクスメカトロニクス講演会, 2015