检索结果-内蒙古大学图书馆

CorsNet: 3D Point Cloud Registration by Deep Neural Network

IEEE roboticS AND AUTOMATION LETTERS 2020年第3期5卷 3960-3966页

作者： Kurobe, Akiyoshi Sekikawa, Yusuke Ishikawa, Kohta Saito, Hideo Keio Univ Dept Sci & Technol Yokohama Kanagawa 2238522 Japan Denso IT Lab Inc Tokyo 1500002 Japan

Point cloud registration is a key problem for robotics and computer vision communities. This represents estimating a rigid transform which aligns one point cloud to another. Iterative closest point (ICP) is a well-known classical method for this problem, yet it generally achieves high alignment only when the source and template point cloud are mostly pre-aligned. If each point cloud is far away or contains a repeating structure, the registration often fails because of being fallen into a local minimum. Recently, inspired by PointNet, several deep learning-based methods have been developed. PointNetLK is a representative approach, which directly optimizes the distance of aggregated features using gradient method by Jacobian. In this paper, we propose a point cloud registration system based on deep learning: CorsNet. Since CorsNet concatenates the local features with the global features and regresses correspondences between point clouds, not directly pose or aggregated features, more useful information is integrated than the conventional approaches. For comparison, we also developed a novel deep learning approach (DirectNet) that directly regresses the pose between point clouds. Through our experiments, we show that CorsNet achieves higher accuracy than not only the classic ICP method, but also the recently proposed learning-based proposal PointNetLK and DirectNet, including on seen and unseen categories.

关键词： Three-dimensional displays Feature extraction Transforms computer architecture Estimation Deep learning Network architecture computer vision for other robotic applications deep learning in robotics and automation perception for grasping and manipulation

来源：评论

学校读者我要写书评

暂无评论

HDR Reconstruction Based on the Polarization Camera

引用

IEEE roboticS AND AUTOMATION LETTERS 2020年第4期5卷 5113-5119页

作者： Wu, Xuesong Zhang, Hong Hu, Xiaoping Shakeri, Moein Fan, Chen Ting, Juiwen Natl Univ Def Technol Coll Intelligence Sci & Technol Changsha 410073 Peoples R China Univ Alberta Dept Comp Sci Edmonton AB T6G 2R3 Canada

The recent development of the on-chip micropolarizer technology has made it possible to acquire - with the same ease of operation as a conventional camera -spatially aligned and temporally synchronized polarization images simultaneously in four orientations. This development has created new opportunities for interesting applications including those in robotic% In this letter, we investigate the use of this sensor technology in highdynamic-range (HDR) imaging. Specifically, observing that natural light can be attenuated differently by varying the direction of the polarization filter, we treat the multiple images captured by the polarization camera as a set captured at different exposure times, useful to the reconstruction of an HDR image. In our approach, we first study the radiometric model of the polarization camera, and relate the polarizer direction, degree and angle of polarization of light to the exposure time of a pixel in the polarization images. Subsequently, by applying the standard radiometric calibration procedure of a camera, we recover the camera response function. With multiple polarization images at known pixel-specific exposure times, we can then proceed to estimate the irradiance maps from the images and generate an HDR image. Two datasets are created to evaluate our approach, and experimental results show the dynamic range by our approach can be increased by an amount dependent on light polarization. We also use two robotics experiments on feature matching and visual odometry to demonstrate the potential benefit of this increased dynamic range.

关键词： computer vision for other robotic applications sensor fusion

来源：评论

学校读者我要写书评

暂无评论

Low to High Dimensional Modality Hallucination Using Aggregated Fields of View

引用

IEEE roboticS AND AUTOMATION LETTERS 2020年第2期5卷 1983-1990页

作者： Gunasekar, Kausic Qiu, Qiang Yang, Yezhou Arizona State Univ Tempe AZ 85281 USA Duke Univ Durham NC 27708 USA

Real-world robotics systems deal with data from a multitude of modalities, especially for tasks such as navigation and recognition. The performance of those systems can drastically degrade when one or more modalities become inaccessible, due to factors such as sensors' malfunctions or adverse environments. Here, we argue modality hallucination as one effective way to ensure consistent modality availability and thereby reduce unfavorable consequences. While hallucinating data from a modality with richer information, e.g., RGB to depth, has been researched extensively, we investigate the more challenging low-to-high modality hallucination with interesting use cases in robotics and autonomous systems. We present a novel hallucination architecture that aggregates information from multiple fields of view of the local neighborhood to recover the lost information from the extant modality. The process is implemented by capturing a non-linear mapping between the data modalities and the learned mapping is used to aid the extant modality to mitigate the risk posed to the system in the adverse scenarios which involve modality loss. We also conduct extensive classification and segmentation experiments on UWRGBD and NYUD datasets and demonstrate that hallucination allays the negative effects of the modality loss. Implementation and models: https://***/kausic94/Hallucination.

关键词： Deep learning in robotics and automation robot safety modality hallucination computer vision for other robotic applications

来源：评论

学校读者我要写书评

暂无评论

Cross-View Semantic Segmentation for Sensing Surroundings

引用

IEEE roboticS AND AUTOMATION LETTERS 2020年第3期5卷 4867-4873页

作者： Pan, Bowen Sun, Jiankai Leung, Ho Yin Tiga Andonian, Alex Zhou, Bolei MIT Comp Sci & Artificial Intelligence Lab 77 Massachusetts Ave Cambridge MA 02139 USA Chinese Univ Hong Kong Dept Informat Engn Hong Kong Peoples R China

Sensing surroundings plays a crucial role in human spatial perception, as it extracts the spatial configuration of objects as well as the free space from the observations. To facilitate the robot perception with such a surrounding sensing capability, we introduce a novel visual task called Cross-view Semantic Segmentation as well as a framework named View Parsing Network (VPN) to address it. In the cross-view semantic segmentation task, the agent is trained to parse the first-view observations into a top-down-view semantic map indicating the spatial location of all the objects at pixel-level. The main issue of this task is that we lack the real-world annotations of top-down-view data. To mitigate this, we train the VPN in 3D graphics environment and utilize the domain adaptation technique to transfer it to handle real-world data. We evaluate our VPN on both synthetic and real-world agents. The experimental results show that our model can effectively make use of the information from different views and multi-modalities to understanding spatial information. Our further experiment on a LoCoBot robot shows that our model enables the surrounding sensing capability from 2D image input. Code and demo videos can be found at https://***.

关键词： Semantic scene understanding deep learning for visual perception visual learning visual-based navigation computer vision for other robotic applications

来源：评论

学校读者我要写书评

暂无评论

ACMarker: Acoustic Camera-Based Fiducial Marker System in Underwater Environment

引用

IEEE roboticS AND AUTOMATION LETTERS 2020年第4期5卷 5018-5025页

作者： Wang, Yusheng Ji, Yonghoon Liu, Dingyu Tamura, Yusuke Tsuchiya, Hiroshi Yamashita, Atsushi Asama, Hajime Univ Tokyo Dept Precis Engn Grad Sch Engn Tokyo 1138654 Japan JAIST Sch Mat Sci Nomi Ishikawa 9231211 Japan Tohoku Univ Dept Robot Grad Sch Engn Sendai Miyagi 9808577 Japan Wakachiku Construct Co Ltd Res Inst Chiba 2990268 Japan

ACMarker is an acoustic camera-based fiducial marker system designed for underwater environments. Optical camera-based fiducial marker systems have been widely used in computer vision and robotics applications such as augmented reality (AR), camera calibration, and robot navigation. However, in underwater environments, the performance of optical cameras is limited owing to water turbidity and illumination conditions. Acoustic cameras, which are forward-looking sonars, have been gradually applied in underwater situations. They can acquire high-resolution images even in turbid water with poor illumination. We propose methods to recognize a simply designed marker and to estimate the relative pose between the acoustic camera and the marker. The proposed system can be applied to various underwater tasks such as object tracking and localization of unmanned underwater vehicles. Simulation and real experiments were conducted to test the recognition of such markers and pose estimation based on the markers.

关键词： Marine robotics computer vision for other robotic applications

来源：评论

学校读者我要写书评

暂无评论

Multimodal Multispectral Imaging System for Small UAVs

引用

IEEE roboticS AND AUTOMATION LETTERS 2020年第2期5卷 1039-1046页

作者： Haavardsholm, Trym Vegard Skauli, Torbjorn Stahl, Annette Norwegian Def Res Estab FFI NO-2007 Kjeller Norway Norwegian Univ Sci & Technol NTNU Dept Engn Cybernet NO-7491 Trondheim Norway

Multispectral imaging is an attractive sensing modality for small unmanned aerial vehicles (UAVs) in numerous applications. The most compact spectral camera architecture is based on spectral filters in the focal plane. Vehicle movement can be used to scan the scene using multiple bandpass filters arranged perpendicular to the flight direction. With known camera trajectory and scene structure, it is possible to assemble a spectral image in software. In this letter, we demonstrate the feasibility of a novel concept for low-cost wide area multispectral imaging with integrated spectral consistency testing. Six bandpass filters are arranged in a periodically repeating pattern. Since different bands are recorded at different times and in different viewing directions, there is a risk of obtaining spectral artifacts in the image. We exploit the repeated sampling of bands to enable spectral consistency testing, which leads to significantly improved spectral integrity. In addition, an unfiltered region permits conventional 2D video imaging that can be used for image-based navigation and 3D reconstruction. The proposed multimodal imaging system was tested on a UAV in a realistic experiment. The results demonstrate that spectral reconstruction and consistency testing can be performed by image processing alone, based on visual simultaneous localization and mapping (VSLAM).

关键词： computer vision for other robotic applications Mapping Surveillance Systems

来源：评论

学校读者我要写书评

暂无评论

Unseen Salient Object Discovery for Monocular Robot vision

引用

IEEE roboticS AND AUTOMATION LETTERS 2020年第2期5卷 1484-1491页

作者： Chan, Darren M. Riek, Laurel D. Univ Calif San Diego La Jolla CA 92093 USA

A key challenge in robotics is the capability to perceive unseen objects, which can improve a robot's ability to learn from and adapt to its surroundings. One approach is to employ unsupervised, salient object discovery methods, which has shown promise in the computer vision literature. However, most state-of-the-art methods are unsuitable for robotics because they are limited to processing whole video segments before discovering objects, which can constrain real-time perception. To address these gaps, we introduce Unsupervised Foraging of Objects (UFO), a novel, unsupervised, salient object discovery method designed for monocular robot vision. We designed UFO with a parallel discover-prediction paradigm, permitting it to discover arbitrary, salient objects on a frame-by-frame basis, which can help robots to engage in scalable object learning. We compared UFO to the two fastest and most accurate methods for unsupervised salient object discovery (Fast Segmentation and Saliency-Aware Geodesic), and show that UFO 6.5 times faster, achieving state-of-the-art precision, recall, and accuracy. Furthermore our evaluation suggests that UFO is robust to real-world perception challenges encountered by robots, including moving cameras and moving objects, motion blur, and occlusion. It is our goal that this work will be used with other robot perception methods, to design robots that can learn novel object concepts, leading to improved autonomy.

关键词： Object detection segmentation and categorization computer vision for other robotic applications

来源：评论

学校读者我要写书评

暂无评论

Automated High-Productivity Microinjection System for Adherent Cells

引用

IEEE roboticS AND AUTOMATION LETTERS 2020年第2期5卷 1167-1174页

作者： Pan, Fei Chen, Shuxun Jiao, Yang Guan, Zhangyan Shakoor, Adnan Sun, Dong City Univ Hong Kong Dept Biomed Engn Hong Kong Peoples R China

Automated microinjection systems for suspension cells have been studied for years. Nevertheless, microinjection systems for adherent cells still suffer from laborious manual operations and low productivity. This paper presents a new automated microinjection system with high productivity for adherent cells. This system enhances productivity through four approaches. First, cells are detected automatically to replace manual selections. Second, the injection paths of detected cells are optimized rapidly to save time. Third, the penetration depth is adjusted adaptively according to the moving plane of the dish holder plate. Finally, constant outflow-based injection is adopted to minimize clogging. The first three approaches aim to improve the injection speed, and the last one aims to extend the usage time of micropipettes. Experiments of massive injections on MC3T3-E1 cells are performed to evaluate cell detection efficiency, injection speed, success rate, and survival rate. Results confirm that the system allows injections of over 1500 cells in one hour without much training and preparation a priori.

关键词： Biological cell manipulation computer vision for other robotic applications object detection segmentation and categorization

来源：评论

学校读者我要写书评

暂无评论

Sensor Transfer: Learning Optimal Sensor Effect Image Augmentation for Sim-to-Real Domain Adaptation

引用

IEEE roboticS AND AUTOMATION LETTERS 2019年第3期4卷 2431-2438页

作者： Carlson, Alexandra Skinner, Katherine A. Vasudevan, Ram Johnson-Roberson, Matthew Univ Michigan Robot Inst Ann Arbor MI 48109 USA Univ Michigan Dept Mech Engn Ann Arbor MI 48109 USA Univ Michigan Dept Naval Architecture & Marine Engn Ann Arbor MI 48109 USA

Performance on benchmark datasets has drastically improved with advances in deep learning. Still, cross-dataset generalization performance remains relatively low due to the domain shift that can occur between two different datasets. This domain shift is especially exaggerated between synthetic and real datasets. Significant research has been done to reduce this gap, specifically via modeling variation in the spatial layout of a scene, such as occlusions, and scene environmental factors, such as time of day and weather effects. However, few works have addressed modeling the variation in the sensor domain as a means of reducing the synthetic to real domain gap. The camera or sensor used to capture a dataset introduces artifacts into the image data, which are unique to the sensor model, suggesting that sensor effects may also contribute to domain shift. To address this, we propose a learned augmentation network composed of physically-based augmentation functions. Our proposed augmentation pipeline transfers specific effects of the sensor model-chromatic aberration, blur, exposure, noise, and color temperature-from a real dataset to a synthetic dataset. We provide experiments which demonstrate that augmenting synthetic training datasets with the proposed learned augmentation framework reduces the domain gap between synthetic and real domains for object detection in urban driving scenes.

关键词： Deep Learning in robotics and Automation Visual Learning computer vision for other robotic applications Simulation and Animation

来源：评论

学校读者我要写书评

暂无评论

VUNet: Dynamic Scene View Synthesis for Traversability Estimation Using an RGB Camera

引用

IEEE roboticS AND AUTOMATION LETTERS 2019年第2期4卷 2062-2069页

作者： Hirose, Noriaki Sadeghian, Ann R. Xia, Fei Martin-Martin, Roberto Savarese, Silvio Stanford Univ Comp Sci Dept Stanford CA 94305 USA

We present VUNet, a novel view(VU) synthesis method for mobile robots in dynamic environments, and its application to the estimation of future traversability. Our method predicts future images for given virtual robot velocity commands using only RGB images at previous and current time steps. The future images result from applying two types of image changes to the previous and current images: first, changes caused by different camera pose. Second, changes due to the motion of the dynamic obstacles. We learn to predict these two types of changes disjointly using two novel network architectures, SNet and DNet. We combine SNet and DNet to synthesize future images that we pass to our previously presented method GONet [N. Hirose, A. Sadeghian, M. Vazquez, P. Goebel, and S. Savarese, "Gonet: A semi-supervised deep learning approach for traversability estimation," in Proc. IEEE International Conference on Intelligent Robots and Systems, 2018, pp. 3044-3051] to estimate the traversable areas around the robot. Our quantitative and qualitative evaluation indicate that our approach for view synthesis predicts accurate future images in both static and dynamic environments. We also show that these virtual images can be used to estimate future traversability correctly. We apply our view synthesis-based traversability estimation method to two applications for assisted teleoperation.

关键词： Robot safety computer vision for other robotic applications collision avoidance

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：