检索结果-内蒙古大学图书馆

Target-Style-Aware Unsupervised Domain Adaptation for Object Detection

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第2期6卷 3825-3832页

作者： Yun, Woo-han Han, ByungOk Lee, Jaeyeon Kim, Jaehong Kim, Junmo Korea Adv Inst Sci & Technol Robot Program Daejeon 34129 South Korea ETRI Intelligent Robot Res Div Daejeon 34129 South Korea Korea Adv Inst Sci & Technol Sch Elect Engn Daejeon 34141 South Korea

Vision modules running on mobility platforms, such as robots and cars, often face challenging situations such as a domain shift where the distributions of training (source) data and test (target) data are different. The domain shift is caused by several variation factors, such as style, camera viewpoint, object appearance, object size, backgrounds, and scene layout. In this work, we propose an object detection training framework for unsupervised domain-style adaptation. The proposed training framework transfers target-style information to source samples and simultaneously trains the detection network with these target-stylized source samples in an end-to-end manner. The detection network can learn the target domain from the target-stylized source samples. The style is extracted from object areas obtained by using pseudo-labels to reflect the style of the object areas more than that of the irrelevant backgrounds. We empirically verified that the proposed methods improve detection accuracy in diverse domain shift scenarios using the Cityscapes, FoggyCityscapes, Sim10k, BDD100k, PASCAL, and Watercolor datasets.

关键词： deep learning for visual perception object detection segmentation and categorization transfer learning

来源：评论

学校读者我要写书评

暂无评论

LaneAF: Robust Multi-Lane Detection With Affinity Fields

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第4期6卷 7477-7484页

作者： Abualsaud, Hala Liu, Sean Lu, David B. Situ, Kenny Rangesh, Akshay Trivedi, Mohan M. Univ Calif San Diego Lab Intelligent & Safe Automobiles San Diego CA 92092 USA

This study presents an approach to lane detection involving the prediction of binary segmentation masks and per-pixel affinity fields. These affinity fields, along with the binary masks, can then be used to cluster lane pixels horizontally and vertically into corresponding lane instances in a post-processing step. This clustering is achieved through a simple row-by-row decoding process with little overhead;such an approach allows LaneAF to detect a variable number of lanes without assuming a fixed or maximum number of lanes. Moreover, this form of clustering is more interpretable in comparison to previous visual clustering approaches, and can be analyzed to identify and correct sources of error. Qualitative and quantitative results obtained on popular lane detection datasets demonstrate the model's ability to detect and cluster lanes effectively and robustly. Our proposed approach sets a new state-of-the-art on the challenging CULane dataset and the recently introduced Unsupervised LLAMAS dataset.

关键词： Object detection segmentation and categorization deep learning for visual perception

来源：评论

学校读者我要写书评

暂无评论

Panoster: End-to-End Panoptic Segmentation of LiDAR Point Clouds

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第2期6卷 3216-3223页

作者： Gasperini, Stefano Mahani, Mohammad-Ali Nikouei Marcos-Ramiro, Alvaro Navab, Nassir Tombari, Federico Tech Univ Munich Fac Comp Sci D-85748 Garching Germany BMW Grp D-80788 Munich Germany Johns Hopkins Univ Dept Comp Sci Baltimore MD 21218 USA Google CH-8002 Zurich Switzerland

Panoptic segmentation has recently unified semantic and instance segmentation, previously addressed separately, thus taking a step further towards creating more comprehensive and efficient perception systems. In this letter, we present Panoster, a novel proposal-free panoptic segmentation method for LiDAR point clouds. Unlike previous approaches relying on several steps to group pixels or points into objects, Panoster proposes a simplified framework incorporating a learning-based clustering solution to identify instances. At inference time, this acts as a class-agnostic segmentation, allowing Panoster to be fast, while outperforming prior methods in terms of accuracy. Without any post-processing, Panoster reached state-of-the-art results among published approaches on the challenging SemanticKITTI benchmark, and further increased its lead by exploiting heuristic techniques. Additionally, we showcase how our method can be flexibly and effectively applied on diverse existing semantic architectures to deliver panoptic predictions.

关键词： Computer vision for transportation deep learning for visual perception LiDAR point clouds panoptic segmentation

来源：评论

学校读者我要写书评

暂无评论

learning Occupancy Priors of Human Motion From Semantic Maps of Urban Environments

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第2期6卷 3248-3255页

作者： Rudenko, Andrey Palmieri, Luigi Doellinger, Johannes Lilienthal, Achim J. Arras, Kai O. Bosch Corp Res D-71272 Renningen Germany Orebro Univ Mobile Robot & Olfact Lab S-70182 Orebro Sweden Bosch Ctr Artificial Intelligence D-71272 Renningen Germany

Understanding and anticipating human activity is an important capability for intelligent systems in mobile robotics, autonomous driving, and video surveillance. While learning from demonstrations with on-site collected trajectory data is a powerful approach to discover recurrent motion patterns, generalization to new environments, where sufficient motion data are not readily available, remains a challenge. In many cases, however, semantic information about the environment is a highly informative cue for the prediction of pedestrian motion or the estimation of collision risks. In this work, we infer occupancy priors of human motion using only semantic environment information as input. To this end, we apply and discuss a traditional Inverse Optimal Control approach, and propose a novel approach based on Convolutional Neural Networks (CNN) to predict future occupancy maps. Our CNN method produces flexible context-aware occupancy estimations for semantically uniform map regions and generalizes well already with small amounts of training data. Evaluated on synthetic and real-world data, it shows superior results compared to several baselines, marking a qualitative step-up in semantic environment assessment.

关键词： deep learning for visual perception human detection and tracking human motion analysis human motion prediction semantic scene understanding

来源：评论

学校读者我要写书评

暂无评论

REDE: End-to-End Object 6D Pose Robust Estimation Using Differentiable Outliers Elimination

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第2期6卷 2886-2893页

作者： Hua, Weitong Zhou, Zhongxiang Wu, Jun Huang, Huang Wang, Yue Xiong, Rong Zhejiang Univ State Key Lab Ind Control Technol Hangzhou 310027 Zhejiang Peoples R China Zhejiang Univ Inst Cyber Syst & Control Hangzhou 310027 Zhejiang Peoples R China Beijing Inst Technol Beijing 100081 Peoples R China

Object 6D pose estimation is a fundamental task in many applications. Conventional methods solve the task by detecting and matching the keypoints, then estimating the pose. Recent efforts bringing deep learning into the problem mainly overcome the vulnerability of conventional methods to environmental variation due to the hand-crafted feature design. However, these methods cannot achieve end-to-end learning and good interpretability at the same time. In this letter, we propose REDE, a novel end-to-end object pose estimator using RGB-D data, which utilizes network for keypoint regression, and a differentiable geometric pose estimator for pose error back-propagation. Besides, to achieve better robustness when outlier keypoint prediction occurs, we further propose a differentiable outliers elimination method that regresses the candidate result and the confidence simultaneously. Via confidence weighted aggregation of multiple candidates, we can reduce the effect from the outliers in the final estimation. Finally, following the conventional method, we apply a learnable refinement process to further improve the estimation. The experimental results on three benchmark datasets show that REDE slightly outperforms the state-of-the-art approaches and is more robust to object occlusion. Our code is available at https://***/HuaWeitong/REDE.

关键词： deep learning for visual perception pose estimation RGB-D perception

来源：评论

学校读者我要写书评

暂无评论

Identifying Reflected Images From Object Detector in Indoor Environment Utilizing Depth Information

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第2期6卷 635-642页

作者： Park, Daehee Park, Yong-Hwa Korea Adv Inst Sci & Technol Dept Mech Engn Daejeon 34141 South Korea

We observed that mirror reflection severely degrades person detection performance in an indoor environment, which is an essential task for service robots. To address this problem, we propose a new real-time method to identify reflected virtual images in an indoor environment utilizing 3D depth information. Images reflected by the mirror are similar to real objects, so it is a non-trivial task to differentiate them. Conventional object detectors, which do not deal with this problem, obviously recognize reflected images as real objects. The proposed method compares the geometric relationship between the 3D spatial information of the detected object and its surrounding environment where the object locates. It analyzes the layout of surrounding indoor space utilizing semantic segmentation and plane detection method. With the estimated layout of indoor space, detected object candidates are examined whether they are real or reflected images utilizing 3D depth information. To verify the proposed method, a large indoor dataset was newly acquired and examined in a dedicated Living-lab environment. The performance of the algorithm is verified by comparing conventional detectors with the proposed method in the acquired Living-lab dataset.

关键词： Mirrors Indoor environment Three-dimensional displays Cameras Layout Image segmentation Detectors deep learning for visual perception human detection and tracking RGB-D perception service robotics

来源：评论

学校读者我要写书评

暂无评论

Geometry Guided Network for Point Cloud Registration

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第4期6卷 7270-7277页

作者： Min, Taewon Kim, Eunseok Shim, Inwook Agcy Def Dev Add Ground Technol Res Inst GTRI Daejeon South Korea

Point cloud registration is a well-known way to align two different point clouds via a rigid transform estimation in robotics and computer vision applications. In particular, deep learning-based methods have recently attempted to extract highly distinguishable point features for each point. However, it is still challenging to learn highly distinctive point features in different locations but in a similar shape, bringing performance limitations. To address this issue, we propose Geometry Guided Network, namely G(2) Net, for point cloud registration with spherical positional encoding method and unsupervised geometry consistency loss. Combined with self-attention, the positional encoding learns the globally unique features by assigning global geometric positional information into irregular 3D points. The uniqueness of each feature is further strengthened with geometric consistency loss across two different point cloud sets. We demonstrate that G(2) Net outperforms current state-of-the-arts models in point cloud registration tasks with both full and partial registration experiments for the ModelNet40 and Augmented ICL-NUIM datasets. Various visualizations on learned features are provided for demonstrating the global shape-awareness of our methodology.

关键词： deep learning for visual perception deep learning methods localization

来源：评论

学校读者我要写书评

暂无评论

Sparse-PointNet: See Further in Autonomous Vehicles

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第4期6卷 7049-7056页

作者： Wang, LeiChen Goldluecke, Bastian Daimler AG Dept Res & Dev Radar Sensor D-51147 Sindelfingen Germany Univ Konstanz Dept Comp Sci D-78464 Constance Germany

Since the density of LiDAR points reduces significantly with increasing distance, popular 3D detectors tend to learn spatial features from dense points and ignore very sparse points in the far range. As a result, their performance degrades dramatically beyond 50 meters. Motivated by the above problem, we introduce a novel approach to jointly detect objects from multimodal sensor data, with two main contributions. First, we leverage PointPainting [15] to develop a new key point sampling algorithm, which encodes the complex scene into a few representative points with approximately similar point density. Further, we fuse a dynamic continuous occupancy heatmap to refine the final proposal. In addition, we feed radar points into the network, which allows it to take into account additional cues. We evaluate our method on the widely used nuScenes dataset. Our method outperforms all state-of-the-art methods in the far range by a large margin and also achieves comparable performance in the near range.

关键词： Sensor fusion object detection deep learning for visual perception

来源：评论

学校读者我要写书评

暂无评论

LaserFlow: Efficient and Probabilistic Object Detection and Motion Forecasting

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第2期6卷 526-533页

作者： Meyer, Gregory P. Charland, Jake Pandey, Shreyash Laddha, Ankit Gautam, Shivam Vallespi-Gonzalez, Carlos Wellington, Carl K. Uber Adv Technol Grp Pittsburgh PA 15206 USA

In this work, we present LaserFlow, an efficient method for 3D object detection and motion forecasting from LiDAR. Unlike the previous work, our approach utilizes the native range view representation of the LiDAR, which enables our method to operate at the full range of the sensor in real-time without voxelization or compression of the data. We propose a new multi-sweep fusion architecture, which extracts and merges temporal features directly from the range images. Furthermore, we propose a novel technique for learning a probability distribution over future trajectories inspired by curriculum learning. We evaluate LaserFlow on two autonomous driving datasets and demonstrate competitive results when compared to the existing state-of-the-art methods.

关键词： Computer vision for transportation deep learning methods deep learning for visual perception

来源：评论

学校读者我要写书评

暂无评论

Multi-View Object Pose Refinement With Differentiable Renderer

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第2期6卷 2579-2586页

作者： Shugurov, Ivan Pavlov, Ivan Zakharov, Sergey Ilic, Slobodan Tech Univ Munich Dept Informat D-85748 Garching Germany Siemens AG D-81739 Munich Germany Toyota Res Inst Los Altos CA USA

This letter introduces a novel multi-view 6 DoF object pose refinement approach focusing on improving methods trained on synthetic data. It is based on the DPOD detector, which produces dense 2D-3D correspondences between the model vertices and the image pixels in each frame. We have opted for the use of multiple frames with known relative camera transformations, as it allows introduction of geometrical constraints via an interpretable ICP-like loss function. The loss function is implemented with a differentiable renderer and is optimized iteratively. We also demonstrate that a full detection and refinement pipeline, which is trained solely on synthetic data, can be used for auto-labeling real data. We perform quantitative evaluation on LineMOD, Occlusion, Homebrewed and YCB-V datasets and report excellent performance in comparison to the state-of-the-art methods trained on the synthetic and real data. We demonstrate empirically that our approach requires only a few frames and is robust to close camera locations and noise in extrinsic camera calibration, making its practical usage easier and more ubiquitous.

关键词： deep learning for visual perception object detection perception for grasping and manipulation

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：