检索结果-内蒙古大学图书馆

TransDSSL: Transformer Based Depth Estimation via Self-Supervised learning

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第4期7卷 10969-10976页

作者： Han, Daechan Shin, Jeongmin Kim, Namil Hwang, Soonmin Choi, Yukyung Sejong Univ Sch Intelligent Mechatron Engn Seoul 05006 South Korea Naver Labs Gyeonggi Do 13561 South Korea Carnegie Mellon Univ Pittsburgh PA 15213 USA

Recently, transformers have been widely adopted for various computer vision tasks and show promising results due to their ability to encode long-range spatial dependencies in an image effectively. However, very few studies on adopting transformers in self-supervised depth estimation have been conducted. When replacing the CNN architecture with the transformer in self-supervised learning of depth, we encounter several problems such as problematic multi-scale photometric loss function when used with transformers and, insufficient ability to capture local details. In this letter, we propose an attention-based decoder module, Pixel-Wise Skip Attention (PWSA), to enhance fine details in feature maps while keeping global context from transformers. In addition, we propose utilizing self-distillation loss with single-scale photometric loss to alleviate the instability of transformer training by using correct training signals. We demonstrate that the proposed model performs accurate predictions on large objects and thin structures that require global context and local details. Our model achieves state-of-the-art performance among the self-supervised monocular depth estimation methods on KITTI and DDAD benchmarks.

关键词： deep learning for visual perception computer vision for transportation visual learning

来源：评论

学校读者我要写书评

暂无评论

Tracker Meets Night: A Transformer Enhancer for UAV Tracking

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第2期7卷 3866-3873页

作者： Ye, Junjie Fu, Changhong Cao, Ziang An, Shan Zheng, Guangze Li, Bowen Tongji Univ Sch Mech Engn Shanghai 201804 Peoples R China Tongji Univ Sch Automot Studies Shanghai 201804 Peoples R China JD COM Inc Tech & Data Ctr Beijing 100108 Peoples R China

Most previous progress in object tracking is realized in daytime scenes with favorable illumination. State-of-the-arts can hardly carry on their superiority at night so far, thereby considerably blocking the broadening of visual tracking-related unmanned aerial vehicle (UAV) applications. To realize reliable UAV tracking at night, a spatial-channel Transformer-based low-light enhancer (namely SCT), which is trained in a novel task-inspired manner, is proposed and plugged prior to tracking approaches. To achieve semantic-level low-light enhancement targeting the high-level task, the novel spatial-channel attention module is proposed to model global information while preserving local context. In the enhancement process, SCT denoises and illuminates nighttime images simultaneously through a robust non-linear curve projection. Moreover, to provide a comprehensive evaluation, we construct a challenging nighttime tracking benchmark, namely DarkTrack2021, which contains 110 challenging sequences with over 100 K frames in total. Evaluations on both the public UAVDark135 benchmark and the newly constructed DarkTrack2021 benchmark show that the task-inspired design enables SCT with significant performance gains for nighttime UAV tracking compared with other top-ranked low-light enhancers. Real-world tests on a typical UAV platform further verify the practicability of the proposed approach. The DarkTrack2021 benchmark and the code of the proposed approach are publicly available at https://***/vision4robotics/SCT.

关键词： Transformers Task analysis Feature extraction Autonomous aerial vehicles visualization Target tracking Lighting Aerial systems applications deep learning for visual perception data sets for robotic vision low-light enhancement nighttime tracking spatial-channel transformer

来源：评论

学校读者我要写书评

暂无评论

Multi-Dimensional Cooperative Network for Stereo Matching

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第1期7卷 581-587页

作者： Chen, Wei Jia, Xiaogang Wu, Mingfei Liang, Zhengfa Natl Univ Def Technol Dept Comp Sci Changsha 410073 Peoples R China

The dimensions of cost volumes and corresponding aggregation networks play a critical role in balancing the speed and accuracy for stereo matching. Current most 2D stereo networks based on 3D cost volumes are speedy but poor in precision, while 3D stereo networks with 4D volumes are slow but precise. To tackle this problem, we propose a novel stereo framework for combining 2D and 3D networks. The disparity range generated by the 2D network is used to guide the 3D network and reduce the computational complexity. Meanwhile, the 3D network can refine the rough disparity from coarse to fine. Through the cooperation of 2D and 3D networks, our method can achieve accurate stereo results at a fast speed. We evaluate our method on three popular public benchmark datasets. Experimental results from the KITTI official website show that, our method can achieve similar accuracy with other 3D stereo networks (PSMNet, GCNet, GwcNet, etc.) at a significantly faster speed. The ablation studies further demonstrate the facticity and reasonability of our propose method.

关键词： Computer vision for automation deep learning for visual perception RGB-D perception

来源：评论

学校读者我要写书评

暂无评论

learning Cross-Scale visual Representations for Real-Time Image Geo-Localization

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第2期7卷 5087-5094页

作者： Zhang, Tianyi Johnson-Roberson, Matthew Univ Michigan Inst Robot Ann Arbor MI 48109 USA Univ Michigan Dept Naval Architecture & Marine Engn Ann Arbor MI 48109 USA

Robot localization remains a challenging task in GPS denied environments. State estimation approaches based on local sensors, e.g. cameras or IMUs, are drifting-prone for long-range missions as error accumulates. In this study, we aim to address this problem by localizing image observations in a 2D multimodal geospatial map. We introduce the cross-scale(1) dataset and a methodology to produce additional data from cross-modality sources. We propose a framework that learns cross-scale visual representations without supervision. Experiments are conducted on data from two different domains, underwater and aerial. In contrast to existing studies in cross-view image geo-localization, our approach a) performs better on smaller-scale multi-modal maps;b) is more computationally efficient for real-time applications;c) can serve directly in concert with state estimation pipelines.(2)

关键词： deep learning for visual perception marine robotics representation learning

来源：评论

学校读者我要写书评

暂无评论

LoopNet: Where to Focus? Detecting Loop Closures in Dynamic Scenes

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第2期7卷 2031-2038页

作者： Osman, Hussein Darwish, Nevin Bayoumi, AbdElMoniem Cairo Univ Dept Comp Engn Fac Engn Giza 12613 Egypt

Loop closure detection is essential in visual simultaneous localization and mapping systems to recognize previously visited scenes, reducing pose and map estimates uncertainty. However, loop closure detection is highly challenging due to perceptual aliasing and scene variations in real-world environments caused by dynamic objects, changes in viewpoint, and illumination variations. This paper introduces a novel plug-and-play model, LoopNet, to find similarities between scenes via determining key landmarks to focus on without being distracted by scene variations. This proposed multi-scale attention-based Siamese convolutional model learns feature embeddings that focus on the discriminative objects in the scene instead of holistic features. We show that our method outperforms the state-of-the-art approaches in indoor and outdoor environments while being robust to scene variations and perceptual aliasing.

关键词： deep learning for visual perception SLAM localization

来源：评论

学校读者我要写书评

暂无评论

CertainNet: Sampling-Free Uncertainty Estimation for Object Detection

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第2期7卷 698-705页

作者： Gasperini, Stefano Haug, Jan Mahani, Mohammad-Ali Nikouei Marcos-Ramiro, Alvaro Navab, Nassir Busam, Benjamin Tombari, Federico Tech Univ Munchen TUM Fac Comp Sci D-857481 Garching Germany BMW Grp D-80788 Munich Germany Tech Univ Munchen TUM Fac Comp Sci D-85748 Garching Germany Johns Hopkins Univ Dept Comp Sci Baltimore MD 21218 USA Google CH-8002 Zurich Switzerland

Estimating the uncertainty of a neural network plays a fundamental role in safety-critical settings. In perception for autonomous driving, measuring the uncertainty means providing additional calibrated information to downstream tasks, such as path planning, that can use it towards safe navigation. In this work, we propose a novel sampling-free uncertainty estimation method for object detection. We call it CertainNet, and it is the first to provide separate uncertainties for each output signal: objectness, class, location and size. To achieve this, we propose an uncertainty-aware heatmap, and exploit the neighboring bounding boxes provided by the detector at inference time. We evaluate the detection performance and the quality of the different uncertainty estimates separately, also with challenging out-of-domain samples: BDD100K and nuImages with models trained on KITTI. Additionally, we propose a new metric to evaluate location and size uncertainties. When transferring to unseen datasets, CertainNet generalizes substantially better than previous methods and an ensemble, while being real-time and providing high quality and comprehensive uncertainty estimates.

关键词： Computer vision for transportation deep learning for visual perception uncertainty estimation object detection

来源：评论

学校读者我要写书评

暂无评论

DiffSRL: learning Dynamical State Representation for Deformable Object Manipulation With Differentiable Simulation

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第4期7卷 9533-9540页

作者： Chen, Sirui Liu, Yunhao Yao, Shang Wen Li, Jialong Fan, Tingxiang Pan, Jia Univ Hong Kong Hong Kong Peoples R China Ctr Garment Prod Ltd Hong Kong Peoples R China

Dynamic state representation learning is essential for robot learning. Good latent space that can accurately describe dynamic transition and constraints can significantly accelerate reinforcement learning training as well as reduce motion planning complexity. However, deformable object have very complicated dynamics and is hard to be represented directly by a neural network without any prior physics information. We propose DiffSRL, an end-to-end dynamic state representation learning pipeline that uses differentiable physics engine to teach neural network how to represent high dimensional pointcloud data collected from deformable objects. Our specially designed loss function can guide neural network aware physics constraints and feasibility. We benchmark the performance of our methods as well as other state representation algorithms with multiple downstream tasks on PlasticineLab. Our model demonstrates superior performance most of the time on all tasks. We also demonstrate our model's performance in real hardware setting with two manipulation tasks on a UR-5 robot arm.

关键词： Representation learning deep learning for visual perception deep learning in grasph and manipulation

来源：评论

学校读者我要写书评

暂无评论

Continual Adaptation of Semantic Segmentation Using Complementary 2D-3D Data Representations

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第4期7卷 11665-11672页

作者： Frey, Jonas Blum, Hermann Milano, Francesco Siegwart, Roland Cadena, Cesar Swiss Fed Inst Technol Robot Syst Lab CH-8003 Zurich Switzerland Swiss Fed Inst Technol Autonomous Syst Lab Zurich Switzerland

Semantic segmentation networks are usually pretrained once and not updated during deployment. As a consequence, misclassifications commonly occur if the distribution of the training data deviates from the one encountered during the robot's operation. We propose to mitigate this problem by adapting the neural network to the robot's environment during deployment, without any need for external supervision. Leveraging complementary data representations, we generate a supervision signal, by probabilistically accumulating consecutive 2D semantic predictions in a volumetric 3D map. We then train the network on renderings of the accumulated semantic map, effectively resolving ambiguities and enforcing multi-view consistency through the 3D representation. In contrast to scene adaptation methods, we aim to retain the previously-learned knowledge, and therefore employ a continual learning experience replay strategy to adapt the network. Through extensive experimental evaluation, we show successful adaptation to real-world indoor scenes both on the ScanNet dataset and on in-house data recorded with an RCB-D sensor. Our method increases the segmentation accuracy on average by 9.9% compared to the fixed pre-trained neural network, while retaining knowledge from the pre-training dataset.

关键词： Continual learning deep learning for visual perception semantic scene understanding

来源：评论

学校读者我要写书评

暂无评论

Bayesian deep Neural Networks for Supervised learning of Single-View Depth

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第2期7卷 2565-2572页

作者： Rodriguez-Puigvert, Javier Martinez-Cantin, Ruben Civera, Javier Univ Zaragoza I3A Zaragoza 50018 Spain

Uncertainty quantification is essential for robotic perception, as overconfident or point estimators can lead to collisions and damages to the environment and the robot. In this letter, we evaluate scalable approaches to uncertainty quantification in single-view supervised depth learning, specifically MC dropout and deep ensembles. For MC dropout, in particular, we explore the effect of the dropout at different levels in the architecture. We show that adding dropout in all layers of the encoder brings better results than other variations found in the literature. This configuration performs similarly to deep ensembles with a much lower memory footprint, which is relevant for applications. Finally, we explore the use of depth uncertainty for pseudo-RGBD ICP and demonstrate its potential to estimate accurate two-view relative motion with the real scale.

关键词： deep learning for visual perception deep learning methods and probabilistic inference

来源：评论

学校读者我要写书评

暂无评论

Design and Control of a Highly Redundant Rigid-flexible Coupling Robot to Assist the COVID-19 Oropharyngeal-Swab Sampling

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第2期7卷 1856-1863页

作者： Hu, Yingbai Li, Jian Chen, Yongquan Wang, Qiwen Chi, Chuliang Zhang, Heng Gao, Qing Lan, Yuanmin Li, Zheng Mu, Zonggao Sun, Zhenglong Knoll, Alois Shenzhen Inst Artificial Intelligence & Robot Soc Shenzhen 518129 Peoples R China Tech Univ Munich Chair Robot Artificial Intelligence & Real Time S D-85748 Munich Germany Chinese Univ Hong Kong Inst Robot & Intelligent Mfg Shenzhen 518172 Peoples R China Chinese Univ Hong Kong Sch Sci & Engn Shenzhen 518172 Peoples R China Longgang Dist Peoples Hosp Shenzhen 518172 Peoples R China Chinese Univ Hong Kong Dept Surg Hong Kong Peoples R China Chinese Univ Hong Kong Chow Yuk Ho Technol Ctr Innovat Med Hong Kong Peoples R China Shandong Univ Technol Sch Mech Engn Zibo 255000 Peoples R China

The outbreak of novel coronavirus pneumonia (COVID-19) has caused mortality and morbidity worldwide. Oropharyngeal-swab (OP-swab) sampling is widely used for the diagnosis of COVID-19 in the world. To avoid the clinical staff from being affected by the virus, we developed a 9-degree-of-freedom (DOF) rigid-flexible coupling (RFC) robot to assist the COVID-19 OP-swab sampling. This robot is composed of a visual system, UR5 robot arm, micro-pneumatic actuator and force-sensing system. The robot is expected to reduce risk and free up the clinical staff from the long-term repetitive sampling work. Compared with a rigid sampling robot, the developed force-sensing RFC robot can facilitate OP-swab sampling procedures in a safer and softer way. In addition, a varying-parameter zeroing neural network-based optimization method is also proposed for motion planning of the 9-DOF redundant manipulator. The developed robot system is validated by OP-swab sampling on both oral cavity phantoms and volunteers.

关键词： deep learning for visual perception medical robots and systems redundant robots task and motion planning

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：