检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Yamada, Jun Lee, Youngwoon Salhotra, Gautam Pertsch, Karl Pflueger, Max Sukhatme, Gaurav S. Lim, Joseph J. Englert, Peter Cognitive Learning for Vision and Robotics Lab United States Robotic Embedded Systems Laboratory Department of Computer Science University of Southern California United States

Deep reinforcement learning (RL) agents are able to learn contact-rich manipulation tasks by maximizing a reward signal, but require large amounts of experience, especially in environments with many obstacles that complicate exploration. In contrast, motion planners use explicit models of the agent and environment to plan collision-free paths to faraway goals, but suffer from inaccurate models in tasks that require contacts with the environment. To combine the benefits of both approaches, we propose motion planner augmented RL (MoPA-RL) which augments the action space of an RL agent with the long-horizon planning capabilities of motion planners. Based on the magnitude of the action, our approach smoothly transitions between directly executing the action and invoking a motion planner. We evaluate our approach on various simulated manipulation tasks and compare it to alternative action spaces in terms of learning efficiency and safety. The experiments demonstrate that MoPA-RL increases learning efficiency, leads to a faster exploration, and results in safer policies that avoid collisions with the environment. Videos and code are available at https://***/mopa-rl. Copyright © 2020, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

PSFHS Challenge Report: Pubic Symphysis and Fetal Head Segmentation from Intrapartum Ultrasound Images

arXiv

引用

arXiv 2024年

作者： Bai, Jieyun Zhou, Zihao Ou, Zhanhong Koehler, Gregor Stock, Raphael Maier-Hein, Klaus Elbatel, Marawan Martí, Robert Li, Xiaomeng Qiu, Yaoyang Gou, Panjie Chen, Gongping Zhao, Lei Zhang, Jianxun Dai, Yu Wang, Fangyijie Silvestre, Guénolé Curran, Kathleen Sun, Hongkun Xu, Jing Cai, Pengzhou Jiang, Lu Lan, Libin Ni, Dong Zhong, Mei Chen, Gaowen Campello, Víctor M. Lu, Yaosheng Lekadir, Karim Guangdong Provincial Key Laboratory of Traditional Chinese Medicine Informatization Jinan University Guangzhou China Auckland Bioengineering Institute The University of Auckland Auckland New Zealand Heidelberg Germany Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong Computer Vision and Robotics Group University of Girona Girona Spain Co. LTD Beijing China College of Artificial Intelligence Nankai University Tianjin China College of Computer Science and Electronic Engineering Hunan University Changsha China School of Medicine University College Dublin Dublin Ireland School of Computer Science University College Dublin Dublin Ireland School of Statistics & Mathematics Zhejiang Gongshang University Hangzhou China School of Computer Science & Engineering Chongqing University of Technology Chongqing China National-Regional Key Technology Engineering Laboratory for Medical Ultrasound Guangdong Provincial Key Laboratory of Biomedical Measurements and Ultrasound Imaging School of Biomedical Engineering Health Science Center Shenzhen University Shenzhen China NanFang Hospital of Southern Medical University Guangzhou China Zhujiang Hospital of Southern Medical University Guangzhou China Departament de Matemàtiques i Informàtica Universitat de Barcelona Barcelona Spain Barcelona Spain Institute The University of Auckland Private Bag 92019 Auckland1142 New Zealand

Segmentation of the fetal and maternal structures, particularly intrapartum ultrasound imaging as advocated by the International Society of Ultrasound in Obstetrics and Gynecology (ISUOG) for monitoring labor progression, is a crucial first step for quantitative diagnosis and clinical decision-making. This requires specialized analysis by obstetrics professionals, in a task that i) is highly time- and cost-consuming and ii) often yields inconsistent results. The utility of automatic segmentation algorithms for biometry has been proven, though existing results remain suboptimal. To push forward advancements in this area, the Grand Challenge on Pubic Symphysis-Fetal Head Segmentation (PSFHS) was held alongside the 26th International Conference on Medical Image Computing and computer Assisted Intervention (MICCAI 2023). This challenge aimed to enhance the development of automatic segmentation algorithms at an international scale, providing the largest dataset to date with 5,101 intrapartum ultrasound images collected from two ultrasound machines across three hospitals from two institutions. The scientific community's enthusiastic participation led to the selection of the top 8 out of 179 entries from 193 registrants in the initial phase to proceed to the competition's second stage. These algorithms have elevated the state-of-the-art in automatic PSFHS from intrapartum ultrasound images. A thorough analysis of the results pinpointed ongoing challenges in the field and outlined recommendations for future work. The top solutions and the complete dataset remain publicly available, fostering further advancements in automatic segmentation and biometry for intrapartum ultrasound imaging. © 2024, CC0.

关键词： Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

Understanding Adversarial Examples From the Mutual Influence of Images and Perturbations

Understanding Adversarial Examples From the Mutual Influence...

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Chaoning Zhang Philipp Benz Tooba Imtiaz In So Kweon Robotics and Computer Vision (RCV) Laboratory Korea Advanced Institute of Science and Technology (KAIST) Daejeon Korea Korea Advanced Institute of Science and Technology Daejeon South Korea

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

A wide variety of works have explored the reason for the existence of adversarial examples, but there is no consensus on the explanation. We propose to treat the DNN logits as a vector for feature representation, and exploit them to analyze the mutual influence of two independent inputs based on the Pearson correlation coefficient (PCC). We utilize this vector representation to understand adversarial examples by disentangling the clean images and adversarial perturbations, and analyze their influence on each other. Our results suggest a new perspective towards the relationship between images and universal perturbations: Universal perturbations contain dominant features, and images behave like noise to them. This feature perspective leads to a new method for generating targeted universal adversarial perturbations using random source images. We are the first to achieve the challenging task of a targeted universal attack without utilizing original training data. Our approach using a proxy dataset achieves comparable performance to the state-of-the-art baselines which utilize the original training dataset.

关键词： Perturbation methods Correlation Training data Feature extraction Training Task analysis Robustness

来源：评论

学校读者我要写书评

暂无评论

RTM3D: Real-Time Monocular 3D Detection from Object Keypoints for Autonomous Driving 16th

RTM3D: Real-Time Monocular 3D Detection from Object Keypoin...

引用

16th European Conference on computer vision, ECCV 2020

作者： Li, Peixuan Zhao, Huaici Liu, Pengfei Cao, Feidao Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Shenyang China Key Lab of Image Understanding and Computer Vision ShenyangLiaoning China

ISBN: (纸本)9783030585792

In this work, we propose an efficient and accurate monocular 3D detection framework in single shot. Most successful 3D detectors take the projection constraint from the 3D bounding box to the 2D box as an important component. Four edges of a 2D box provide only four constraints and the performance deteriorates dramatically with the small error of the 2D detector. Different from these approaches, our method predicts the nine perspective keypoints of a 3D bounding box in image space, and then utilize the geometric relationship of 3D and 2D perspectives to recover the dimension, location, and orientation in 3D space. In this method, the properties of the object can be predicted stably even when the estimation of keypoints is very noisy, which enables us to obtain fast detection speed with a small architecture. Training our method only uses the 3D properties of the object without any extra annotations, category-specific 3D shape priors, or depth maps. Our method is the first real-time system (FPS > 24) for monocular image 3D detection while achieves state-of-the-art performance on the KITTI benchmark. © 2020, Springer Nature Switzerland AG.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Multi-camera Torso Pose Estimation using Graph Neural Networks

arXiv

引用

arXiv 2020年

作者： Rodriguez-Criado, Daniel Bachiller, Pilar Bustos, Pablo Vogiatzis, George Manso, Luis J. School of Engineering and Applied Science Computer Science Department Aston University United Kingdom Robotics and Artificial Vision Laboratory Caceres School of Technology Universidad de Extremadura Spain

Estimating the location and orientation of humans is an essential skill for service and assistive robots. To achieve a reliable estimation in a wide area such as an apartment, multiple RGBD cameras are frequently used. Firstly, these setups are relatively expensive. Secondly, they seldom perform an effective data fusion using the multiple camera sources at an early stage of the processing pipeline. Occlusions and partial views make this second point very relevant in these scenarios. The proposal presented in this paper makes use of graph neural networks to merge the information acquired from multiple camera sources, achieving a mean absolute error below 125mm for the location and 10◦ for the orientation using low-resolution RGB images. The experiments, conducted in an apartment with three cameras, benchmarked two different graph neural network implementations and a third architecture based on fully connected layers. The software used has been released as open-source in a public repository1. Copyright © 2020, The Authors. All rights reserved.

关键词： Data fusion

来源：评论

学校读者我要写书评

暂无评论

An improved YOLO V3 for small vehicles detection in aerial images

An improved YOLO V3 for small vehicles detection in aerial i...

引用

作者： Moran Ju Haibo Luo Zhongbo Wang Shenyang Institute of Automation &Institutes for Robotics and Intelligent Manufacturing & Key Laboratory of Opt-Electronic Information Processing Chinese Academy of Sciences University of Chinese Academy of Sciences The Key Laboratory of Image Understanding and Computer Vision

Small vehicle detection in aerial images is a challenge in computer vision because small vehicles occupy less pixels and the environment around the small vehicles is complex. To improve the detection performance for the vehicles in aerial images, we propose an improved YOLO V3. The main contributions of our work include:(1)We redesign the backbone of YOLO V3 to select suitable scales for small vehicle detection in aerial images;(2) To make the improved YOLO V3 much stronger, we redesign the loss function of original YOLO V3 by GIOU loss and Focal loss;(3) To verify the performance of improved YOLO V3, we do the comparative experiments on VEDAI dataset. The experimental results show that the proposed method has obtained better performance than original YOLO V3 for small vehicle detection in aerial image.

关键词： Convolutional neural network Small vehicle detection YOLO V3 Aerial image

来源：评论

学校读者我要写书评

暂无评论

Self-slimmed vision Transformer

arXiv

引用

arXiv 2021年

作者： Zong, Zhuofan Li, Kunchang Song, Guanglu Wang, Yali Qiao, Yu Leng, Biao Liu, Yu School of Computer Science and Engineering Beihang University China SenseTime Research China ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China Shanghai AI Laboratory China

vision transformers (ViTs) have become the popular structures and outperformed convolutional neural networks (CNNs) on various vision tasks. However, such powerful transformers bring a huge computation burden, because of the exhausting token-to-token comparison. The previous works focus on dropping insignificant tokens to reduce the computational cost of ViTs. But when the dropping ratio increases, this hard manner will inevitably discard the vital tokens, which limits its efficiency. To solve the issue, we propose a generic self-slimmed learning approach for vanilla ViTs, namely SiT. Specifically, we first design a novel Token Slimming Module (TSM), which can boost the inference efficiency of ViTs by dynamic token aggregation. As a general method of token hard dropping, our TSM softly integrates redundant tokens into fewer informative ones. It can dynamically zoom visual attention without cutting off discriminative token relations in the images, even with a high slimming ratio. Furthermore, we introduce a concise Feature Recalibration Distillation (FRD) framework, wherein we design a reverse version of TSM (RTSM) to recalibrate the unstructured token in a flexible auto-encoder manner. Due to the similar structure between teacher and student, our FRD can effectively leverage structure knowledge for better convergence. Finally, we conduct extensive experiments to evaluate our SiT. It demonstrates that our method can speed up ViTs by 1.7× with negligible accuracy drop, and even speed up ViTs by 3.6× while maintaining 97% of their performance. Surprisingly, by simply arming LV-ViT with our SiT, we achieve new state-of-the-art performance on ImageNet. Code is available at https://***/Sense-X/SiT. © 2021, CC BY.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Automation of Predictive Maintenance: An Experimental Framework for Aircraft Landing Gear

Engineering Reports

引用

Engineering Reports 2025年第6期7卷

作者： Izaak Stanton Kamran Munir Ahsan Ikram Murad El-Bakry Centre for Machine Vision Bristol Robotics Laboratory (BRL) University of the West of England (UWE) Bristol UK Computer Science Research Centre (CSRC) School of Computing and Creative Technologies (SCC) College of Arts Technology and Environment (CATE) University of the West of England (UWE) Bristol UK Airbus Operations Ltd. Filton Bristol UK

Terabytes of data are recorded per flight by modern aircraft, providing a goldmine for predictive maintenance modeling, however, the required domain knowledge to build ML tools limits the number developed by airline manufacturers each year. Automated machine learning (AutoML) libraries can simplify model development, providing features such as automated preprocessing, model selection, and hyperparameter tuning to improve the efficiency and accessibility of the development workflow. This research presents an experimental analysis comparing industry-selected machine learning models and a hand-picked selection of automated machine-learning tools. The selected models were evaluated against real and synthetic time series datasets for different Airbus landing gear components across six datasets. The traditional and automated models obtained comparable MAE and F1 scores on regression and classification problems, accordingly, demonstrating the effectiveness of their use in this field. Based on these findings, a robust framework is proposed to utilize automated ML to optimize predictive maintenance tool development. This research is a stepping stone towards greater use of automation for predictive maintenance and presents insights into the field and AutoML. By integrating greater automation, AutoML can exploit more of the available data and deskill the development process to enable non-data scientists to produce health monitoring models for a more diverse pool of aircraft components.

关键词： aircraft maintenance automated machine learning machine learning predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

CertainOdom: Uncertainty Weighted Multi-task Learning Model for LiDAR Odometry Estimation

CertainOdom: Uncertainty Weighted Multi-task Learning Model ...

引用

IEEE International Conference on robotics and Biomimetics

作者： Leyuan Sun Guanqun Ding Yusuke Yoshiyasu Fumio Kanehiro Department of Intelligent and Mechanical Interaction Systems Graduate School of Science and Technology University of Tsukuba Tsukuba Ibaraki Japan CNRS-AIST Joint Robotics Laboratory (JRL) IRL National Institute of Advanced Industrial Science and Technology (AIST). Digital Architecture Research Center (DARC) National Institute of Advanced Industrial Science and Technology (AIST) Tokyo Japan Computer Vision Research Team Artificial Intelligence Research Center (AIRC) National Institute of Advanced Industrial Science and Technology (AIST) Japan

ISBN: (纸本)9781665481106

As a basic and indispensable module, LiDAR odom-etry estimation is widely used in robotics. In recent years, learning-based modeling approaches for odometry estimation have been validated to be feasible. However, it is necessary to consider security factors as the highest priorities when we apply the learning-based model to certain high-risk real-world scenarios, such as autonomous driving. The odometry uncertainty estimation provides more valuable information for downstream tasks, such as route planning and navigation. In this paper, we propose an end-to-end neural network (namely CertainOdom) to solve odometry and uncertainty estimation tasks by applying multi-task learning. Instead of using the manually-tuned hyper-parameters, we employ the learnable uncertainties to weigh the balance between the error of translation and orientation in the loss function. We evaluate the estimated trajectory and uncertainty on KITTI dataset. We also compare the robustness against the traditional geometry-based methods on our artificially degraded KITTI LiDAR dataset. Extensive experimental results show that our model with uncertainty weighted loss achieves competitive performance in LiDAR odometry estimation. We also explain our uncertainties qualitatively and quantitatively.

关键词： Uncertainty Laser radar Biological system modeling Estimation Multitasking Robustness Trajectory

来源：评论

学校读者我要写书评

暂无评论

Development of Hard Hat Wearing Monitoring System Using Deep Neural Networks with High Inference Speed

Development of Hard Hat Wearing Monitoring System Using Deep...

引用

International Russian Automation Conference (RusAutoCon)

作者： Nikolay Filatov Natalia Maltseva Aleksandr Bakhshiev Laboratory of computer vision systems The Russian State Scientific Center for Robotics and Technical Cybernetics Saint-Petersburg Russia Peter the Great St. Petersburg Polytechnic University Saint-Petersburg Russia

ISBN: (数字)9781728161303

ISBN: (纸本)9781728161310

Personal protection equipment is essential for safe working conditions on a construction sites and other industrial enterprises. However, there is a number of employee who violate safety precautions, thus, taking additional risks. To avoid accidents strict supervision should be applied. In this work an automatic hard hat wearing detection system from surveillance cameras is developed. To save computational resources small neural networks with high inference speed are applied. For the training of neural networks, a dataset consisting of several industrial scenes and 1478 images was composed. Frame based precision of SqueezeDet neural network for object detection was increased by 9% with the use of additional MobileNets classifier without significant decrease in operating speed. The overall system achieved 0.75 F1-score on a test dataset. Therefore, the developed hard hat wearing monitoring systems is suitable for enhancing on-site safety of workers.

关键词： Neural networks Safety Monitoring Object detection computer vision Training Feature extraction

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：