检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Alberb, Muhammad Elbatel, Marawan Elgebaly, Aya Montoya-Del-Angel, Ricardo Li, Xiaomeng Martí, Robert Computer Vision and Robotics Institute University of Girona Spain The Hong Kong University of Science and Technology Hong Kong

Digital Breast Tomosynthesis (DBT) is an advanced breast imaging modality that offers superior lesion detection accuracy compared to conventional mammography, albeit at the trade-off of longer reading time. Accelerating lesion detection from DBT using deep learning is hindered by limited data availability and huge annotation costs. A possible solution to this issue could be to leverage the information provided by a more widely available modality, such as mammography, to enhance DBT lesion detection. In this paper, we present a novel framework, CoMoTo, for improving lesion detection in DBT. Our framework leverages unpaired mammography data to enhance the training of a DBT model, improving practicality by eliminating the need for mammography during inference. Specifically, we propose two novel components, Lesion-specific Knowledge Distillation (LsKD) and Intra-modal Point Alignment (ImPA). LsKD selectively distills lesion features from a mammography teacher model to a DBT student model, disregarding background features. ImPA further enriches LsKD by ensuring the alignment of lesion features within the teacher before distilling knowledge to the student. Our comprehensive evaluation shows that CoMoTo is superior to traditional pretraining and image-level KD, improving performance by 7% Mean Sensitivity under low-data setting. Our code is available at https://***/Muhammad-Al-Barbary/CoMoTo. Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Tracking method for Human computer Interaction using Wii Remote

Tracking method for Human Computer Interaction using Wii Rem...

引用

International Conference on Emerging Trends in robotics and Communication Technologies (INTERACT)

作者： L Bharath S Shashank V S Nageli Sangeeta Shrivastava S Rakshit BNM Institute of Technology Bangalore India Computer Vision Group Center for Artificial Intelligence and Robotics Bangalore India

Over the years the techniques and methods that have been used to interact with the computers have evolved significantly. From the primitive use of punch cards to the latest touch screen panels we can see the vast improvement in interaction with the system. The same applies to the projection technology for creating various geometric displays. Researchers are exploring new ways of projection and interaction technologies to create `illusion' that can reshape our perception and interaction methodologies. In this paper we implemented (Infrared) IR light source tracking system which can be used for tracking single and multiple IR light source positions and can be used effectively in optical tracking problems such as tracking head position which is all pervasive requirement in a Virtual Reality System. We present a method of mapping IR light source position and orientation to an image. We defined the interaction techniques for an image manipulations with the help of fingers such as zoom, tilt/rotate, scale etc. We can extend our tracking capabilities to implement the touch screen feature to commercial applications. The paper illustrates the hardware and software used for implementing IR light source tracking based applications.

关键词： Head Bluetooth Light emitting diodes Cameras Tracking Software Libraries

来源：评论

学校读者我要写书评

暂无评论

SR-LSTM: State Refinement for LSTM towards Pedestrian Trajectory Prediction

SR-LSTM: State Refinement for LSTM towards Pedestrian Trajec...

引用

IEEE/CVF Conference on computer vision and Pattern Recognition

作者： Pu Zhang Wanli Ouyang Pengfei Zhang Jianru Xue Nanning Zheng Institute of Artificial Intelligence and Robotics Xian Jiaotong University The University of Sydney SenseTime Computer Vision Research Group

ISBN: (纸本)9781728132945

In crowd scenarios, reliable trajectory prediction of pedestrians requires insightful understanding of their social behaviors. These behaviors have been well investigated by plenty of studies, while it is hard to be fully expressed by hand-craft rules. Recent studies based on LSTM networks have shown great ability to learn social behaviors. However, many of these methods rely on previous neighboring hidden states but ignore the important current intention of the neighbors. In order to address this issue, we propose a data-driven state refinement module for LSTM network (SR-LSTM), which activates the utilization of the current intention of neighbors, and jointly and iteratively refines the current states of all participants in the crowd through a message passing mechanism. To effectively extract the social effect of neighbors, we further introduce a social-aware information selection mechanism consisting of an element-wise motion gate and a pedestrian-wise attention to select useful message from neighboring pedestrians. Experimental results on two public datasets, i.e. ETH and UCY, demonstrate the effectiveness of our proposed SR-LSTM and we achieve state-of-the-art results.

关键词： Pedestrians Neighbor Social Behavior trajectory Refining socio-economic effects current status

来源：评论

学校读者我要写书评

暂无评论

Towards Single Point Incremental Forming Accuracy: An Approach for the Springback Effect Compensation

Towards Single Point Incremental Forming Accuracy: An Approa...

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Walid K. Shaker Alexandr Klimchik Institute of Robotics and Computer Vision Innopolis University Republic of Tatarstan Russia School of Computer Science University of Lincoln Lincoln United Kingdom

The springback effect is a common occurrence in incremental forming, where the formed workpiece elastically deforms and slightly shifts from the desired shape after the tool is released. This phenomenon causes an error between the target and obtained shape, leading to reduced geometric accuracy. It is is a significant challenge in incremental forming and it is a reason why the process has lower accuracy compared to conventional forming methods. This paper presents an off-line springback effect compensation model aiming to generate an optimized toolpath that accounts for the material springback effect. The model is based on an off-line numerical simulation conducted on Abaqus/CAE software. The results demonstrated that the proposed model can effectively reduce the error between the desired and obtained shape by 31.8% for aluminum, 63.2% for copper, and 63.1 % for magnesium.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Classification of textures seen from different distances and under varying illumination direction

Classification of textures seen from different distances and...

引用

IEEE International Conference on Image Processing

作者： X. Llado J. Marti M. Petrou Computer Vision and Robotics Group University of Girona Girona Spain Informatics and Telematic Institute EKETA Thessaloniki Greece

Changes in the angle of illumination incident upon a 3D surface texture can significantly alter its appearance, implying variations in the image texture. These texture variations produce displacements of class members in the feature space, increasing the failure rates of texture classifiers. To avoid this problem, a model-based texture recognition system which classifies textures seen from different distances and under different illumination directions is presented in this paper. The system works on the basis of a surface model obtained by means of 4-source colour photometric stereo, used to generate 2D image textures under different illumination directions. The recognition system combines coocurrence matrices for feature extraction with a Nearest Neighbour classifier. Moreover, the recognition allows one to guess the approximate direction of the illumination used to capture the test image.

关键词： Lighting Surface texture Image texture Photometry Cameras Informatics computer vision Robot vision systems Application software Stereo vision

来源：评论

学校读者我要写书评

暂无评论

Learning monocular reactive UAV control in cluttered natural environments

Learning monocular reactive UAV control in cluttered natural...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Stéphane Ross Narek Melik-Barkhudarov Kumar Shaurya Shankar Andreas Wendel Debadeepta Dey J. Andrew Bagnell Martial Hebert The Robotics Institute Carnegie Mellon University Pittsburgh PA USA Institute for Computer Graphics and Vision Graz University of Technology Austria

ISBN: (纸本)9781467356404

Autonomous navigation for large Unmanned Aerial Vehicles (UAVs) is fairly straight-forward, as expensive sensors and monitoring devices can be employed. In contrast, obstacle avoidance remains a challenging task for Micro Aerial Vehicles (MAVs) which operate at low altitude in cluttered environments. Unlike large vehicles, MAVs can only carry very light sensors, such as cameras, making autonomous navigation through obstacles much more challenging. In this paper, we describe a system that navigates a small quadrotor helicopter autonomously at low altitude through natural forest environments. Using only a single cheap camera to perceive the environment, we are able to maintain a constant velocity of up to 1.5m/s. Given a small set of human pilot demonstrations, we use recent state-of-the-art imitation learning techniques to train a controller that can avoid trees by adapting the MAVs heading. We demonstrate the performance of our system in a more controlled environment indoors, and in real natural forest environments outdoors.

关键词： Training Cameras Trajectory Optical imaging Sensors Visualization Vegetation

来源：评论

学校读者我要写书评

暂无评论

Self-Prompting Large vision Models for Few-Shot Medical Image Segmentation

arXiv

引用

arXiv 2023年

作者： Wu, Qi Zhang, Yuyao Elbatel, Marawan The Hong Kong University of Science and Technology Hong Kong Computer Vision and Robotics Institute University of Girona Spain

Recent advancements in large foundation models have shown promising potential in the medical industry due to their flexible prompting capability. One such model, the Segment Anything Model (SAM), a prompt-driven segmentation model, has shown remarkable performance improvements, surpassing state-of-the-art approaches in medical image segmentation. However, existing methods primarily rely on tuning strategies that require extensive data or prior prompts tailored to the specific task, making it particularly challenging when only a limited number of data samples are available. In this paper, we propose a novel perspective on self-prompting in medical vision applications. Specifically, we harness the embedding space of SAM to prompt itself through a simple yet effective linear pixel-wise classifier. By preserving the encoding capabilities of the large model, the contextual information from its decoder, and leveraging its interactive promptability, we achieve competitive results on multiple datasets (i.e. improvement of more than 15% compared to fine-tuning the mask decoder using a few images). Our code is available at https://***/PeterYYZhang/few-shot-self-prompt-SAM Copyright © 2023, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Task-Oriented Grasp Prediction with Visual-Language Inputs

arXiv

引用

arXiv 2023年

作者： Tang, Chao Huang, Dehao Meng, Lingxiao Liu, Weiyu Zhang, Hong Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology Shenzhen China Institute for Robotics and Intelligent Machines Georgia Institute of Technology Atlanta United States

To perform household tasks, assistive robots receive commands in the form of user language instructions for tool manipulation. The initial stage involves selecting the intended tool (i.e., object grounding) and grasping it in a task-oriented manner (i.e., task grounding). Nevertheless, prior researches on visual-language grasping (VLG) focus on object grounding, while disregarding the fine-grained impact of tasks on object grasping. Task-incompatible grasping of a tool will inevitably limit the success of subsequent manipulation steps. Motivated by this problem, this paper proposes GraspCLIP, which addresses the challenge of task grounding in addition to object grounding to enable task-oriented grasp prediction with visual-language inputs. Evaluation on a custom dataset demonstrates that GraspCLIP achieves superior performance over established baselines with object grounding only. The effectiveness of the proposed method is further validated on an assistive robotic arm platform for grasping previously unseen kitchen tools given the task specification. Our presentation video is available at: https://***/watch?v=e1wfYQPeAXU. Copyright © 2023, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Implementation of a Real-Time Target Tracking Behaviour Using Video Sensors

引用

IFAC Proceedings Volumes 2001年第7期34卷 517-521页

作者： V. lla P. Ridao J.De La Cruz J. Batlle Computer Vision and Robotics Group Institute of Informatics and Applications. University of Girona Edifici Politecnica ll Campus Montilivi 17071 Girona Spain

Using software OS, real-time operation is constrained by acquisition and preprocessing tasks of input signals. In this way, this paper presents an implementation of a real time target tracking behaviour, from snapped images of the environment, as an example of how to take advantage of real-time hardware devices as a helpful systems for control architectures. A specific board based on FPGA/DSP processors has been used in order to reach this goal. The system has been thought for a marine and underwater environment and it has been tested using GARBI autonomous underwater vehicle. The implemented behaviours allow the robot to navigate autonomously and follow a diver.

关键词： behaviour binary image autonomous vehicle computer control

来源：评论

学校读者我要写书评

暂无评论

Wavelet Integrated CNNs for Noise-Robust Image Classification

arXiv

引用

arXiv 2020年

作者： Li, Qiufu Shen, Linlin Guo, Sheng Lai, Zhihui Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence & Robotics for Society China Malong Technologies

Convolutional Neural Networks (CNNs) are generally prone to noise interruptions, i.e., small image noise can cause drastic changes in the output. To suppress the noise effect to the final predication, we enhance CNNs by replacing max-pooling, strided-convolution, and average-pooling with Discrete Wavelet Transform (DWT). We present general DWT and Inverse DWT (IDWT) layers applicable to various wavelets like Haar, Daubechies, and Cohen, etc., and design wavelet integrated CNNs (WaveCNets) using these layers for image classification. In WaveCNets, feature maps are decomposed into the low-frequency and high-frequency components during the down-sampling. The low-frequency component stores main information including the basic object structures, which is transmitted into the subsequent layers to extract robust high-level features. The high-frequency components, containing most of the data noise, are dropped during inference to improve the noise-robustness of the WaveCNets. Our experimental results on ImageNet and ImageNet-C (the noisy version of ImageNet) show that WaveCNets, the wavelet integrated versions of VGG, ResNets, and DenseNet, achieve higher accuracy and better noise-robustness than their vanilla versions. Copyright © 2020, The Authors. All rights reserved.

关键词： Image classification

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：