检索结果-内蒙古大学图书馆

15th Asian Conference on computer vision, ACCV 2020

作者： Zhang, Zhengxi Zhao, Liang Liu, Yunan Zhang, Shanshan Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High -Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9783030695378

It is an important yet challenging task to detect objects on hazy images in real-world applications. The major challenge comes from low visual quality and large haze density variations. In this work, we aim to jointly solve the image dehazing and the object detection tasks in real hazy scenarios by using haze density as prior knowledge. Our proposed Unified Dehazing and Detection (UDnD) framework consists of three parts: a residual-aware haze density classifier, a density-aware dehazing network, and a density-aware object detector. First, the classifier exploits the residuals of hazy images to accurately predict density levels, which provide rich domain knowledge for the subsequent two tasks. Then, we design respectively a High-Resolution Dehazing Network (HRDN) and a Faster R-CNN-based multi-domain object detector to leverage the extracted density information and tackle hazy object detection. Experiments demonstrate that UDnD performs favorably against other methods for object detection in real-world hazy scenes. Also, HRDN achieves better results than state-of-the-art dehazing methods in terms of PSNR and SSIM. Hence, HRDN can conduct haze removal effectively, based on which UDnD is able to provide high-quality detection results. © 2021, Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Multi-view Action Recognition via Directed Gromov-Wasserstein Discrepancy

arXiv

引用

arXiv 2024年

作者： Nguyen, Hoang-Quan Truong, Thanh-Dat Luu, Khoa Computer Vision and Image Understanding Lab University of Arkansas FayettevilleAR72701 United States

Action recognition has become one of the popular research topics in computer vision. There are various methods based on Convolutional Networks and self-attention mechanisms as Transformers to solve both spatial and temporal dimensions problems of action recognition tasks that achieve competitive performances. However, these methods lack a guarantee of the correctness of the action subject that the models give attention to, i.e., how to ensure an action recognition model focuses on the proper action subject to make a reasonable action prediction. In this paper, we propose a multi-view attention consistency method that computes the similarity between two attentions from two different views of the action videos using Directed Gromov-Wasserstein Discrepancy. Furthermore, our approach applies the idea of Neural Radiance Field to implicitly render the features from novel views when training on single-view datasets. Therefore, the contributions in this work are three-fold. Firstly, we introduce the multi-view attention consistency to solve the problem of reasonable prediction in action recognition. Secondly, we define a new metric for multi-view consistent attention using Directed Gromov-Wasserstein Discrepancy. Thirdly, we built an action recognition model based on Video Transformers and Neural Radiance Fields. Compared to the recent action recognition methods, the proposed approach achieves state-of-the-art results on three large-scale datasets, i.e., Jester, Something-Something V2, and Kinetics-400. © 2024, CC BY.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Terahertz compressive imaging: understanding and improvement by a better strategy for data selection

Terahertz compressive imaging: understanding and improvement...

引用

作者： Xing, Chungui Qi, Feng Liu, Zhaoyang Wang, Yelong Guo, Shuxu State Key Laboratory on Integrated Optoelectronics College of Electronic Science and Engineering Jilin University Changchun China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Shenyang China Key Lab of Image Understanding and Computer Vision Shenyang China

Compressive sensing (CS) is a novel sampling modality, which indicates the signals can be sampled at a rate much below the Nyquist sampling rate. CS has increasing interest recently due to high demand of rapid, efficient, and in-expensive signal processing applications in the μmWave and mmWave frequencies, such as communication and imaging. There have been a lot of theoretical studies on this topic, but there is a lack of systematic experimental analysis of the implementation method itself. In this paper, we have investigated the influencing factors of terahertz compressive sensing based on experimental results, including illumination and the size of the pixel. Besides, to differentiate from current approaches, which generally make full use of the data, we propose to sort the data first and select a part of them based on amplitude, which might deliver a better image by prompting the mathematical calculations compulsively. We believe that such considerations given above would help to make a better system design and improve the performance of compressive imaging, and these results will also be helpful in the application of terahertz communication. © 2021 John Wiley & Sons, Ltd

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Assignment problem based deep embedding 1

引用

2nd Chinese Conference on Pattern Recognition and computer vision, PRCV 2019

作者： Zheng, Ruishen Xie, Jin Qian, Jianjun Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China

ISBN: (数字)9783030317232

ISBN: (纸本)9783030317225

How to measure the similarity of samples is a fundamental problem in many computer vision tasks such as retrieval and clustering. Due to the rapid development of deep neural networks, deep metric learning has been widely studied. Some studies focus on the hard sample mining strategy for triplet loss. We observe that hard mining strategies are also vital for contrastive loss. But the hardest mining strategy for contrastive loss is sensitive to outliers. In this paper, based on combinatorial information of sample pairs, we propose a novel linear assignment problem based hard sample mining strategy for contrastive loss to learn feature embeddings. Specifically, our method can assign 0/1 weight to sample pairs for the hard sample selection by maximizing a linear assignment loss and ensure that each sample is only included by one pair for the optimization. Our method can obtain the state-of-the-art performance on the CUB-200-2011, Cars196, and In-shop datasets with the GoogLeNet network. © Springer Nature Switzerland AG 2019.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

Fast Candidate Region Extraction for SAR Ship Target 37

Fast Candidate Region Extraction for SAR Ship Target

引用

37th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2022

作者： Zhang, Panpan Luo, Haibo Xu, Zheng He, Miao Shenyang Institute of Automation Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Shenyang110016 China University of Chinese Academy of Sciences Beijing100049 China Key Laboratory of Opto-Electronic Information Processing Shenyang110016 China The Key Lab of Image Understanding and Computer Vision Shenyang110016 China

ISBN: (纸本)9781665465366

At present, deep learning technology is widely used in ship target detection in synthetic aperture radar (SAR) images. However, high-resolution remote sensing SAR images cover a larger area and have larger image sizes. To be able to use the deep learning model for training and testing, the image needs to be cropped to the appropriate size. In a high-resolution SAR ship image, the ship target usually takes only a small part of the whole image. As a result, only part of the cropped image contains the target, and most of the rest are background regions. This will cause a lot of computational redundancy in the model inference stage. To solve this problem, a fast candidate region extraction algorithm is proposed in this paper for ship target extraction. The algorithm consists of three parts: firstly, extract the saliency map of the SAR ship image, secondly, perform median filtering on the segmented image, and thirdly, extract candidate regions. The superiority of the algorithm was demonstrated by experiments on the AIR-SARShip-1.0 dataset. © 2022 IEEE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Multi-scale dynamic feature encoding network for image demoiréing 17

Multi-scale dynamic feature encoding network for image demoi...

引用

17th IEEE/CVF International Conference on computer vision Workshop, ICCVW 2019

作者： Cheng, Xi Fu, Zhenyong Yang, Jian PCA Lab Key Lab of Intelligent Percept. and Syst. for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9781728150239

The prevalence of digital sensors, such as digital cameras and mobile phones, simplifies the acquisition of photos. Digital sensors, however, suffer from producing Moire when photographing objects having complex textures, which deteriorates the quality of photos. Moire spreads across various frequency bands of images and is a dynamic texture with varying colors and shapes, which pose two main challenges in demoireing - an important task in image restoration. In this paper, towards addressing the first challenge, we design a multi-scale network to process images at different spatial resolutions, obtaining features in different frequency bands, and thus our method can jointly remove moire in different frequency bands. Towards solving the second challenge, we propose a dynamic feature encoding module (DFE), embedded in each scale, for dynamic texture. Moire pattern can be eliminated more effectively via *** proposed method, termed Multi-scale convolutional network with Dynamic feature encoding for image DeMoireing (MDDM), can outperform the state of the arts in fidelity as well as perceptual on benchmarks. © 2019 IEEE.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

image processing in quantum computers

arXiv

引用

arXiv 2018年

作者： Dendukuri, Aditya Luu, Khoa Computer Vision and Image Understanding Lab Computer Science and Computer Engineering Department University of Arkansas FayettevilleAR72701 United States

Quantum image Processing (QIP) is an exciting new field showing a lot of promise as a powerful addition to the arsenal of image Processing techniques. Representing image pixel by pixel using classical information requires enormous amount of computational resources. Hence, exploring methods to represent images in a different paradigm of information is important. In this work, we study the representation of images in Quantum Information. The main motivation for this pursuit is the ability of storing N bits of classical information in only log2N quantum bits (qubits). The promising first step was the exponentially efficient implementation of the Fourier transform in quantum computers as compared to Fast Fourier Transform in classical computers. In addition, images encoded in quantum information could obey unique quantum properties like superposition or entanglement. Copyright © 2018, The Authors. All rights reserved.

关键词： Qubits

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

Accurate quaternion radial harmonic Fourier moments for color image reconstruction and object recognition

引用

Pattern Analysis and Applications 2020年第4期23卷 1551-1567页

作者： Liu, Yunan Zhang, Shanshan Li, Guangyu Wang, Houjun Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing 210094 China National Ocean Technology Center Tianjin 300112 China

Orthogonal moments have become a powerful tool for object representation and image analysis. Radial harmonic Fourier moments (RHFMs) are one of such image descriptors based on a set of orthogonal projection bases, which outperform other moments because of their computational efficiency. However, the conventional computational framework of RHFMs produces geometric error and numerical integration error, which will affect the accuracy of RHFMs, thus degrading the image reconstruction performance. To overcome this shortcoming, we propose a new computational framework of RHFMs, namely accurate quaternion radial harmonic Fourier moments (AQRHFMs), for color image processing, and also analyze the properties of AQRHFMs. Firstly, we propose a precise computation method of RHFMs to reduce the geometric and numerical errors. Secondly, by using the algebra of quaternions, we extend the accurate RHFMs to AQRHFMs in order to deal with the color images in a holistic manner. Experimental results show the proposed AQRHFMs achieve promising performance in image reconstruction and object recognition in both noise-free and noisy conditions. © 2020, Springer-Verlag London Ltd., part of Springer Nature.

关键词： Geometric error Numerical error Object recognition Quaternion Radial harmonic Fourier moments

来源：评论

学校读者我要写书评

暂无评论

A Shape Retentive Filtering Algorithm for Post-processing of Instance Contour of Cervical Cell Based on Level Set Method

A Shape Retentive Filtering Algorithm for Post-processing of...

引用

International Conference on computer and Communications (ICCC)

作者： Guangqi Liu Qinghai Ding Moran Ju Haibo Luo Tianming Jin Miao He The Key Laboratory of Image Understanding and Computer Vision Shenyang China Space Star Technology Company Ltd. Beijing China

ISBN: (数字)9781728186351

ISBN: (纸本)9781728186368

A novel filtering algorithm is proposed based on level set method (LSM) and linear time Euclidean distance transform (LET) algorithm in this paper, which has the property of shape retention and thus is suitable for post-processing of the initial contours for contacting instances in digital Pap image. As one of our contributions, we propose two new metrics based on the pixel-level average false positive rate and false negative rate that used by baseline method. A significant decrease in pixel-level average false positive rate (FP) by 62% can obtain by our proposed method. The result of quantitative and qualitative evaluation shows that our proposed shape retentive filtering algorithm (SRFA) can effectively filter out the false positive fragments of the initial instance contour of cervical cells from the ISBI-2014 dataset.

关键词： Measurement Shape Level set Transforms Euclidean distance Filtering algorithms Medical diagnostic imaging

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

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

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：