检索结果-内蒙古大学图书馆

Combined Improved Dirichlet Models and Deep Learning Models for Road Extraction from remote sensing images

CANADIAN JOURNAL OF remote sensing 2021年第3期47卷 465-484页

作者： Chen, Ziyi Wang, Cheng Li, Jonathan Zhong, Bineng Du, Jixiang Fan, Wentao Huaqiao Univ Comp Sci & Technol Dept Fujian Key Lab Big Data Intelligence & Secur Xiamen Key Lab Comp Vis & Pattern Recognit Xiamen Fujian Peoples R China Xiamen Univ Sch Informat Sci & Technol South Siming Rd 422 Xiamen 361005 Fujian Peoples R China Univ Waterloo Dept Geog & Environm Management Waterloo ON N2L 3G1 Canada Guangxi Normal Univ Dept Comp Sci Guilin 541004 Peoples R China

Combining Dirichlet Mixture Models (DMM) with deep learning models for road extraction is an attractive study topic. Benefiting from DMM, the manually labeling work is alleviated. However, DMM suffers from high computational complexity due to pixel by pixel computations. Also, traditional constant parameter settings of DMM may not be suitable for different target images. To address the above problems, we propose an improved DMM which embeds superpixel strategy and sparse representation into DMM. In our road extraction framework, we first use improved DMM to filter out most backgrounds. Then, a trained deep CNN model is used for further precise road area recognition. To further promote the processing speed, we also apply the superpixel scanning strategy for CNN models. We tested our method on a Shaoshan dataset and proved that our method not only can achieve better results than other compared state-of-the-art image segmentation methods, but the processing speed and accuracy of DMM are also improved.

关键词： Superpixels

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of image Edge Detection Algorithm on FPGA

引用

International Journal of Circuits, Systems and Signal processing 2022年 16卷 628-636页

作者： Shylashree, N. Anil Naik, M. Mamatha, A.S. Sridhar, V. Department of Electronics and communication Engineering RV College of Engineering Bengaluru India Department of Electronics & Communication Engineering St. Joseph Engineering College Mangaluru India Department of Electronics & Communication Engineering Nitte Meenakshi Institute of Technology Bengaluru India

— image processing is an important task in data processing systems for applications such as medical sectors, remote sensing, and microscopy tomography. Edge recognition is a sort of image division method that is used to simplify the image records so as to reduce the amount of data to be processed. Edges are considered the most important in image processing because they are used to characterize the boundaries of an image. The performance of the Canny edge recognition algorithm remarkably surpasses the present edge recognition technology in various computer visualization methods. The main drawback of using Canny edge boundary is that it consumes lot of period due to its complex computation. In order to tackle this problem a hybrid edge recognition method is proposed in block stage to locate edges with no loss. It employs the Sobel operator estimate method to calculate the value and direction of the gradient by substituting complex processes by hardware cost savings, traditional non-maximum suppression adaptive thresholding block organization, and conventional hysteresis thresholding. Pipeline was presented to lessen latency. The planned strategy is simulated using Xilinx ISE Design Suite14.2 running on a Xilinx Spartan-6 FPGA board. The synthesized architecture uses less hardware to detect edges and operates at maximum frequency of 935 MHz. © 2022, North Atlantic University Union NAUN. All rights reserved.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Detection of Appearance and Behavior Anomalies in Stationary Camera Videos Using Convolutional Neural Networks

引用

pattern recognition AND image ANALYSIS 2022年第2期32卷 254-265页

作者： Chen, H. Bohush, R. Kurnosov, I. Ma, G. Weichen, Y. Ablameyko, S. Zhejiang Shuren Univ Hangzhou 310015 Peoples R China Int Sci & Technol Cooperat Base Zhejiang Prov Rem Remote Sensing Image Proc & Applicat Hangzhou 310000 Peoples R China Polotsk State Univ Novopolotsk 211440 BELARUS Belarusian State Univ Minsk 220030 BELARUS EarthView Image Inc Huzhou 313200 Peoples R China Natl Acad Sci Belarus United Inst Informat Problems Minsk 220012 BELARUS

The automatic detection and tracking of appearance and behavior anomalies in video surveillance systems is one of the promising areas for the development and implementation of artificial intelligence. In this paper, we present a formalization of these problems. Based on the proposed generalization, a detection and tracking algorithm that uses the tracking-by-detection paradigm and convolutional neural networks (CNNs) is developed. At the first stage, people are detected using the YOLOv5 CNN and are marked with bounding boxes. Then, their faces in the selected regions are detected and the presence or absence of face masks is determined. Our approach to face-mask detection also uses YOLOv5 as a detector and classifier. For this problem, we generate a training dataset by combining the Kaggle dataset and a modified Wider Face dataset, in which face masks were superimposed on half of the images. To ensure a high accuracy of tracking and trajectory construction, the CNN features of the images are included in a composite descriptor, which also contains geometric and color features, to describe each person detected in the current frame and compare this person with all people detected in the next frame. The results of the experiments are presented, including some examples of frames from processed video sequences with visualized trajectories for loitering and falls.

关键词： video surveillance face mask tracking-by-detection motion features loitering

来源：评论

学校读者我要写书评

暂无评论

HyperLeaf2024 – A Hyperspectral Imaging Dataset for Classification and Regression of Wheat Leaves

HyperLeaf2024 – A Hyperspectral Imaging Dataset for Classif...

引用

IEEE Computer Society Conference on Computer Vision and pattern recognition Workshops (CVPRW)

作者： William Michael Laprade Pawel Pieta Svetlana Kutuzova Jesper Cairo Westergaard Mads Nielsen Svend Christensen Anders Bjorholm Dahl Department of Applied Mathematics and Computer Science Technical University of Denmark Department of Computer Science University of Copenhagen Department of Plant and Environmental Sciences University of Copenhagen

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Hyperspectral imaging is a widely used method in remote sensing, particularly for use in airborne and satellite-based land surveillance. Its versatility is, however, much larger and has also seen usage in everything ranging from food processing and surveillance to astronomy and waste sorting. It is also gaining inroads with agricultural research. With most available datasets focusing on per-pixel classification, there is, however, a potential for hyperspectral whole-image analysis, but there is a severe lack of datasets for whole-image analysis. To help fill this gap and facilitate methodological development in whole-image hyperspectral image analysis, we introduce the Hy-perLeaf2024 dataset. The dataset consists of 2410 hyper-spectral images of wheat leaves, along with associated classification and regression targets at both the leaf level and the plot level. In addition to the dataset, we also provide experiments showing the importance of pretraining and highlighting the future research direction in whole-image hyper-spectral image analysis.

关键词： Adaptation models image analysis image coding Surveillance Conferences Focusing Distance measurement

来源：评论

学校读者我要写书评

暂无评论

An Effective One-shot Body Part Multi-View Reconstruction Device with Self-calibration Capabilities

An Effective One-shot Body Part Multi-View Reconstruction De...

引用

2024 Optical 3D Metrology, O3DM 2024

作者： Bonotto, Matteo Evangelista, Daniele Imperoli, Marco Pretto, Alberto Department of Information Engineering University of Padova Padova Italy FlexSight Srl Padova Italy

This paper introduces a custom-built low-cost camera ring device designed for automatic cast synthesis, able to accurately and instantly scan body parts. The scanned mesh will be used as a backbone model for the cast design and 3D printing. The system is based on the multi-view active stereo principle and it is composed of a circular array of 16 synchronized cameras (Fig. 1) and 4 equally distributed IR pseudo-random laser pattern projectors. We employ a custom multi-view stereo reconstruction pipeline based on (Schönberger et al., 2016), which guarantees optimal results without the downsides of the supervised data-driven multi-view stereo algorithms, i.e. data collection and ground truth labeling. Additionally, inspired by (Duda and Frese, 2018), we propose a novel, automated calibration system to extract intrinsic and extrinsic camera parameters which are required to perform robust multi-view stereo reconstructions. © Author(s) 2024.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

LRSAA: Large-scale remote sensing image Target recognition and Automatic Annotation

arXiv

引用

arXiv 2024年

作者： Dong, Wuzheng Zhu, Yujuan School of Mathematical Sciences Nankai University Tianjin China

This paper introduces a novel method for object recognition and automatic labeling in large-area remote sensing images, called LRSAA. The proposed method integrates the YOLOv11 and MobileNetV3-SSD object detection algorithms through ensemble learning to enhance overall model performance. Additionally, it utilizes Poisson disk sampling segmentation techniques along with the EIOU metric to optimize both the training and inference processes of segmented images, culminating in an integrated results framework. This approach not only minimizes computational resource requirements but also achieves an effective balance between accuracy and processing speed. The source code for this project is publicly accessible at https://***/anaerovane/LRSAA. © 2024, CC BY-NC-SA.

关键词： image annotation

来源：评论

学校读者我要写书评

暂无评论

Industrial objects recognition in intelligent manufacturing for computer vision

引用

INTERNATIONAL JOURNAL OF INTELLIGENT UNMANNED SYSTEMS 2022年第4期10卷 401-415页

作者： Jain, Tushar Meerut Inst Engn & Technol Mech Engn Meerut Uttar Pradesh India Natl Inst Technol Kurukshetra Kurukshetra Haryana India

Purpose The overall goal of this research is to develop algorithms for feature-based recognition of 2D parts from intensity images. Most present industrial vision systems are custom-designed systems, which can only handle a specific application. This is not surprising, since different applications have different geometry, different reflectance properties of the parts. Design/methodology/approach Computer vision recognition has attracted the attention of researchers in many application areas and has been used to solve many ranges of problems. Object recognition is a type of pattern recognition. Object recognition is widely used in the manufacturing industry for the purpose of inspection. Machine vision techniques are being applied in areas ranging from medical imaging to remote sensing, industrial inspection to document processing and nanotechnology to multimedia databases. In this work, recognition of objects manufactured in mechanical industry is considered. Mechanically manufactured parts have recognition difficulties due to manufacturing process including machine malfunctioning, tool wear and variations in raw material. This paper considers the problem of recognizing and classifying the objects of such mechanical part. Red, green and blue RGB images of five objects are used as an input. The Fourier descriptor technique is used for recognition of objects. Artificial neural network (ANN) is used for classification of five different objects. These objects are kept in different orientations for invariant rotation, translation and scaling. The feed forward neural network with back-propagation learning algorithm is used to train the network. This paper shows the effect of different network architecture and numbers of hidden nodes on the classification accuracy of objects as well as the effect of learning rate and momentum. Findings One important finding is that there is not any considerable change in the network performances after 500 iterations. It has been found that

关键词： Industrial objects recognition Fuzzy image classification Generic fourier descriptor Artificial neural network Intelligent manufacturing Robot vision

来源：评论

学校读者我要写书评

暂无评论

Leveraging Road Area Semantic Segmentation with Auxiliary Steering Task 1

引用

21st International Conference on image Analysis and processing (ICIAP)

作者： Maanpaa, Jyri Melekhov, Iaroslav Taher, Josef Manninen, Petri Hyyppa, Juha Natl Land Survey Finland Dept Remote Sensing & Photogrammetry Finnish Geospatial Res Inst FGI Espoo 02150 Finland Aalto Univ Sch Sci Espoo 02150 Finland

ISBN: (数字)9783031064272

ISBN: (纸本)9783031064272;9783031064265

Robustness of different pattern recognition methods is one of the key challenges in autonomous driving, especially when driving in the high variety of road environments and weather conditions, such as gravel roads and snowfall. Although one can collect data from these adverse conditions using cars equipped with sensors, it is quite tedious to annotate the data for training. In this work, we address this limitation and propose a CNN-based method that can leverage the steering wheel angle information to improve the road area semantic segmentation. As the steering wheel angle data can be easily acquired with the associated images, one could improve the accuracy of road area semantic segmentation by collecting data in new road environments without manual data annotation. We demonstrate the effectiveness of the proposed approach on two challenging data sets for autonomous driving and show that when the steering task is used in our segmentation model training, it leads to a 0.1-2.9% gain in the road area mIoU (mean Intersection over Union) compared to the corresponding reference transfer learning model.

关键词： Road area semantic segmentation Multi-task learning Transfer learning Domain adaptation Autonomous driving

来源：评论

学校读者我要写书评

暂无评论

E²(GO)MOTION: Motion Augmented Event Stream for Egocentric Action recognition

E<SUP>2</SUP>(GO)MOTION: Motion Augmented Event Stream for E...

引用

IEEE/CVF Conference on Computer Vision and pattern recognition (CVPR)

作者： Plizzari, Chiara Planamente, Mirco Goletto, Gabriele Cannici, Marco Gusso, Emanuele Matteucci, Matteo Caputo, Barbara Politecn Torino Turin Italy CINI Consortium Rome Italy Politecn Milan Milan Italy

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Event cameras are novel bio-inspired sensors, which asynchronously capture pixel-level intensity changes in the form of "events". Due to their sensing mechanism, event cameras have little to no motion blur, a very high temporal resolution and require significantly less power and memory than traditional frame-based cameras. These characteristics make them a perfect fit to several real-world applications such as egocentric action recognition on wearable devices, where fast camera motion and limited power challenge traditional vision sensors. However, the ever-growing field of event-based vision has, to date, overlooked the potential of event cameras in such applications. In this paper, we show that event data is a very valuable modality for egocentric action recognition. To do so, we introduce N-EPIC-Kitchens, the first event-based camera extension of the large-scale EPIC-Kitchens dataset. In this context, we propose two strategies: (i) directly processing eventcamera data with traditional video processing architectures (E-2(GO)) and (ii) using event-data to distill optical flow information (E-2(GO)MO). On our proposed benchmark, we show that event data provides a comparable performance to RGB and optical flow, yet without any additional flow computation at deploy time, and an improved performance of up to 49' with respect to RGB only information. The NEPIC-Kitchens dataset is available at https:/EgocentricVision/N-EPIC-Kitchens.

关键词： Computer vision image motion analysis Wearable computers Memory management Vision sensors Cameras Robustness

来源：评论

学校读者我要写书评

暂无评论

Semantic Segmentation Algorithm of Landslide Based on remote sensing image and DEM 5

Semantic Segmentation Algorithm of Landslide Based on Remote...

引用

5th International Conference on pattern recognition and Artificial Intelligence, PRAI 2022

作者： Zhou, Yongxiu Wang, Honghui Yang, Ronghao Xie, Dalan Liu, Jie Chengdu University of Technology Key Laboratory of Earth Exploration and Information Technology of Ministry of Education Chengdu610059 China Chengdu University of Technology College of Computer Science and Cyber Security Chengdu610059 China Chengdu University of Technology College of Earth Sciences Chengdu610059 China Chengdu University of Technology College of Nuclear Technology and Automation Engineering Chengdu610059 China

ISBN: (数字)9781665499163

ISBN: (纸本)9781665499163

The fast landslide segmentation algorithm based on deep learning technology for remote sensing images can play an important role in disaster analysis and risk assessment. At this stage, deep learning-based landslide segmentation algorithms mainly use RGB images as training data for the models, and a few studies have started to add digital elevation models (DEMs) as training data. In order to study the effect of DEM as training data on the accuracy improvement of landslide segmentation algorithm, we use RGB remote sensing images and DEM as training data, use U-Net combined with pspnet network structure, add FCN network structure in the training process, and analyze the test results using various evaluation metrics. Finally, we conclude that compared with the model using only RGB images as input data, adding DEM as input data can effectively improve the overall accuracy of the landslide segmentation model and reduce the false accept rate of the model in complex terrain. © 2022 IEEE.

关键词： Semantics

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：