检索结果-内蒙古大学图书馆

Fusion of Ship Perceptual Information for Electronic Navigational Chart and Radar images based on deep learning

JOURNAL OF NAVIGATION 2020年第1期73卷 192-211页

作者： Guo, Muzhuang Guo, Chen Zhang, Chuang Zhang, Daheng Gao, Zongjiang Dalian Maritime Univ Coll Marine Elect Engn Dalian 116026 Liaoning Peoples R China Dalian Maritime Univ Nav Coll Dalian 116026 Peoples R China

Superimposing Electronic Navigational Chart (ENC) data on marine radar images can enrich information for navigation. However, direct image superposition is affected by the performance of various instruments such as Global Navigation Satellite Systems (GNSS) and compasses and may undermine the effectiveness of the resulting information. We propose a data fusion algorithm based on deep learning to extract robust features from radar images. By deep learning in this context we mean employing a class of machine learning algorithms, including artificial neural networks, that use multiple layers to progressively extract higher level features from raw input. We first exploit the ability of deep learning to perform target detection for the identification of marine radar targets. Then, image processing is performed on the identified targets to determine reference points for consistent data fusion of ENC and marine radar information. Finally, a more intelligent fusion algorithm is built to merge the marine radar and electronic chart data according to the determined reference points. The proposed fusion is verified through simulations using ENC data and marine radar images from real ships in narrow waters over a continuous period. The results suggest a suitable performance for edge matching of the shoreline and real-time applicability. The fused image can provide comprehensive information to support navigation, thus enhancing important aspects such as safety.

关键词： deep learning Marine radar Electronic Navigational Chart (ENC) Data fusion

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Object Detection for Sorghum Panicles in UAV imagery

Semi-Supervised Object Detection for Sorghum Panicles in UAV...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Enyu Cai Jiaqi Guo Changye Yang Edward J. Delp Video and Image Processing Laboratory (VIPER) School of Electrical and Computer Engineering Purdue University West Lafayette Indiana USA

The sorghum panicle is an important trait related to grain yield and plant development. Detecting and counting sorghum panicles can provide significant information for plant phenotyping. Current deep-learning-based object detection methods for panicles require a large amount of training data. The data labeling is time-consuming and not feasible for real application. In this paper, we present an approach to reduce the amount of training data for sorghum panicle detection via semi-supervised learning. Results show we can achieve similar performance as supervised methods for sorghum panicle detection by only using 10% of original training data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Face Feature Extraction and Recognition Based on Lighted deep Convolutional Neural Network 7th

Face Feature Extraction and Recognition Based on Lighted Dee...

引用

7th International Conference on Artificial Intelligence and Security, ICAIS 2021

作者： Tian, Ying Wang, Yang Cui, Longlei School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China

ISBN: (纸本)9783030786144

Face recognition is one of the most challenging research fields in image processing, pattern recognition and artificial intelligence, and its practical application has a bright future. Face is vulnerable to illumination and expression factors in the process of image acquisition. The traditional machine learning method for extracting face features usually requires high clarity of face images to achieve ideal results. Face feature extraction and recognition based on deep learning method can effectively solve this kind of problem, but the recognition rate is greatly improved, at the same time, the size of the network and the difficulty of training are also sharply increased. It does not meet the increasingly lightweight requirements of the network. This paper studies the current mainstream DCNN architecture, especially MobileNet and ShuffleNet at light-weight mobile level. Some high-efficiency and practical structural features of convolution are summarized;A Nonlinear separable deep convolutional neural network X-Net is designed;Focusing on the loss of the sample in the real face dataset, focus loss is introduced to reduce the effect of sample deviation on network fitting. The experimental results show that the feature extraction based on deep convolutional neural network in this paper can use dynamic library DLL to play an effective role in practical commercial projects. © 2021, Springer Nature Switzerland AG.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A new method for detection and prediction of occluded text in natural scene images

引用

SIGNAL processing-image COMMUNICATION 2022年 100卷

作者： Mittal, Ayush Shivakumara, Palaiahnakote Pal, Umapada Lu, Tong Blumenstein, Michael Indian Stat Inst Kolkata India Univ Malaya Fac Comp Sci & Informat Technol Dept Comp Syst & Technol Kuala Lumpur 50603 Malaysia Nanjing Univ Natl Key Lab Novel Software Technol Nanjing Peoples R China Univ Technol Sydney Sydney NSW Australia

Text detection from natural scene images is an active research area for computer vision, signal, and image processing because of several real-time applications such as driving vehicles automatically and tracing person behaviors during sports or marathon events. In these situations, there is a high probability of missing text information due to the occlusion of different objects/persons while capturing images. Unlike most of the existing methods, which focus only on text detection by ignoring the effect of missing texts, this work detects and predicts missing texts so that the performance of the OCR improves. The proposed method exploits the property of DCT for finding significant information in images by selecting multiple channels. For chosen DCT channels, the proposed method studies texture distribution based on statistical measurement to extract features. We propose to adopt Bayesian classifier for categorizing text pixels using extracted features. Then a deep learning model is proposed for eliminating false positives to improve text detection performance. Further, the proposed method employs a Natural Language processing (NLP) model for predicting missing text information by using detected and recognition texts. Experimental results on our dataset, which contains texts occluded by objects, show that the proposed method is effective in predicting missing text information. To demonstrate the effectiveness and objectiveness of the proposed method, we also tested it on the standard datasets of natural scene images, namely, ICDAR 2017-MLT, Total-Text, and CTW1500.

关键词： DCT channels Bayesian classifier Text detection Natural language processing Text restoration Text prediction

来源：评论

学校读者我要写书评

暂无评论

Hybrid deep learning Approach for Efficient Outdoor Parking Monitoring in Smart Cities 1

引用

16th International Conference on Hybrid Artificial Intelligent Systems, HAIS 2021

作者： Iglesias, Alberto Tellaeche Pastor-López, Iker Urquijo, Borja Sanz García-Bringas, Pablo D4K Group University of Deusto Avda. Universidades 24 Bilbao48007 Spain

ISBN: (数字)9783030862718

ISBN: (纸本)9783030862701

The problem of transport is one of the fundamental problems in today's large cities and one of the fundamental pillars on which work is being done under the paradigm of smart cities. Although the use of public transport is encouraged in cities, there are always problems related to private transport parking availability. This work focuses on the development of an algorithm for monitoring parking spaces in open-air car parks, which is effective and simple from the point of view of the costs required for its deployment and robust in detecting the state of the car park. To this end, an algorithm based on deep learning has been developed for processing the status images of different car parks, obtaining real-time information on the real status of the car park, without the need for extensive deployment of devices in the car park. The proposed solution has been shown to outperform other image-based solutions for the same problem. © 2021, Springer Nature Switzerland AG.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

基于视觉处理器芯片的遥感图像智能处理系统设计与验证

引用

航天返回与遥感 2023年第5期44卷 54-64页

作者：于双铭武文波窦润江刘力源刘剑吴南健中国科学院半导体研究所半导体超晶格国家重点实验室北京100083 中国科学院大学材料科学与光电技术学院北京100049 北京空间机电研究所北京100094 中国科学院大学电子电气与通信工程学院北京100049

随着遥感卫星成像技术向高分辨率、高帧率的方向快速发展,星上遥感图像处理技术面临海量数据处理速度慢、有效信息提取能力不足、载荷功耗高等瓶颈问题。文章提出一种面向星上处理的遥感图像智能处理系统,系统架构设计基于一款边缘型视... 详细信息

随着遥感卫星成像技术向高分辨率、高帧率的方向快速发展,星上遥感图像处理技术面临海量数据处理速度慢、有效信息提取能力不足、载荷功耗高等瓶颈问题。文章提出一种面向星上处理的遥感图像智能处理系统,系统架构设计基于一款边缘型视觉处理器芯片,该芯片为可重构并行处理器架构,可通过指令编程兼容支持图像预处理算法、计算机视觉算法和深度学习神经网络算法。基于算法-硬件协同设计思想,对图像处理算法进行了剪枝和量化等压缩优化,在芯片上实现算法的高效部署。搭建基于视觉处理器芯片的遥感图像智能处理系统,进行实验验证。结果表明,该系统能够完成对遥感图像的实时目标检测等智能化处理,系统处理能力达到200 M像素/s,芯片峰值计算能效达到2×1012次/W(300 MHz时)。

关键词：遥感图像图像处理视觉处理器深度学习神经网络

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Lane Detection Based on Attention Mechanism and Post-processing of Prediction

Two-Stage Lane Detection Based on Attention Mechanism and Po...

引用

IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)

作者： Yuanlong Wang Hengtao Jiang Zhiqiang Jing Guanying Chen Changsheng Ma Rongxian Qiu College of Energy and Power Engineering Nanjing University of Aeronautics and Astronautics Nanjing China School of Mechanical Engineering Nanjing University of Science and Technology Nanjing China

Existing lane detection methods have achieved remarkable performance in complex real-world scenarios, but many of them still have some problems, such as poor anti-interference ability, poor real-time performance, and difficult deployment at the vehicle end. In this work, we combine the characteristics of deep learning and traditional algorithms and propose a two-stage lane detection method: Firstly, the model uses the output of backbone based on line-anchor for feature pooling, and at the same time, an attention mechanism based on line-anchor is applied to extract global features. Then, the pooled features are integrated with the global features to solve the problems such as the occlusion of the lane lines. Then, the fused features are input into the classification branch and regression branch, and then the relevant position information such as the confidence degree and offset of the lane line are output. Finally, according to the characteristics of lane detection, a special predictive post-processing module, Post-processing of Prediction Results (PPR) is designed based on the output lane information. PPR can improve the detection performance without increasing the number of model training parameters. The experimental results show that the recognition time of one frame image by our method is only 0.012s, meanwhile the accuracy rate can reach 95.6%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Survey of deep learning and Its Applications: A New Paradigm to Machine learning

引用

ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING 2020年第4期27卷 1071-1092页

作者： Dargan, Shaveta Kumar, Munish Ayyagari, Maruthi Rohit Kumar, Gulshan Maharaja Ranjit Singh Punjab Tech Univ Dept Computat Sci Bathinda Punjab India Univ Dallas Coll Business Irving TX USA Shaheed Bhagat Singh State Tech Campus Dept Comp Applicat Ferozepur Punjab India

Nowadays, deep learning is a current and a stimulating field of machine learning. deep learning is the most effective, supervised, time and cost efficient machine learning approach. deep learning is not a restricted learning approach, but it abides various procedures and topographies which can be applied to an immense speculum of complicated problems. The technique learns the illustrative and differential features in a very stratified way. deep learning methods have made a significant breakthrough with appreciable performance in a wide variety of applications with useful security tools. It is considered to be the best choice for discovering complex architecture in high-dimensional data by employing back propagation algorithm. As deep learning has made significant advancements and tremendous performance in numerous applications, the widely used domains of deep learning are business, science and government which further includes adaptive testing, biological image classification, computer vision, cancer detection, natural language processing, object detection, face recognition, handwriting recognition, speech recognition, stock market analysis, smart city and many more. This paper focuses on the concepts of deep learning, its basic and advanced architectures, techniques, motivational aspects, characteristics and the limitations. The paper also presents the major differences between the deep learning, classical machine learning and conventional learning approaches and the major challenges ahead. The main intention of this paper is to explore and present chronologically, a comprehensive survey of the major applications of deep learning covering variety of areas, study of the techniques and architectures used and further the contribution of that respective application in the real world. Finally, the paper ends with the conclusion and future aspects.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Positive Unlabelled learning for Satellite images'time Series Analysis: An Application to Cereal and Forest Mapping

引用

REMOTE SENSING 2022年第1期14卷

作者： Desloires, Johann Ienco, Dino Botrel, Antoine Ranc, Nicolas Univ Montpellier INRAE UMR TETIS F-34000 Montpellier France Syngenta Seeds F-31790 St Sauveur France

Applications in which researchers aim to extract a single land type from remotely sensed data are quite common in practical scenarios: extract the urban footprint to make connections with socio-economic factors;map the forest extent to subsequently retrieve biophysical variables and detect a particular crop type to successively calibrate and deploy yield prediction models. In this scenario, the (positive) targeted class is well defined, while the negative class is difficult to describe. This one-class classification setting is also referred to as positive unlabelled learning (PUL) in the general field of machine learning. To deal with this challenging setting, when satellite image time series data are available, we propose a new framework named positive and unlabelled learning of satellite image time series (PUL-SITS). PUL-SITS involves two different stages: In the first one, a recurrent neural network autoencoder is trained to reconstruct only positive samples with the aim to higight reliable negative ones. In the second stage, both labelled and unlabelled samples are exploited in a semi-supervised manner to build the final binary classification model. To assess the quality of our approach, experiments were carried out on a real-world benchmark, namely Haute-Garonne, located in the southwest area of France. From this study site, we considered two different scenarios: a first one in which the process has the objective to map Cereals/Oilseeds cover versus the rest of the land cover classes and a second one in which the class of interest is the Forest land cover. The evaluation was carried out by comparing the proposed approach with recent competitors to deal with the considered positive and unlabelled learning scenarios.

关键词： land cover mapping positive unlabelled learning satellite image time series deep learning

来源：评论

学校读者我要写书评

暂无评论

Interactive Intelligent 3D Surveying Vehicle Based on deep learning 23

Interactive Intelligent 3D Surveying Vehicle Based on Deep L...

引用

Proceedings of the 2023 5th International Conference on Video, Signal and image processing

作者： Zeyu Hu Haisong Chen Jingfang Wei Yunyi Zuo Kaiyang Xu Yuji Iwahori Haibin Wu Aili Wang Heilongjiang Province Key Laboratory of Laser Spectroscopy Technology and Application Harbin University of Science and Technology China Shenzhen Polytechnic University China Department of Computer Science Chubu University Japan

ISBN: (纸本)9798400709272

With the rapid development of artificial intelligence, the emergence of intelligent vehicles has brought disruptive changes to traditional survey technology. In response to the limitations of geological environmental factors on the scope and search progress of field exploration, this article utilizes a modular design concept to develop a system structure framework and specific solutions for each functional module of a multi-functional intelligent survey vehicle. An intelligent control platform based on the Nvidia Jetson TX2 and ROS systems has been built, and software programs for eye movement control and 3D dense reconstruction have been written. A system that can assist motion control through line of sight has been designed, A small, low-cost intelligent survey vehicle that can simultaneously perform real-time scene 3D reconstruction. This survey vehicle combines IoT technology, and on the basis of traditional survey vehicle functions, it has functions such as eye tracking, scene 3D reconstruction, remote object detection, etc. The obtained information is transmitted back to the PC through remote communication for users to view the survey results in real-time. At the same time, the operation of the survey vehicle can be controlled according to the direction of the line of sight, providing intelligent interaction ability and multi-dimensional exploration results for exploration work.

关键词： 3D dense reconstruction Eye tracking control motion Intelligent survey vehicle SLAM YOLOv5

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：