检索结果-内蒙古大学图书馆

A new approach to oil spill detection that combines deep learning with unmanned aerial vehicles

COMPUTERS & INDUSTRIAL ENGINEERING 2019年 135卷 1300-1311页

作者： Jiao, Zeyu Jia, Guozhu Cai, Yingjie Beihang Univ Sch Econ & Management Beijing 100191 Peoples R China Beihang Univ Sch Comp Sci & Engn 37 Xue Yuan Rd Beijing 100191 Peoples R China

This study presents a novel approach to automatic oil spill detection, using unmanned aerial vehicle (UAV) images to realize intelligent control in oil production. Despite considerable effort, oil spills still cannot be detected automatically and effectively due to the complexity of the real production environment, which forces oil enterprises to manually inspect facilities and detect oil spills. To solve the problem, we propose an approach consisting of UAVs, deep learning and traditional algorithms-an approach which divides the oil spill detection task into three independent sub-tasks. First, we constructed a model based on the deep convolutional neural network, which can quickly detect the suspected oil spill area in images to ensure there are no omissions. Second, to remove other obstacles in the images, we adjusted the otsu algorithm to filter the detection results, which improves precision while not affecting the recall rate. Third, the Maximally Stable External Regions algorithm was used to obtain the detail polygon region from the detection box, thus automatically evaluating the severity of the oil spill. Experiments showed that our method could solve problems effectively, reducing the cost of oil spill detection by 57.2% when compared with the traditional manual inspection process.

关键词： Oil spill Unmanned aerial vehicle Deep convolutional neural network otsu algorithm Maximally stable extremal regions Intelligent control

来源：评论

学校读者我要写书评

暂无评论

Round Traffic Sign Detection algorithm

Round Traffic Sign Detection Algorithm

引用

作者： Yinrong Huang Bing Wang Xiemin Yuan School of Electronics and Information Engineering Guang'an Vocational and Technical College School of Communication and Information Engineering Chongqing University of Posts and Telecommunications

Traffic signs are an important part of autonomous driving and intelligent transportation. It provides instructions for pedestrians and vehicles and is critical to road traffic safety. However, existing detection algorithms cannot achieve real-time high-precision detection. Therefore, this paper proposes an algorithm that combines traditional methods with deep learning to detect circular traffic signs. Based on the HSV color space, the red and blue channel images are separated, and the candidate regions of the original image are extracted using the Hough transform. The shallow convolutional neural network(CNN) classifier rejects not traffic signs and classifies traffic signs. Experiments show that the algorithm is real and effective. On the CPU platform, the average accuracy rate is 96.2%, and the detection speed reaches 0.3 s/frame. Under the condition of ensuring the average accuracy rate, the detection speed is greatly reduced. The algorithm achieves the fastest speed, which makes real-time high-precision detection possible. The algorithm is more suitable for vehicle embedded systems.

关键词： Traffic signs detection HSV Hough transform CNN algorithm otsu algorithm

来源：评论

学校读者我要写书评

暂无评论

A Hybrid algorithm of otsu and Adaptive Region for Image Segmentation

A Hybrid Algorithm of Otsu and Adaptive Region for Image Seg...

引用

IEEE International Conference on Power, Intelligent Computing and Systems

作者： Luo Chunlei Sha Hao Wang Hu He Yi College of Mechanical and Electrical Engineering Central South University

ISBN: (纸本)9781728137216

The traditional Region Growing (RG) algorithm is a semi-automatic image segmentation algorithm that requires manual selection of seed points, manual setting of thresholds, which may cause the cavity and over-segmentation while deals with the uneven and undivided image for noise and grayscale. Therefore, the classical otsu method is adopted to find the optimal threshold in HSV space to obtain the initial binarized segmentation image. Then, the Adaptive Region Growing (ARG) algorithm is applied to find the image edge. To be specific, the initial seed point is confirmed automatically through histogram firstly. Secondly, the threshold of growth condition is determined according to the average similarity of image. Finally, the image is grown into the contour edges. This image is mixed together with the initial otsu segmentation image can obtain the final processed image. Experimental results show that the proposed algorithm has strong anti-interference, which can effectively reduce the mis-segmentation rate.

关键词： Image segmentation Machine vision Obstacle detective RG algorithm otsu algorithm image segmentation robot vision Image images Imagery (Psychotherapy) edge image suppression of interference region growing image segmentation algorithm algorithms

来源：评论

学校读者我要写书评

暂无评论

The Chromatic Aberration 2-D Entropy Threshold Segmentation Method Based on Adaptive Step-Length Firefly algorithm

引用

RECENT ADVANCES IN ELECTRICAL & ELECTRONIC ENGINEERING 2019年第2期12卷 130-137页

作者： Wu Shaofeng Tong Yifei Liu Jiafeng Tan Qingmeng Li Dongbo Nanjing Univ Sci & Technol Sch Mech Engn Nanjing Jiangsu Peoples R China

Background: To effectively solve the segmentation problem with multi-target complex image, the chromatic aberration 2-D entropy threshold segmentation method based on Adaptive Step Length Firefly algorithm (ASLFA) is proposed in this paper. Methods: Firstly, the significance of image entropy value is analyzed and the threshold segmentation is proposed with maximum entropy principle. Then, in order to solve the problem of large amount and longtime of calculation in the threshold segmentation process, the improved firefly algorithm (FA) is proposed replacing the fixed step-length with adaptive step-length. Results: Finally, in order to make full use of the image information, the space distance of chromatic aberration is introduced and combined with FA. Conclusion: Contrast test of the proposed method and 2-D entropy threshold based on standard firefly algorithm (SFA) and genetic algorithm (CA) proves that the proposed method can improve the segmentation accuracy while ensuring the segmentation speed, and is suitable for fast and effective segmentation of multi-target images and complex images.

关键词： Threshold segmentation 2-D entropy firefly algorithm adaptive step-length chromatic aberration genetic algorithm otsu algorithm

来源：评论

学校读者我要写书评

暂无评论

Video Background/Foreground Separation Model Based on Non-Convex Rank Approximation RPCA and Superpixel Motion Detection

引用

IEEE ACCESS 2020年 8卷 157493-157503页

作者： Wang, Yongli Wei, Hongchao Ding, Xiaoyun Tao, Juliang Shandong Univ Sci & Technol Coll Math & Syst Sci Qingdao 266590 Peoples R China

Traditional robust principal component analysis (RPCA) is very prone to voids in the process of background/foreground separation of complex scene videos and easy to misjudge the dynamic background as a moving target, which makes the separation effect unideal. In order to address this problem, this article introduces the super-pixel segmentation technique into the RPCA model. First, the Linear Spectral Clustering algorithm (LSC) is used to mark the super-pixel segmentation of the video sequence and a super-pixel grouping matrix is obtained. Then a new video background/foreground separation model is proposed based on the non-convex rank approximation RPCA and super-pixel motion detection (SPMD) technique. The otsu algorithm is used to obtain the motion mask matrix and the augmented lagrange alternating direction method is used to solve the improved RPCA model. The results of numerical experiment show that the method proposed in this article has a higher accuracy in the detection of moving objects in dynamic background.

关键词： Matrix decomposition Image segmentation Sparse matrices Heuristic algorithms Video sequences Object detection Motion segmentation Video background foreground separation RPCA superpixel segmentation linear spectral clustering algorithm otsu algorithm motion mask

来源：评论

学校读者我要写书评

暂无评论

Improved optical tomography based on hybrid frequency-domain and time-domain radiative transfer model

引用

INFRARED PHYSICS & TECHNOLOGY 2020年 111卷 103484-103484页

作者： Zhao, Fang-Zhou Qi, Hong Liu, Shao-Bin Ren, Ya-Tao Harbin Inst Technol Sch Energy Sci & Engn 92 West Dazhi St Harbin 150001 Peoples R China Minist Ind & Informat Technol Key Lab Aerosp Thermophys Harbin 150001 Peoples R China

Based on the hybrid frequency-domain (FD) and time-domain (TD) radiative transfer equation (RTE), a novel reconstruction strategy is developed to retrieve the optical parameter fields in the participating medium. The discrete ordinate method is employed to solve the forward FD and TD RTE to simulate the radiative transfer process. The sequential quadratic programming is utilized to solve the inverse problem for obtaining the optical parameters combined with an adjoint method. The otsu algorithm is applied to the FD reconstructed results to distinguish the target region and the background region. To overcome the ill-posedness of the inverse problem, the generalized Gaussian Markov random field model is employed as the regularization term in the objective function. Various numerical experiments are studied and all results demonstrate that the proposed hybrid reconstruction scheme is suitable for efficient and accurate optical tomography by combining the FD and TD radiative transfer models. Meanwhile, the crosstalk of the ill-posed inverse problem can be alleviated effectively.

关键词： Optical tomography otsu algorithm Sequential quadratic programming Frequency-domain and time-domain Radiative transfer equation

来源：评论

学校读者我要写书评

暂无评论

A Window Detection algorithm for Remote Laser Gas Leakage Detection System

引用

Procedia Computer Science 2020年 174卷 720-728页

作者： Xiaozhou Dong Jiaying Li Junxian Wu Juan Liu School of Mechanical Electrical & Information Engineering Shandong University Wei Hai 264200 China

The Remote Laser Gas Leakage Detection System used for gas leak detection in high-rise residential buildings. It aligns the equipment to the windows of the residential kitchen and emits infrared lasers for indoor inspection. This paper proposes a method to combine methane detection with window recognition. By identifying and positioning the window, the required rotation angle to the next window can be returned to the device, thereby guiding it for detection. The window recognition process includes image correction, grayscale and binarization processing, morphological processing, edge detection, and feature extraction. The experimental results show that the method can accurately identify and locate the windows on the facade of residential buildings and guide the equipment for detection.

关键词： Digital Image Processing Methane Detection otsu algorithm

来源：评论

学校读者我要写书评

暂无评论

About quantifying small color differences in digital images

COMPUTER OPTICS

引用

COMPUTER OPTICS 2020年第4期44卷 606-+页

作者： Palchikova, I. G. Smirnov, E. S. Barinova, O. A. Latyshov, I., V Vasiliev, V. A. Kondakov, A., V Technol Design Inst Sci Instrument Engn SB RAS 41 Russkaya Str Novosibirsk 630058 Russia Volgograd Acad Russian Internal Affairs Minist 130 Istoricheskaya Str Volgograd 400075 Russia St Petersburg Univ Russian Internal Affairs Minist 1 Pilot Pilyutov Str St Petersburg 198206 Russia

We discuss aspects of the use and possibilities provided by three-color colorimeters or digital cameras in problems of detecting small color differences by computer vision methods. The spectral dependence of the total color differences between pairs of visually indiscernible monochromatic stimuli is experimentally revealed. An experimental setup based on the UM-2 monochromator is created for producing a digital atlas of monochromatic stimuli at 1-nm increments. The atlas serves to test the color gamut and color differentiation of cameras. It is experimentally shown that in the visible spectral range a color difference of 3 units is detected by pairs of stimuli that are unevenly distributed across the spectrum and differ in wavelengths from 1 to 6 nm. The capabilities of computer vision are tested on the examples of identifying additional texts during a technical and forensic examination of documents. A new algorithm is developed for finding and quantitatively characterizing color difference of inserts based on a digital image of the inscription. In the algorithm, the objective analysis of the image is divided into a block of color segmentation and that of color tone and color difference assessment. With such an approach, the color segmentation block performs preprocessing functions, making a border map for the classes with different colors for the subsequent calculations. The otsu method of optimal global threshold transformation is for the first time applied to a problem of image segmentation by color saturation. The trial of the algorithm confirms its efficiency in the solution of expert tasks.

关键词： digital camera color gamut RGB sensor color monochromatic stimuli dominant wavelength saturation digital image processing otsu algorithm segmentation color difference

来源：评论

学校读者我要写书评

暂无评论

Simulation of the Effect of Noise on Terahertz Digital Holography Reconstructed Image 14

Simulation of the Effect of Noise on Terahertz Digital Holog...

引用

14th National Conference on Laser Technology and Optoelectronics (LTO)

作者： Lin, Ping Li, Qi Shen, Zuochun Harbin Inst Technol Natl Key Lab Sci & Technol Tunable Laser Harbin 150080 Heilongjiang Peoples R China

ISBN: (数字)9781510630475

ISBN: (纸本)9781510630475

In the terahertz imaging experiments, target is often embedded in a support plate (such as PTFE, etc.). Background noise will be caused by many factors, such as uneven material and non-smoothness of support plate. In this paper, the impacts of noise on terahertz in-line digital holography single-exposure, support-domain constrained phase retrieval algorithm and its reconstructed results are simulated. The support domain is determined by the combination of the otsu algorithm and the opening and closing operation. Firstly, the influences of noise on 2.52 terahertz in-line digital holographic reconstruction are studied when the transmittance of support plate is 0.93. The mean value of Gaussian noise of the support plate is 0, and the standard deviation range is between 0 and 0.1, and the interval is 0.005. Mean square error (MSE) and peak signal-to-noise ratio (PSNR) are used as the evaluation criteria. Finally, the Gaussian noise with mean value of 0 and standard deviation of 0.04 is selected to simulate and analyze the effect of the reconstructed image with different transmittances. The results show that, when the transmittance of the support plate is 0.93 and the noise standard deviation is 0-0.04, the peak signal-to-noise ratio is less than 6% lower than of the ideal support plate reconstruction.

关键词： terahertz in-line digital holography support domain phase retrieval algorithm Gaussian noise otsu algorithm

来源：评论

学校读者我要写书评

暂无评论

Sinkhole Detection by Deep Learning and Data Association 11

Sinkhole Detection by Deep Learning and Data Association

引用

11th International Conference on Ubiquitous and Future Networks (ICUFN)

作者： Nam Vu Hoai Nguyen Manh Dung Ro, Soonghwan PTIT Fac Informat Technol Dept Comp Sci Hanoi Vietnam Kongju Univ Deprtment Informat & Commun Cheonan South Korea

ISBN: (纸本)9781728113395

Accurate tracking of the sinkholes that are appearing frequently now is an important method of protecting human and property damage. Although many sinkhole detection systems have been proposed, it is still far from completely solved especially in-depth area. Furthermore, detection of sinkhole algorithms experienced the problem of unstable result that makes the system difficult to fire a warning in real-time. In this paper, we proposed a method of sinkhole tracking that takes advantage of the recent development of CNN transfer learning. Our system consists of three main parts which are binary segmentation, sinkhole classification, and sinkhole tracking. The experiment results show that the sinkhole can be tracked in real-time on the dataset. These achievements have proven that the proposed system is able to apply to the practical application.

关键词： sinkholedetection deep learning sinkhole tracking HA algorithm otsu algorithm

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：