检索结果-内蒙古大学图书馆

4th IEEE International conference on Image, Vision and Computing, ICIVC 2019

作者： Zeng, Qinghao Chen, Jinlong Yang, Minghao University of Electronic Technology Guangxi Key Laboratory of Trusted Software of Guilin Guilin541004 China University of Electronic Technology Guangxi Key Laboratory of Cryptography and Information Security of Guilin Guilin541004 China Chinese Academy of Sciences Key Laboratory of Pattern Recognition Institute of Automation Beijing100190 China

ISBN: (纸本)9781728123257

Aiming at the aircraft target in visible light remote sensing image, this paper proposes a false alarm removal method for target detection under small sample training conditions. First, use data enhancement methods for small sample data to increase the number of samples and improve the generalization ability of features. Then, according to the clear outline of the aircraft target and the obvious characteristics of the edge features, the Haar feature plus AdaBoost algorithm is used to preliminary detect the aircraft target. Finally, the convolutional neural network is used to extract the target features, and the preliminary detection results are classified to remove the false alarm targets and improve the accuracy of the detection. The experimental results show that the detection effect is good in aircraft target detection. © 2019 IEEE.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

The application of difference method to dim point target detection in infrared images

The application of difference method to dim point target det...

引用

IEEE National conference on Aerospace and Electronics (NAECON)

作者： Wei-Ping Yang Zhen-Kang Shen Zhi-Yong Li Department of Elecetrical Engineering National University of Defense Technology Changsha Hunan China

ISBN: (纸本)0780318935

This paper deals with the detection of dim point targets in infrared images. Dim point targets detection is always a difficulty in information processing. Researchers have proposed many effective methods; this paper introduces a new method. Whereas difference method has obtained good result in one dimensional signal processing, this paper manages to apply it to two dimensional signal processing, that is to say, dim point targets detection in infrared images of low SNR. The image background is color noise, and its column correlation is strong. So, ordinary methods probably lose the true targets because of the strong color noise, but unlike them, difference method can overcome this shortcoming, it can eliminate correlation noise and enhance useful information, finally pick out the probable targets from noise background. In the paper, the method was given a more extensive account. In order to improve the detection effect, we utilize prefilter. The prefilter is realized by the alpha filter. Because the same targets have same location in more than three frames, using alpha filter can utilize the information of adjacent frames, increase the SNR of the raw data and reduce the noise of the images.< >

关键词： Object detection Colored noise Infrared detectors Infrared imaging signal processing signal to noise ratio Background noise Filters Information processing Information filtering

来源：评论

学校读者我要写书评

暂无评论

Optimization of lifting wavelet filters for ECG data compression

International Conference on Signal Processing Proceedings, I...

引用

International conference on signal processing Proceedings, ICSP 1998年 1卷 249-252页

作者： Kuzume, Koichi Niijima, Koichi Yuge Natl Coll of Technology Ehime-ken Japan

This paper presents a new method to design wavelet filters optimized for Electrocardiogram (ECG) data compression. The feature of these filters, called adaptive lifting wavelet filters, is to set the variance of distribution of wavelet coefficients small adapting to the ECG signals. Designed filters are almost compactly supported and a perfect reconstruction.

关键词： Adaptive filtering

来源：评论

学校读者我要写书评

暂无评论

Seismic Fault SAM: Adapting SAM with Lightweight Modules and 2.5D Strategy for Fault Detection 17

Seismic Fault SAM: Adapting SAM with Lightweight Modules and...

引用

17th IEEE International conference on signal processing, ICSP 2024

作者： Chen, Ran Zhang, Zeren Ma, Jinwen Peking University School of Mathematical Sciences Department of Information and Computational Sciences Beijing100871 China

ISBN: (纸本)9798350387384

Seismic fault detection holds significant geographical and practical application value, aiding experts in subsurface structure interpretation and resource exploration. Despite some progress made by automated methods based on deep learning, research in the seismic domain faces significant challenges, particularly because it is difficult to obtain high-quality, largescale, open-source, and diverse datasets, which hinders the development of general foundation models. Therefore, this paper proposes Seismic Fault SAM, which, for the first time, applies the general pre-training foundation model - Segment Anything Model (SAM) - to seismic fault interpretation. This method aligns the universal knowledge learned from a vast amount of images with the seismic domain tasks through an Adapter design. Specifically, our innovative points include designing lightweight Adapter modules, freezing most of the pre-training weights, and only updating a small number of parameters to allow the model to converge quickly and effectively learn fault features;combining 2.5D input strategy to capture 3D spatial patterns with 2D models;integrating geological constraints into the model through prior-based data augmentation techniques to enhance the model's generalization capability. Experimental results on the largest publicly available seismic dataset, Thebe, show that our method surpasses existing 3D models on both OIS and ODS metrics, achieving state-of-the-art performance and providing an effective extension scheme for other seismic domain downstream tasks that lack labeled data. © 2024 IEEE.

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

Algorithms exploiting ultrasonic sensors for subject classification

Algorithms exploiting ultrasonic sensors for subject classif...

引用

Unmanned/Unattended Sensors and Sensor Networks VI conference

作者： Desai, Sachi Quoraishee, Shafik U.S. Army RDECOM ARDEC Picatinny Arsenal NJ 07806-5000 United States

ISBN: (纸本)9780819477866

Proposed here is a series of techniques exploiting micro-Doppler ultrasonic sensors capable of characterizing various detected mammalian targets based on their physiological movements captured a series of robust features. Employed is a combination of unique and conventional digital signal processing techniques arranged in such a manner they become capable of classifying a series of walkers. These processes for feature extraction develops a robust feature space capable of providing discrimination of various movements generated from bipeds and quadrupeds and further subdivided into large or small. These movements can be exploited to provide specific information of a given signature dividing it in a series of subset signatures exploiting wavelets to generate start/stop times. After viewing a series spectrograms of the signature we are able to see distinct differences and utilizing kurtosis, we generate an envelope detector capable of isolating each of the corresponding step cycles generated during a walk. The walk cycle is defined as one complete sequence of walking/running from the foot pushing off the ground and concluding when returning to the ground. This time information segments the events that are readily seen in the spectrogram but obstructed in the temporal domain into individual walk sequences. This walking sequence is then subsequently translated into a three dimensional waterfall plot defining the expected energy value associated with the motion at particular instance of time and frequency. The value is capable of being repeatable for each particular class and employable to discriminate the events. Highly reliable classification is realized exploiting a classifier trained on a candidate sample space derived from the associated gyrations created by motion from actors of interest. The classifier developed herein provides a capability to classify events as an adult humans, children humans, horses, and dogs at potentially high rates based on the tested sample s

关键词： Digital signal processing

来源：评论

学校读者我要写书评

暂无评论

Adaptive air-to-air target tracking in severe jamming environment

Adaptive air-to-air target tracking in severe jamming enviro...

引用

作者： Feldmann, Michael Nickel, Ulrich Koch, Wolfgang Sensor Data and Information Fusion Dept. Fraunhofer FKIE Neuenahrer Str. 20 53343 Wachtberg Germany

ISBN: (纸本)9781457702679

In the presence of jamming, the task of tracking targets using adaptive phased array radars raises challenges for both signal processing and tracking algorithms. While algorithms for deep nulling of jammers, such as adaptive beamforming, are well-known, tracking algorithms still have to face the problem of the jammer notch, where targets are barely visible (for the antenna) due to jamming interference and/or adaptive jammer suppression. On top of that, tracking algorithms have to cope with inaccurate predictions and large bias of measurements, possibly leading to track instabilities culminating in track loss. This paper deals with the problem of maintaining a track for a single target in severe jamming environment. We present different stabilization measures to improve track stability and track continuity (e.g., avoidance of antenna look directions in the jammer notch, usage of pseudo-measurements to maintain the track file if the predicted target direction is in the jammer notch, etc.). In this context, the most accurate modeling of angle measurement uncertainties plays a decisive role. Simulation results demonstrate significant improvements of tracking performance. © 2011 IEEE.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Research on Exam Behavior Recognition Based on Efficientnet Improvement

Research on Exam Behavior Recognition Based on Efficientnet ...

引用

signal processing and Intelligent Computing (SPIC), International conference on

作者： Ning Gan Jingyi Zhang Wenhong Liu College of Automation and Electrical Engineering Shengyang Ligong University Shenyang China College of Information Science and Engineering Northeastern University Qinghuangdao China

ISBN: (数字)9798350368888

ISBN: (纸本)9798350368895

This article addresses issues such as poor real-time recognition of student exam behavior and difficulty in detecting small ***, the attention CBAM module is introduced to perform attention operations in both spatial and channel dimensions, making the model more focused on the target ***, the feature fusion module is improved in Efficientnet to enable the model to obtain more small target features and further enhance its ability to detect small targets; Based on these optimization methods, a new object detection model EfficientZet-L-S was developed, and automatic recognition experiments were conducted using simulated exam scene video *** average accuracy of identifying inappropriate behavior in the examination room increased from 75.6% to 81.3%.

关键词： Training Accuracy Attention mechanisms Target recognition signal processing algorithms Object detection Streaming media signal processing Feature extraction Real-time systems

来源：评论

学校读者我要写书评

暂无评论

A Ship Target Detection Method for SAR Image Based on Local Region

A Ship Target Detection Method for SAR Image Based on Local ...

引用

International Radar conference (RADAR)

作者： Xie, Weitong Du, Lan Dai, Hui Li, Yi Xidian Univ Natl Lab Radar Signal Proc Xian Peoples R China

ISBN: (纸本)9781728126609

Using the knowledge of image processing, machine learning and pattern recognition to develop the techniques of acquiring target regions from Synthetic Aperture Radar (SAR) images accurately has caught researchers' wide attention. A ship target detection method for SAR image based on local region under the multi-scale and multi-target condition is introduced in this paper. This method firstly learns the gradient-based local region generation mode based on the training data with object annotation, then generates a small number of local regions with different sizes, and finally uses the local region based CFAR detector, where the extracted object regions are regarded as the guard windows instead of setting fixed guard window to detect the true object regions. Due to the introduction of local regions, the proposed method can obtain good detection performance in the multi-scale situation, and directly obtain the accurate target regions to avoid the problem caused by the target clustering in traditional ship detection method. The effectiveness of the proposed method is verified using measured RADASAT-2 data by comparing with the traditional SAR ship target detection methods.

关键词： local regions constant false alarm rate (CFAR) synthetic aperture radar (SAR) images target detection

来源：评论

学校读者我要写书评

暂无评论

RTUNet++: Assessment of Osteosarcoma MRI Image Segmentation leveraging Hybrid CNN-Transformer Approach with Dense Skip Connection 8

RTUNet++: Assessment of Osteosarcoma MRI Image Segmentation ...

引用

8th International conference on signal and Image processing, ICSIP 2023

作者： Zou, Binfeng Chen, Yifei Chen, Zhanghao Sun, Yifei Huang, Yifan Qin, Feiwei Wang, Changmiao HDU-ITMO Joint Institute Hangzhou Dianzi University Hangzhou China Hangzhou Dianzi University School of Computer Science and Technology Hangzhou China Shenzhen Research Institute of Big Data Medical Big Data Lab Shenzhen China

ISBN: (纸本)9798350397932

Orthopedic osteosarcoma is a prevalent malignant bone tumor. Preoperative planning, efficacy evaluation, and metastasis detection of osteosarcoma necessitate the use of magnetic resonance imaging (MRI). Due to the varying 10-cations, structures, sizes, and shapes of osteosarcomas among patients, as well as the high degree of tumor heterogeneity, segmenting osteosarcoma images manually presents a significant challenge for clinicians. In the meantime, the grayscale and texture features within the tumor in MRI images are not homogeneous, resulting in small grayscale differences between the tumor tissue and the surrounding normal tissue, which also presents a significant challenge for deep learning-based image segmentation methods. This paper proposes RTUNet++, a novel method for segmenting osteosarcoma MRI images. This method integrates the ResNet residual module, Transformer attention mechanism, and UNet++ Dense Skip Connection structure. We employ a CNN-Transformer hybrid architecture to prevent the loss of spatial feature data. Features with different semantic scales are aggregated at the decoder using multi-fusion dense jump connections to achieve flexible feature fusion. Consequently, in comparison experiments with various classical models, our proposed RTUNet++ achieves superior segmentation results on an osteosarcoma MRI image dataset. © 2023 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Research on Imaging Algorithm of Industrial Pipeline Detection Based on List-Mode data 5

Research on Imaging Algorithm of Industrial Pipeline Detecti...

引用

5th International conference on Intelligent Control, Measurement and signal processing, ICMSP 2023

作者： Wang, Ming Zhao, Min Yao, Min Ma, Bolin Xiao, Hui College of Automation Engineering Nanjing University of Aeronautics and Astronautics Nanjing China

ISBN: (纸本)9798350336030

In order to realize the y-photon nondestructive detection of industrial confined pipelines, it is necessary to construct large axial ring y-photon detectors, but with the increase of the axial length of the detectors, the acquisition of response lines will be truncated and missing, resulting in the degradation of the detection imaging quality in large axial space. In this paper, we propose a list-mode data-based imaging algorithm for industrial confined pipe detection, which makes full use of the list-mode to conform to the position and time information in the event and to reasonably assign the weights of the system matrix in the image reconstruction. When calculating the weight contribution of the pixels passing through a response line to that response line, only the pixels within the uncertainty range need to be calculated without the pixels corresponding to the complete response line, and the system matrix containing time-of-flight (TOF) information is obtained, thus effectively suppressing the noise caused by truncated and missing large axial spatial data. In addition, the parallel feature of CUDA is also used to divide the system matrix calculation process into small blocks that are independent of each other to achieve accelerated optimization of the algorithm. Finally, two industrial models are used for simulation experiments, and the experimental results show that the proposed method can significantly improve the resolution and spatial contrast of large axial spatial reconstruction images in industrial confined pipeline inspection, and can meet the demand of y-photon nondestructive inspection of industrial confined pipelines. © 2023 IEEE.

关键词： Photons

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：