检索结果-内蒙古大学图书馆

24th International Conference on Electronic Packaging technology (ICEPT)

作者： Jiang, Ye Liu, Zhiyong Liao, Guanglan Huazhong Univ Sci & Technol Sch Mech Sci & Engn Wuhan Peoples R China

ISBN: (纸本)9798350338812;9798350338829

The chip on PCBA is developing towards miniaturization and high density. It becomes more difficult to detect micro solder bump defects inside the electronic package and soldering defects cause 71% of electronic package problems. However, fault diagnosis in the industrial manufacturing scenario is more complex and diverse involving the detection and location of solder bump defects at the IC level. As an attractive option to package inspection, X-ray may seriously affect the service life of ICs. Our group proposed a nondestructive diagnosis method on the basis of active thermography. In the recorded thermal image, the solder ball was segmented for the classification analysis. Due to the large size of PCBA, the narrow gap laser is limited to industrial applications. Because of the inefficiency and low identification rate of current detection, here we propose a detection method using infrared thermal imaging and Omni-scale CNN deep learning algorithm. We take the real chip as the experimental target. The infrared thermal sequence is collected to analyze the temperature evolution of different defect types. We use the target region segmentation to extract features to distinguish the invisible solder defects in infrared images. With the hyperparameter optimization, the Omni-scale CNN classification model realizes efficient and highly accurate detection of different solder (400 mu m-500 mu m) defect types.

关键词： Solder bump infrared sequence Chip on board Defect detection Deep learning

来源：评论

学校读者我要写书评

暂无评论

Study on efficient recognition and accurate localization method of waste plastic bottles based on deep learning

引用

ECOLOGICAL INFORMATICS 2025年 86卷

作者： Xie, Shilong Wu, Hu Mao, Wenjie Chu, Xianlong Meng, Yixing Yang, Xianhai Shandong Univ Technol Sch Mech Engn Zibo 255000 Peoples R China

As a vital component of ecologically sustainable development, the effective recovery and reuse of waste plastic bottles is essential for environmental protection and resource recycling. Given the varying recycling values of plastic bottles based on their colors, precise sorting and recycling are particularly important. Traditional manual sorting methods face challenges such as low efficiency and high costs. In contrast, machine vision-based image recognition technology offers a more efficient solution for classifying and recovering waste plastic bottles, with classification recognition and target positioning being critical technologies for the optimal use of ecological resources. This study introduces a deep learning approach for identifying and locating waste plastic bottles, utilizing the reversible column network (RevCol) as the backbone to prevent information loss. A lightweight combined decoupling head is designed to minimize computational load while enhancing accuracy. The Weighted Intersection over Union version 3 (WIoU v3) loss function is incorporated to improve detection performance. By leveraging depth information from an infrared camera alongside RGB image mapping, the method achieves recognition and three-dimensional positioning. Experimental results indicate that the proposed model outperforms traditional models, with a 36.39 % reduction in parameters and a 50.62 % decrease in computational requirements, while accuracy and recall rates improve by 4.56 % and 12.14 %, respectively. Additionally, mAP50 and mAP50-95 values increase by 5.86 % and 3.89 %, and the recognition speed reaches 62 FPS, a 51.22 % improvement, meeting real-time detection needs. Experiments conducted on a deep learning-UR5 robot platform demonstrate high recognition accuracy and sorting success rates in actual waste plastic bottle sorting scenarios. The promotion and implementation of this method will significantly enhance the recycling of waste plastic resources and contribute to th

关键词： Recycling of waste plastic bottles Machine vision Deep learning target recognition classification detection Three-dimensional positioning

来源：评论

学校读者我要写书评

暂无评论

infrared target recognition with deep learning algorithms

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第11期82卷 17213-17230页

作者： Xu, Laixiang Zhao, Fengjie Xu, Peng Cao, Bingxu Hainan Univ Sch Informat & Commun Engn Haikou 570228 Hainan Peoples R China Hainan Univ Sch Biomed Engn Key Lab Biomed Engn Hainan Prov Haikou 570228 Hainan Peoples R China Zhengzhou Univ Henan Sui Xian Peoples Hosp Shangqiu Peoples Hosp 1 Dept Pediat Shangqiu 476000 Peoples R China Zhengzhou Univ Affiliated Hosp 1 Shangqiu 476000 Peoples R China Xinjiang Shen Huo Garbon Co Ltd Roasting 2 Branch Fukang 831500 Peoples R China Henan Univ Technol Luohe Vocat Technol Coll Luohe Inst Technol Sch Informat Engn Luohe 462000 Peoples R China

infrared automatic target recognition (ATR) technology still is a challenging problem in military applications. In recent years, convolutional neural networks (CNNs) models have already led to breakthrough developments in object detection and target recognition. However, the complex environment and the bad weather caused the poor texture information and the weak background of infrared imaging. It's difficult to use standard CNNs to perform accurate feature extraction and target classification. To overcome these shortcomings, we propose a novel deep learning framework, composed of the multi-kernel transformation and the Alpha-Beta divergence. The multi-kernel transformation operation is designed between convolutional layers and pooling layers to increase the confidence of feature extraction. The Alpha-Beta divergence is used as a penalty term to re-encode the output neurons of improved CNNs, which can promote the recognition performance of the entire network. Furthermore, comprehensive theoretical analysis and extensive experiments are confirmed that our proposed framework outperforms ResNet, VGG-19, DenseNet, and the different combinations of models in many aspects, such as short time-consuming, high accuracy, and strong robustness. Our approach yields a maximum accuracy score of 98.43% on our dataset. Meanwhile, we use the OKTAL-SE-based synthetic database and the SENSIAC dataset to verify our models. Experimental results demonstrate the maximum average accuracy is 97.16%, it is feasible and effective for infrared target recognition.

关键词： infrared automatic target recognition Deep learning ALPHA-Beta divergence

来源：评论

学校读者我要写书评

暂无评论

Recognition Method for Dim and Small target Based on Optimized Separable Convolution 24

Recognition Method for Dim and Small Target Based on Optimiz...

引用

4th International Conference on Control and Intelligent Robotics, ICCIR 2024

作者： Hu, Shuang Wu, Lihua Cao, Rui Northwest Institute of Nuclear Technology Xi'an China

ISBN: (纸本)9798400709937

The identification of dim and small targets in space is of great significance for space security and national defense, therefore, in order to effectively solve the classification ability of infrared detection dim small target recognition, a dim and small target recognition method based on optimized separable convolution is proposed. Firstly, according to the characterization characteristics of small and weak targets in infrared detection, the infrared characterization mathematical model of small and weak targets is established. Secondly, a recognition network with noise reduction function and low complexity is constructed by using the wavelet function as the activation function through the lightweight processing of the deeply separable convolution network. Finally, the effectiveness of the identification method is verified by simulation experiments and evaluation analysis. The simulation results show that at the same SNR, the recognition accuracy has been improved by 2.2%, reaching a maximum of 97.1%, and the time has been improved by 93.92%. The proposed method has higher recognition accuracy and efficiency. © 2024 held by the owner/author(s).

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

An Efficient Sun Glitter detection and classification Algorithm in infrared Scenes 49

An Efficient Sun Glitter Detection and Classification Algori...

引用

infrared technology and Applications XLIX 2023

作者： Özertem, Kemal Arda Dept. of Seeker Design Roketsan Elmadağ Ankara06780 Turkey

ISBN: (数字)9781510661837

ISBN: (纸本)9781510661820

Sunlight reflected on the moving sea surface, often referred as sun glitter, can significantly impact the input data in many application areas like defense, security and border surveillance. The effectiveness of vision-based algorithms like target detection and tracking will decrease remarkably under the sun glitter. To deal with this drawback and give a reaction, the sun glitter should be detected in the scene firstly. In this paper, a straightforward and efficient sun glitter detection and classification method for infrared scenes is introduced. In the first step, the behavior of sun glitter in infrared scenes is analyzed. Two stepped frame buffering strategy with dilation process is used to model the spatiotemporal connection between glitter points. After some thresholding steps, the sun glitter detection decision is taken by checking the total number of glitter candidate pixels. And the classification, which means labeling the sun glitter level as low, mid or high for the scope of this paper, is made by checking the number of blobs that are close to each other. The performance of proposed algorithm is tested with real world infrared dataset, which has 30 different scenarios. © 2023 SPIE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

A sensor fusion system with thermal infrared camera and LiDAR for autonomous vehicles and deep learning based object detection

引用

ICT EXPRESS 2023年第2期9卷 222-227页

作者： Choi, Ji Dong Kim, Min Young Kyungpook Natl Univ Dept Future Automot & IT Convergence Daegu South Korea Kyungpook Natl Univ Sch Elect & Elect Engn Daegu South Korea

Vision, Radar, and LiDAR sensors are widely used for autonomous vehicle perception technology. Especially object detection and classification are primarily dependent on vision sensors. However, under poor lighting conditions, dazzling sunlight, or bad weather an object might be difficult to be identified with general vision sensors. In this paper, we propose a sensor fusion system that combines a thermal infrared camera and a LiDAR sensor that can reliably detect and identify objects even in environments with poor visibility, such as day or night. The proposed method obtains the external parameters of the two sensors by designing and manufacturing a 3D calibration target to externally calibrate the thermal infrared camera and the LiDAR sensor. To verify the performance, experiments were conducted in day and night environments. The proposed sensor system and fusion algorithm show that it can reliably detect and identify objects even in environments with poor visibility, such as day or night. (c) 2022 The Author(s). Published by Elsevier B.V. on behalf of The Korean Institute of Communications and Information Sciences. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).

关键词： Sensor fusion LiDAR Thermal infrared camera Autonomous vehicles Object detection Convolution neural network

来源：评论

学校读者我要写书评

暂无评论

A Novel Method Based on Multi-Molecular infrared (MM-IR) AlexNet for Rapid detection of Trace Harmful Substances in Flour

引用

FOOD AND BIOPROCESS technology 2023年第3期16卷 667-676页

作者： Lin, Xiao-Wen Li, Fei-Li Wang, Song Xie, Jun Pan, Qian-Nan Wang, Ping Xu, Chang-Hua Shanghai Ocean Univ Coll Food Sci & Technol Shanghai 201306 Peoples R China Shanghai Engn Res Ctr Aquat Prod Proc & Preservat Shanghai 201306 Peoples R China Minist Agr Lab Qual & Safety Risk Assessment Aquat Prod Stor Shanghai 201306 Peoples R China Natl R&D Branch Ctr Freshwater Aquat Prod Proc Te Shanghai 201306 Peoples R China Shanghai Qinpu Biotechnol Pte Ltd Shanghai 201306 Peoples R China Tianjin Univ Tradit Chinese Med Sch Chinese Mat Med Tianjin 300193 Peoples R China

Due to the severe hazard of traces of harmful substances in flour and its massive production, pretreatment-free, rapid, and accurate determination of trace harmful substances was a practical and urgent demand in modern daily life. In this study, multi-molecular infrared (MM-IR), consisting of one-dimensional infrared (1D-IR), synchronous and asynchronous two-trace two-dimensional correlation infrared (2T-2DCOS-IR), as well as their RGB IR-image, was developed and employed to directly identify flour with diverse harmful substances. The present findings indicated that 2T-2DCOS analysis based on asynchronous pictures was better than others at identifying target substances and shedding new light on previous MM-IR-related studies. Systematical comparison of developed MM-IR-AlexNet flour models with conventional machine learning algorithms indicated that asynchronous MM-IR-AlexNet (2T-2DCOS-IR-AlexNet) had the best performance with 99.6% accuracy. Therefore, it was demonstrated that deep learning-based MM-IR could be a robust method for the direct detection of trace harmful substances in power foods.

关键词： Flour Deep learning MM-IR-AlexNet classification Asynchronous spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Drone-based Bistatic SAR-infrared Cross-modality vehicle detection and classification 3

Drone-based Bistatic SAR-Infrared Cross-modality vehicle det...

引用

2024 3rd International Conference on Image Processing, Object detection, and Tracking, IPODT 2024

作者： Geng, Zhe Da Vida, Bilendo Delvis Xu, Chongqi Zhang, Shiyu Yu, Xiang Zhu, Daiyin College of Electronic and information Engineering Nanjing University of Aeronautics and Astronautics Nanjing211106 China School of Computer Engineering Nanjing Institute of Technology Nanjing211167 China

ISBN: (数字)9781510685529

ISBN: (纸本)9781510685512

Unlike computer vision datasets, aerial images often come with prior knowledge on the distance between the object of interest and the sensors, which makes it possible to recover the sizes of the targets before making any predictions. On the other hand, these images usually consist of large amount of both out-of-library (OOL) targets of high values and clutters, which makes it very challenging to strike a balance between recall rate and precision. To effectively combine the complementary information contained in the aerial images collected by the synthetic aperture radar (SAR) systems and infrared (IR) sensors mounted on drones, a novel two-stage cross-modality vehicle detection and classification strategy is proposed. In Stage 1, all the potential targets are sorted out to form a large candidate pool by jointly considering the target features exhibited in both the SAR and the IR images so that targets with low radar cross section (RCS) are preserved. In Stage 2, multichannel convolution neural network (CNN) models are used to identify the in-library targets based on the multiview target chips while rejecting all the others as either OOL objects of interest or clutters. Experiment results show that the proposed two-stage multiview cross-modality network model architecture offers superior target detection and classification performance than the single-stage deep neural networks relying solely on the IR or SAR data. © 2024 SPIE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

infrared Small UAV target detection Algorithm Based on Enhanced Adaptive Feature Pyramid Networks

引用

IEEE ACCESS 2022年 10卷 115988-115995页

作者： Zheng Lu Peng Yueping Ye Zecong Jiang Rongqi Zhou Tongtong Engn Univ PAP Xian 710086 Peoples R China Engn Univ PAP Coll Informat Engn Xian 710086 Peoples R China

Under the explosive growth of "low-slow-small" unmanned aerial vehicles (UAVs), harassment incidents with "low-slow-small" UAVs, such as illegal surveying and mapping, no-fly zone flights, terrorist attacks, have frequently been occurring due to the low entry barrier to the industry and the lack of market norms and control standards, and severely impair the safety of public life and property. The premise of developing anti-UAV technology is efficient and accurate UAV target detection, which plays a vital role in the follow-up UAV target tracking, attack, and interception. This paper proposes a new DEAX algorithm named enhanced adaptive feature pyramid networks-based target detection Algorithm for infrared small UAV target detection. Our proposed algorithm improves the original feature pyramid networks in four aspects for the small UAV target detection task. 1) Use channel separation to keep more channels when adjusting the number of channels in convolutional to avoid the loss of helpful feature information;2) Design a feature enhancement module to enhance "target feature" and suppress "non-target feature";3) Alleviate the differences of receptive fields and semantic information among different layers by shared convolution;4) Introduce adaptive feature fusion method into feature fusion and complete the construction of enhanced adaptive feature pyramid networks (EAFPN) to solve the problem of weakening feature expression in cross-scale feature fusion. EAFPN is applied to the single-stage target detection networks. We find the detection accuracy and speed of the algorithm outperform those based on feature pyramid networks (FPN), where the improvement on mAP is 8.9%.

关键词： Feature extraction Object detection Semantics detection algorithms target tracking Imaging classification algorithms Object detection feature pyramid feature enhancement

来源：评论

学校读者我要写书评

暂无评论

Defect detection of photovoltaic panel based on morphological segmentation 12

Defect detection of photovoltaic panel based on morphologica...

引用

SPIE 12th International Symposium on Multispectral Image Processing and Pattern Recognition, MIPPR 2023

作者： Cheng, Bolin Li, Bolin Ye, Liang Hubei Key Laboratory of Optical Information and Pattern Recognition China Hubei Engineering Research Center of Video Image and HD Projection China School of Electrical and Information Engineering Wuhan Institute of Technology Wuhan430205 China

ISBN: (数字)9781510674943

ISBN: (纸本)9781510674936

The automatic inspection of photovoltaic panels based on infrared images is one of the important tasks in the daily maintenance of photovoltaic panels in photovoltaic power plants. In this paper, a defect detection method of infrared thermal image photovoltaic panel based on morphological segmentation is proposed. First of all, according to the infrared characteristics of the photovoltaic plant station and the morphological characteristics of the photovoltaic panel, the accurate region of each photovoltaic panel is determined in the inspection image. Then, statistical method is used for feature analysis to determine whether there are defects in photovoltaic panels, and then the defective photovoltaic panels are segmented and different defects are classified according to morphological characteristics, and finally the defect detection and classification of photovoltaic panels are realized. Through the experiment in the actual inspection image of photovoltaic plant station, it is verified that the proposed method has a high accuracy of defect detection and recognition. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Morphology

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：