检索结果-内蒙古大学图书馆

Infrared Small Target Detection with UAV Based on Convolutional Neural Networks

engineering Letters 2025年第5期33卷 1505-1512页

作者： Zhang, Jingshi Zhang, Yujun School of Computer and Software Engineering University of Science and Technology Liaoning Anshan114051 China

Infrared target detection is now applied in many fields, such as medical imaging, military detection, autonomous driving, and environmental monitoring with drones. Due to the small size of these targets, complex environments, and limited contextual information, target detection is challenging. Therefore, this paper proposes an improved method for detecting small infrared targets based on the YOLOv9-c ***, we propose dynamic snake convolution (DSConv), a mechanism designed to precisely model tubular structures by adaptively concentrating on elongated and intricate curvilinear features within local regions. Second, we employ a new spatial and channel synergistic attention module (SCSA), integrating the SCSA module into the neck network of YOLOv9. The SCSA framework integrates two synergistic components, the Shared Multi-Semantic Spatial Attention (SMSA) module and the Progressive Channel Self-Attention (PCSA) module. This enhances the synergy between spatial and channel attention across multiple semantic levels. Finally, we introduce the C2F module into multi-scale dilated attention, altering its original dilation rates. C2F MSDA better aggregates semantic information, effectively reducing the redundancy of self-attention mechanisms. This improvement has shown promising results on the public HIT-UAV dataset, raising the average precision to 0.902 and providing potential technological support for the detection of small infrared targets. © 2025, International Association of Engineers. All rights reserved.

关键词： Target drones

来源：评论

学校读者我要写书评

暂无评论

EPipe: Pipeline Inference Framework with High-quality Offline Parallelism Planning for Heterogeneous Edge Devices 24

EPipe: Pipeline Inference Framework with High-quality Offlin...

引用

43rd International Conference on computer-Aided Design, ICCAD 2024

作者： Xiong, Yi Liu, Weihong Zhang, Rui Zu, Yulong Zhu, Zongwei Zhou, Xuehai School of Computer Science and Technology University of Science and Technology of China China Suzhou Institute for Advanced Research University of Science and Technology of China China School of Software Engineering University of Science and Technology of China China

ISBN: (纸本)9798400710773

Pipeline parallelism is essential for edge computing as it effectively consolidates the limited resources of edge devices, enabling the deployment of large Deep Neural Network (DNN) models and accelerating inference processes without compromising the performance of models. Accurate computation and communication latency estimation on heterogeneous edge devices is essential for searching for a superior parallelism plan. However, existing heterogeneous pipeline inference approaches either incur substantial resource wastage during online parallelism planning, as they utilize profiling strategies that occupy physical devices;or rely on cost models with inadequate representational capabilities, leading to inaccurate predictions, thereby harming the result of pipeline planning. This paper proposes EPipe, a novel pipeline inference framework that supports high-quality offline planning in heterogeneous edge environments. EPipe integrates two core components: the Task-Device Co-analyzer (TDC) and the Multi-pipeline Parallelism Planner (MPP). TDC utilizes an undirected connected graph to depict the compatibility of DNNs across device groups and precisely estimates inference and communication latencies through fine-grained modeling. Based on TDC, MPP utilizes a dynamic programming-based genetic algorithm to explore multi-pipeline solutions, extending beyond traditional single-pipeline methods. A comprehensive experimental evaluation on an edge testbed confirms the effectiveness of EPipe, demonstrating significant speedups in inference tasks for both task streams and single tasks. © 2024 Copyright is held by the owner/author(s).

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

Empowering Semantic Segmentation with Selective Frequency Enhancement and Attention Mechanism for Tampering Detection

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 3270-3283页

作者： Xu, Xu Lv, Wenrui Wang, Wei Zhang, Yushu Chen, Junxin Dalian University of Technology School of Software Dalian116621 China Northeastern University School of Computer Science and Engineering Shenyang110004 China Shenzhen MSU-BIT University Guangdong-Hong Kong-Macao Joint Laboratory for Emotion Intelligence and Pervasive Computing Artificial Intelligence Research Institute Shenzhen518172 China Beijing Institute of Technology School of Medical Technology Beijing100081 China Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing210016 China

Nowadays, massive amounts of multimedia contents are exchanged in our daily life, while tampered images are also flooding the social networks. Tampering detection is therefore becoming increasingly important for multimedia integrity, and it is generally realized by designing specific convolutional neural networks. From a new perspective, this article proposes two pluggable modules for empowering existing semantic segmentation models for tampering detection. First, a selective frequency enhancement (SFE) module is developed to suppress the semantic information and selectively enhance the tamper information. Second, a boundary enhanced attention (BEA) module is designed to highlight the edge information of tempered area. Our SFE and BEA modules are combined with five mainstream semantic segmentation networks for performance evaluation. The experiment results demonstrate that our modules are able to empower the semantic segmentation networks for tampering detection, and their combinations even perform better than state-of-the-art algorithms in certain datasets. © 2020 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Research on Map Construction and Location technology Based on Multi-line LiDAR 5th

Research on Map Construction and Location Technology Based o...

引用

5th International Conference on Energy Storage and Intelligent Vehicles, ICEIV 2022

作者： Liu, Fang Yang, Yang Su, Weixing School of Software Engineering Tiangong University Tianjin300387 China School of Computer Science and Technology Tiangong University Tianjin300387 China

ISBN: (纸本)9789819910267

Point cloud registration is an important part of 3D point cloud map construction based on multi-line lidar. At present, traditional iterative nearest point algorithm (ICP) is mainly used for point cloud registration. For the traditional iterative nearest point algorithm, point cloud registration is time-consuming and error-prone, which leads to the low accuracy of point cloud registration. Based on the principle of traditional iterative nearest point algorithm, this paper proposes an improved ICP algorithm combining PL-ICP algorithm and PP-ICP algorithm. The map construction is realized by this method, and on the basis of the map construction, NDT algorithm is used to further realize the positioning of unmanned vehicles. The experimental results show that the method can effectively construct the point cloud image, reduce the registration time of point cloud, and has good registration accuracy. Through the validation of the dataset, the positioning experiment can be completed by randomly placing the unmanned vehicle in a certain position on the constructed map. © 2023, Beijing Paike Culture Commu. Co., Ltd.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

DNBP-CCA:A Novel Approach to Enhancing Heterogeneous Data Traffic and Reliable Data Transmission for Body Area Network

引用

computers, Materials & Continua 2024年第5期79卷 2851-2878页

作者： Abdulwadood Alawadhi Mohd.Hasbullah Omar Abdullah Almogahed Noradila Nordin Salman A.Alqahtani Atif M.Alamri InterNetWorks Research Laboratory School of ComputingUniversiti Utara MalaysiaSintok06010Malaysia Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn MalaysiaParit RajaJohor86400Malaysia School of Games&Creative Technology University for the Creative ArtsFarnhamGU97DSUK Computer Engineering Department College of Computer and Information SciencesKing Saud UniversityRiyadh11543Saudi Arabia Software Engineering Department College of Computer and Information SciencesKing Saud UniversityRiyadh11543Saudi Arabia

The increased adoption of Internet of Medical Things (IoMT) technologies has resulted in the widespread use ofBody Area Networks (BANs) in medical and non-medical domains. However, the performance of IEEE 802.15.4-based BANs is impacted by challenges related to heterogeneous data traffic requirements among nodes, includingcontention during finite backoff periods, association delays, and traffic channel access through clear channelassessment (CCA) algorithms. These challenges lead to increased packet collisions, queuing delays, retransmissions,and the neglect of critical traffic, thereby hindering performance indicators such as throughput, packet deliveryratio, packet drop rate, and packet delay. Therefore, we propose Dynamic Next Backoff Period and Clear ChannelAssessment (DNBP-CCA) schemes to address these issues. The DNBP-CCA schemes leverage a combination ofthe Dynamic Next Backoff Period (DNBP) scheme and the Dynamic Next Clear Channel Assessment (DNCCA)scheme. The DNBP scheme employs a fuzzy Takagi, Sugeno, and Kang (TSK) model’s inference system toquantitatively analyze backoff exponent, channel clearance, collision ratio, and data rate as input parameters. Onthe other hand, the DNCCA scheme dynamically adapts the CCA process based on requested data transmission tothe coordinator, considering input parameters such as buffer status ratio and acknowledgement ratio. As a result,simulations demonstrate that our proposed schemes are better than some existing representative approaches andenhance data transmission, reduce node collisions, improve average throughput, and packet delivery ratio, anddecrease average packet drop rate and packet delay.

关键词： Internet of Medical Things body area networks backoff period tsk fuzzy model clear channel assessment media access control

来源：评论

学校读者我要写书评

暂无评论

Deep Fusion Co-occurrence Hashing for Image Retrieval 5

Deep Fusion Co-occurrence Hashing for Image Retrieval

引用

5th IEEE International Conference on Information Systems and computer Aided Education, ICISCAE 2022

作者： Yang, Ming Wan, Biao School of Computer Technology and Software Engineering Wuhan Polytechnic Wuhan China

ISBN: (数字)9781665481229

ISBN: (纸本)9781665481229

Improving the perception of objects for an image through label co-occurrence correlation is shown to improve the hash quality. Existing methods ignore the relationship between different representation regions and lack highlighting of salient features when fusing co-occurrence label vectors with image embeddings. To tackle this issue, we proposed a new fusion scheme, i.e., Multi-mapping Multi-modal Factorized Bilinear pooling (MMFB), which extends the single image feature to multiple representations to achieve fusion. As a result, we propose a deep fusion co-occurrence hashing algorithm that uses MMFB instead of MFB in the backbone of the label-attended hash (LAH) algorithm and uses SAGPooling to enhance the perception of attention. Extensive experiments over public benchmarks with multiple labels demonstrate that our algorithm can outperform LAH and state-of-the-art hashing algorithms. © 2022 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Locating What You Need: Towards Adapting Diffusion Models to OOD Concepts In-the-Wild 38

Locating What You Need: Towards Adapting Diffusion Models to...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Yang, Jianan Gao, Chenchao Xiao, Zhiqing Zhao, Junbo Wu, Sai Chen, Gang Wang, Haobo College of Computer Science and Technology Zhejiang University China Institute of Blockchain and Data Security China School of Software Technology Zhejiang University China International School of Information Science and Engineering Dalian University of Technology China

The recent large-scale text-to-image generative models have attained unprecedented performance, while people established adaptor modules like LoRA and DreamBooth to extend this performance to even more unseen concept tokens. However, we empirically find that this workflow often fails to accurately depict the out-of-distribution concepts. This failure is highly related to the low quality of training data. To resolve this, we present a framework called Controllable Adaptor Towards Out-of-Distribution Concepts (CATOD). Our framework follows the active learning paradigm which includes high-quality data accumulation and adaptor training, enabling a finer-grained enhancement of generative results. The aesthetics score and concept-matching score are two major factors that impact the quality of synthetic results. One key component of CATOD is the weighted scoring system that automatically balances between these two scores and we also offer comprehensive theoretical analysis for this point. Then, it determines how to select data and schedule the adaptor training based on this scoring system. The extensive results show that CATOD significantly outperforms the prior approaches with an 11.10 boost on the CLIP score and a 33.08% decrease on the CMMD metric. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Based on FCOS and HSV Recognition Algorithms for Oil Level and Implementations of Train Hydraulic Brake 2

Based on FCOS and HSV Recognition Algorithms for Oil Level a...

引用

2nd International Conference on Frontiers of Electronics, Information and Computation Technologies, ICFEICT 2022

作者： Chen, Qiuyang Pan, Kaixin Zhao, Jianyang Ding, Weihong School of Computer and Software Engineering Huaiyin Institute of Technology Huaian China

ISBN: (数字)9781665454766

ISBN: (纸本)9781665454766

An important application in the field of Digital Image Processing is reading water level recognition. Currently, the automatic recognition method of train hydraulic brake oil level is uncommon, mostly by eye observation oil level position which can cause much errors and poor efficiency. Our project is about how to realize the automatic recognition of train hydraulic brake oil level reading. In this regard, we propose a model algorithm based on FCOS and HSV algorithm. © 2022 IEEE.

关键词： Water levels

来源：评论

学校读者我要写书评

暂无评论

Class-Adaptive Threshold for Class Imbalanced Semi-Supervised Learning 29

Class-Adaptive Threshold for Class Imbalanced Semi-Supervise...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Liu, Xiaoyu Wei, Xiang Wang, Jingjie Lu, Siyang Xing, Weiwei School of Software Engineering Beijing Jiaotong University Beijing China School of Computer and Information Technology Beijing Jiaotong University Beijing China

ISBN: (纸本)9798350330717

The recently proposed class-imbalanced semi-supervised learning (CISSL) algorithms achieved impressive performance by effectively leveraging unlabeled data. However, these algorithms often rely on a pre-defined fixed confidence threshold to filter unlabeled data during training, which overlooks the varying learning dynamics across different classes in class-imbalanced scenarios. Consequently, valuable data could be discarded, leading to degraded performance on minority classes. To tackle this issue, we introduce a novel method called Class-Adaptive Threshold (CAT), which dynamically defines and adjusts the confidence threshold based on the learning status of each class. The core idea of CAT is to iteratively update the thresholds for different classes at each time step, enabling us to fully exploit valuable information that would otherwise be ignored using fixed threshold algorithms. Importantly, CAT does not introduce any additional inference processes. In our experiments, the proposed algorithm achieves state-of-the-art performance on various class-imbalanced datasets. Furthermore, we show that CAT can be seamlessly integrated into the renowned CISSL algorithm, resulting in a remarkable boost in their performance. © 2023 IEEE.

关键词： class-imbalance class-imbalanced semi-supervised learning dynamic threshold semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Learning Label Shift Correction for Test-Agnostic Long-Tailed Recognition 41

Learning Label Shift Correction for Test-Agnostic Long-Taile...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wei, Tong Mao, Zhen Zhou, Zi-Hao Wan, Yuanyu Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China School of Software Technology Zhejiang University Ningbo China

Long-tail learning primarily focuses on mitigating the label distribution shift between long-tailed training data and uniformly distributed test data. However, in real-world applications, we often encounter a more intricate challenge where the test label distribution is agnostic. To address this problem, we first theoretically establish the substantial potential for reducing the generalization error if we can precisely estimate the test label distribution. Motivated by the theoretical insight, we introduce a simple yet effective solution called label shift correction (LSC). LSC estimates the test label distribution within the proposed framework of generalized black box shift estimation, and adjusts the predictions from a pre-trained model to align with the test distribution. Theoretical analyses confirm that accurate estimation of test label distribution can effectively reduce the generalization error. Extensive experimental results demonstrate that our method significantly outperforms previous state-of-the-art approaches, especially when confronted with non-uniform test label distribution. Notably, the proposed method is general and complements existing long-tail learning approaches, consistently improving their performance. The source code is available at https://***/Stomach-ache/label-shift-correction. Copyright 2024 by the author(s)

关键词： Black-box testing

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：