Chinese Journal of Electronics最新文献_第8页

An Improved YOLOv7 Tiny Algorithm for Vehicle and Pedestrian Detection with Occlusion in Autonomous Driving 基于改进YOLOv7微小算法的自动驾驶车辆与行人遮挡检测

IF 1.6 4区计算机科学

Chinese Journal of Electronics Pub Date : 2025-01-01 DOI: 10.23919/cje.2023.00.256

Jian Su;Fang Wang;Wei Zhuang

{"title":"An Improved YOLOv7 Tiny Algorithm for Vehicle and Pedestrian Detection with Occlusion in Autonomous Driving","authors":"Jian Su;Fang Wang;Wei Zhuang","doi":"10.23919/cje.2023.00.256","DOIUrl":"https://doi.org/10.23919/cje.2023.00.256","url":null,"abstract":"Future transportation is advancing in the direction of intelligent transportation systems, where an essential part is vehicle and pedestrian detection. Due to the complex urban traffic environment, vehicles and pedestrians in road monitoring have different forms of occlusion problems, resulting in the missed detection of objects. We design an improved you only look once version 7 (YOLOv7) tiny algorithm for vehicle and pedestrian detection under occlusion, with the following four main improvements. In order to locate the object more accurately, <tex>$1 times 1$</tex> convolution and identity connection are added to the <tex>$3 times 3$</tex> convolution, and convolution reparameterization is used to enhance the inference speed of the network model. In view of the complex road background and more interference, the coordinate attention was added to the connection part of backbone and neck to enhance the network's capacity to detect the object and lessen interference from other targets. At the same time, before being sent to the detection head, global attention mechanism is added to improve the accuracy of model detection by capturing three-dimensional features. Considering the issue of imbalanced training samples, we propose focal complete intersection over union (CIOU) loss instead of CIOU loss to become the bounding box regression loss, so that the regression process attention to high-quality anchor boxes. Experiments show that the improved YOLOv7 tiny algorithm achieves 82.2% map @ 0.5 in pattern analysis, statistical modelling and computational learning visual object classes dataset, which is 2.8% higher than before the improvement. The performance of map @ 0.5:0.95 is 5.2% better than the previous improvement. The proposed improved algorithm can availably to detect partial occlusion objects.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 1","pages":"282-294"},"PeriodicalIF":1.6,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10891995","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143446190","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

IPFA-Net: Important Points Feature Aggregating Net for Point Cloud Classification and Segmentation IPFA-Net：用于点云分类和分割的重要点特征聚合网络

IF 1.6 4区计算机科学

Chinese Journal of Electronics Pub Date : 2025-01-01 DOI: 10.23919/cje.2023.00.065

Jingya Wang;Yu Zhang;Bin Zhang;Jinxiang Xia;Weidong Wang

{"title":"IPFA-Net: Important Points Feature Aggregating Net for Point Cloud Classification and Segmentation","authors":"Jingya Wang;Yu Zhang;Bin Zhang;Jinxiang Xia;Weidong Wang","doi":"10.23919/cje.2023.00.065","DOIUrl":"https://doi.org/10.23919/cje.2023.00.065","url":null,"abstract":"This paper focuses on the problems of point cloud deep neural networks in classification and segmentation tasks, including losing important information during down-sampling, ignoring relationships among points when extracting features, and network performance being susceptible to the sparsity of point cloud. To begin with, this paper proposes a farthest point sampling-important points sampling method for down-sampling, which can preserve important information of point clouds and maintain the geometry of input data. Then, the local feature relation aggregating method is proposed for feature extraction, improving the network's ability to learn contextual information and extract rich local region features. Based on these methods, the important points feature aggregating net (IPFA-Net) is designed for point cloud classification and segmentation tasks. Furthermore, this paper proposes the multi-scale multi-density feature connecting method to reduce the negative impact of point cloud data sparsity on network performance. Finally, the effectiveness of IPFA-Net is demonstrated through experiments on ModelNet40, ShapeNet part, and ScanNet v2 datasets. IPFA-Net is robust to reducing the number of point clouds, with only a 3.3% decrease in accuracy under a 16-fold reduction of point number. In the part segmentation experiments, our method achieves the best segmentation performance for five objects.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 1","pages":"322-337"},"PeriodicalIF":1.6,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10892000","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143446192","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A High-Resolution Calibration Method for Time-to-Digital Converter of Lidar 激光雷达时数转换器的高分辨率标定方法

IF 1.6 4区计算机科学

Chinese Journal of Electronics Pub Date : 2025-01-01 DOI: 10.23919/cje.2023.00.237

Ruqing Liu;Feng Li;Jingguo Zhu;Yan Jiang;Chenghao Jiang;Tao Hu

引用次数: 0

Secure Fine-Grained Multi-Keyword Ciphertext Search Supporting Cloud-Edge-End Collaboration in IoT 支持物联网云端协作的安全细粒度多关键字密文搜索

IF 1.6 4区计算机科学

Chinese Journal of Electronics Pub Date : 2025-01-01 DOI: 10.23919/cje.2023.00.244

Kaifa Zheng;Ziyu Zhou;Jianwei Liu;Beiyuan Yu

{"title":"Secure Fine-Grained Multi-Keyword Ciphertext Search Supporting Cloud-Edge-End Collaboration in IoT","authors":"Kaifa Zheng;Ziyu Zhou;Jianwei Liu;Beiyuan Yu","doi":"10.23919/cje.2023.00.244","DOIUrl":"https://doi.org/10.23919/cje.2023.00.244","url":null,"abstract":"The massive terminals access the Internet of things (IoT) through edge nodes, bringing forth new security and privacy challenges in ciphertext search and data sharing. Meanwhile, existing ciphertext search schemes often overlook lightweight computing paradigms and pay little attention to the search requirements of multiple data owners (DOs)/data users (DUs). To address these issues, we propose a secure fine-grained multi-keyword ciphertext search scheme with cloud-edge-end collaboration computing (SFMS-CC). This SFMS-CC scheme focuses on the efficiency of end users and employs a cloud-edge-end collaborative computing paradigm, effectively offloading the incremental overhead from terminals and achieving low-cost constant overhead for the first time on the DO/DU side. Furthermore, based on public-key cryptography, a ciphertext search framework supporting multi-keyword is presented systematically. Each user is assigned an exclusive search Tok to enhance the user experience. Additionally, by integrating attribute-based encryption, a multi-DOs/multi-DUs model is constructed, seamlessly embedding entity private keys and public keys into encryption, search, decryption, and other steps, ensuring high privacy and security of this scheme. Security analysis demonstrates that the SFMS-CC scheme withstands choose plaintext attack, providing privacy-preserving for outsourced data and user information. Simulation results indicate that the SFMS-CC scheme is efficient and feasible in practice.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 1","pages":"266-281"},"PeriodicalIF":1.6,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10891973","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143438529","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Ultralow Ohmic Contact in Recess-Free Ultrathin Barrier AlGaN/GaN Heterostructures Across a Wide Temperature Range 宽温度范围内无凹槽超薄势垒AlGaN/GaN异质结构中的超低欧姆接触

IF 1.6 4区计算机科学

Chinese Journal of Electronics Pub Date : 2025-01-01 DOI: 10.23919/cje.2023.00.309

Yuhao Wang;Sen Huang;Qimeng Jiang;Xinhua Wang;Jie Fan;Haibo Yin;Ke Wei;Yingkui Zheng;Xinyu Liu

{"title":"Ultralow Ohmic Contact in Recess-Free Ultrathin Barrier AlGaN/GaN Heterostructures Across a Wide Temperature Range","authors":"Yuhao Wang;Sen Huang;Qimeng Jiang;Xinhua Wang;Jie Fan;Haibo Yin;Ke Wei;Yingkui Zheng;Xinyu Liu","doi":"10.23919/cje.2023.00.309","DOIUrl":"https://doi.org/10.23919/cje.2023.00.309","url":null,"abstract":"“Ohmic-before-passivation” process was implemented on ultrathin-barrier AlGaN (<6>$(R_{c})$</tex>. In this process, alloyed Ti/AI/Ni/Au ohmic metal was formed first, followed by <tex>$text{AlN}/text{SiN}_{x}$</tex> passivation contributed to restore two-dimensional electron gas (2DEG) in the access region. Due to the sharp change in the concentration of 2DEG at the metal edge, a reduced transfer length consisted with lower <tex>$R_{c}$</tex> are achieved compared to that of ohmic contact on AlGaN (~20 nm)/GaN heterostructure with pre-ohmic recess process. Temperature-dependent current voltage measurements demonstrate that the carrier transport mechanism is dominated by thermionic field emission above 200 K and by field emission below 200 K. The “ohmic-before-passivation” process enables the relative stability of ohmic contacts between 50 K and 475 K and significantly improves the direct current characteristics of GaN-metal-insulator-semiconductor-high electron mobility transistor, offering a promising means for scaling down and enabling the utilization of low-voltage GaN-based power devices in extreme environmental conditions.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 1","pages":"137-145"},"PeriodicalIF":1.6,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10891970","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143438531","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multimodal Cross-Attention Mechanism-Based Algorithm for Elderly Behavior Monitoring and Recognition 基于多模态交叉注意机制的老年人行为监测和识别算法

IF 1.6 4区计算机科学

Chinese Journal of Electronics Pub Date : 2025-01-01 DOI: 10.23919/cje.2023.00.263

Hao Liu;Zhiquan Feng;Qingbei Guo

{"title":"Multimodal Cross-Attention Mechanism-Based Algorithm for Elderly Behavior Monitoring and Recognition","authors":"Hao Liu;Zhiquan Feng;Qingbei Guo","doi":"10.23919/cje.2023.00.263","DOIUrl":"https://doi.org/10.23919/cje.2023.00.263","url":null,"abstract":"In contrast to the general population, behavior recognition among the elderly poses increased specificity and difficulty, rendering the reliability and usability aspects of safety monitoring systems for the elderly more challenging. Hence, this study proposes a multi-modal perception-based solution for an elderly safety monitoring recognition system. The proposed approach introduces a recognition algorithm based on multi-modal cross-attention mechanism, innovatively incorporating complex information such as scene context and voice to achieve more accurate behavior recognition. By fusing four modalities, namely image, skeleton, sensor data, and audio, we further enhance the accuracy of recognition. Additionally, we introduce a novel human-robot interaction mode, where the system associates directly recognized intentions with robotic actions without explicit commands, delivering a more natural and efficient elderly assistance paradigm. This mode not only elevates the level of safety monitoring for the elderly but also facilitates a more natural and efficient caregiving approach. Experimental results demonstrate significant improvement in recognition accuracy for 11 typical elderly behaviors compared to existing methods.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 1","pages":"309-321"},"PeriodicalIF":1.6,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10892001","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143446226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimization of Binary Randomized Response Based on Lanke Privacy and Utility Analysis 基于Lanke隐私和效用分析的二元随机响应优化

IF 1.6 4区计算机科学

Chinese Journal of Electronics Pub Date : 2025-01-01 DOI: 10.23919/cje.2023.00.272

Yihui Zhou;Wenli Wang;Jun Yan;Zhenqiang wu;Laifeng Lu

{"title":"Optimization of Binary Randomized Response Based on Lanke Privacy and Utility Analysis","authors":"Yihui Zhou;Wenli Wang;Jun Yan;Zhenqiang wu;Laifeng Lu","doi":"10.23919/cje.2023.00.272","DOIUrl":"https://doi.org/10.23919/cje.2023.00.272","url":null,"abstract":"Currently, it has become a consensus to enhance privacy protection. Randomized response (RR) technique, as the mainstream perturbation mechanism for local differential privacy, has been widely studied. However, most of the research in literature managed to modify existing RR schemes and propose new mechanisms with better privacy protection and utility, which are illustrated only by numerical experiments. We study the properties of generalized binary randomized response mechanisms from the perspectives of Lanke privacy and utility. The mathematical expressions of privacy and utility for the binary RR mechanism are given respectively. Moreover, the comparison principle for privacy and utility of any two mechanisms is proved. Finally, the optimization problem of the binary RR mechanism is discussed. Our work is based on a rigorous mathematical proof of privacy and utility for the general binary RR mechanism, and numerical verification illustrates the correctness of the conclusions. It can provide theoretical support for the design of binary RR mechanism and can be applied in data collection, analysis and publishing.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 1","pages":"242-256"},"PeriodicalIF":1.6,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10891974","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143438330","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Energy-Efficient D2D-Aided Dual UAV Data Collection 节能d2d辅助双无人机数据采集

IF 1.6 4区计算机科学

Chinese Journal of Electronics Pub Date : 2025-01-01 DOI: 10.23919/cje.2023.00.271

Qiulei Huang;Wei Wang;Zhaohui Song;Nan Zhao

引用次数: 0

Fault Diagnosis for Railway Point Machines Using VMD Multi-Scale Permutation Entropy and ReliefF Based on Vibration Signals 基于振动信号的VMD多尺度置换熵和缓解的铁路点机故障诊断

IF 1.6 4区计算机科学

Chinese Journal of Electronics Pub Date : 2025-01-01 DOI: 10.23919/cje.2023.00.258

Yongkui Sun;Yuan Cao;Peng Li;Shuai su

引用次数: 0

Fake Face Detection Based on Fusion of Spatial Texture and High-Frequency Noise 基于空间纹理和高频噪声融合的假人脸检测

IF 1.6 4区计算机科学

Chinese Journal of Electronics Pub Date : 2025-01-01 DOI: 10.23919/cje.2023.00.342

Dengyong Zhang;Feifan Qi;Jiahao Chen;Jiaxin Chen;Rongrong Gong;Yuehong Tian;Lebing Zhang

{"title":"Fake Face Detection Based on Fusion of Spatial Texture and High-Frequency Noise","authors":"Dengyong Zhang;Feifan Qi;Jiahao Chen;Jiaxin Chen;Rongrong Gong;Yuehong Tian;Lebing Zhang","doi":"10.23919/cje.2023.00.342","DOIUrl":"https://doi.org/10.23919/cje.2023.00.342","url":null,"abstract":"The rapid development of the Internet has led to the widespread dissemination of manipulated facial images, significantly impacting people's daily lives. With the continuous advancement of Deepfake technology, the generated counterfeit facial images have become increasingly challenging to distinguish. There is an urgent need for a more robust and convincing detection method. Current detection methods mainly operate in the spatial domain and transform the spatial domain into other domains for analysis. With the emergence of transformers, some researchers have also combined traditional convolutional networks with transformers for detection. This paper explores the artifacts left by Deepfakes in various domains and, based on this exploration, proposes a detection method that utilizes the steganalysis rich model to extract high-frequency noise to complement spatial features. We have designed two main modules to fully leverage the interaction between these two aspects based on traditional convolutional neural networks. The first is the multi-scale mixed feature attention module, which introduces artifacts from high-frequency noise into spatial textures, thereby enhancing the model's learning of spatial texture features. The second is the multiscale channel attention module, which reduces the impact of background noise by weighting the features. Our proposed method was experimentally evaluated on mainstream datasets, and a significant amount of experimental results demonstrate the effectiveness of our approach in detecting Deepfake forged faces, outperforming the majority of existing methods.","PeriodicalId":50701,"journal":{"name":"Chinese Journal of Electronics","volume":"34 1","pages":"212-221"},"PeriodicalIF":1.6,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10891978","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143438528","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0