Conference on Intelligent and Human-Computer Interaction Technology最新文献

Performance analysis of 1/2 bit rate convolutional encoder 1/2比特率卷积编码器的性能分析

Conference on Intelligent and Human-Computer Interaction Technology Pub Date : 2022-10-07 DOI: 10.1117/12.2655515

Xinyu Dong, Yuyang Feng, Rui Sun

引用次数: 0

Lane line detection based on improved U-Net network 基于改进U-Net网络的车道线检测

Conference on Intelligent and Human-Computer Interaction Technology Pub Date : 2022-10-07 DOI: 10.1117/12.2655296

Yanqiang Li, Shulin Zhang, Jing Ma, Yong Wang

{"title":"Lane line detection based on improved U-Net network","authors":"Yanqiang Li, Shulin Zhang, Jing Ma, Yong Wang","doi":"10.1117/12.2655296","DOIUrl":"https://doi.org/10.1117/12.2655296","url":null,"abstract":"The lane line detection and recognition are crucial research area for automatic driving. It aims at solving the problem of fuzzy feature expression and low time-sensitives of lane line detection based on semantic segmentation. This paper proposes to remove irrelevant background by dynamic programming region of interest while improving the lightweight neural network (U-Net). A group-by-group convolution and depth wise separable convolution in the backbone network are introduced, simplifies the branches of the backbone network, and atrous convolution is introduced into the enhanced path network with multi-level skip connection structure to retain the underlying coarse-grained semantic feature information. The full-scale skip connection fusion mechanism of the decoder is preserved, while capturing the fine-grained semantics and coarse-grained semantics of the feature map at full scale. The introduction of skip connections between the decoder and the encoder can enhance the lanes without increasing the size of the receptive field. The ability to extract line features and the ability to extract context improves the accuracy of lane lines. The experimental results show that the improved neural network can obtain good detection performance in complex lane lines, and effectively improve the accuracy and time-sensitives of lane lines.","PeriodicalId":312603,"journal":{"name":"Conference on Intelligent and Human-Computer Interaction Technology","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127610041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Research on the design of multifunctional nursing beds based on perceptual imagery 基于感知意象的多功能护理床设计研究

Conference on Intelligent and Human-Computer Interaction Technology Pub Date : 2022-10-07 DOI: 10.1117/12.2655300

Jun-Fang Zeng

引用次数: 0

Research on photoelectric detection gain control system based on FPGA 基于FPGA的光电检测增益控制系统研究

Conference on Intelligent and Human-Computer Interaction Technology Pub Date : 2022-10-07 DOI: 10.1117/12.2655341

Zuofeng Zhou, Hongjun Yang, Hao Liu

{"title":"Research on photoelectric detection gain control system based on FPGA","authors":"Zuofeng Zhou, Hongjun Yang, Hao Liu","doi":"10.1117/12.2655341","DOIUrl":"https://doi.org/10.1117/12.2655341","url":null,"abstract":"The light sensor chip generates different signals through different lighting, and is widely used in light sensors, digital cameras, etc. Therefore, it is very important to test the developed photosensitive chip. In the process of photoelectric detection, light signals of different intensities are faced, and the intensities of these light signals may vary greatly in magnitude over time. In this case, it requires our photoelectric detection system to have the characteristics of high sensitivity and fast response speed; the photoelectric detection system should also have high-precision gain changing ability, so that the optical signal acquisition can be better presented. Aiming at the above problems of photoelectric detection, this paper deeply studies the method of gain adjustment of photoelectric detection system, and designs and realizes the gain control system of photoelectric detection system based on FPGA. The experimental results show that the photoelectric detection gain control system can stably and accurately adjust the gain of the multi-channel photoelectric detection system, and can help the photoelectric detection system to detect plasma signals with different amplitudes and large magnitude gaps.","PeriodicalId":312603,"journal":{"name":"Conference on Intelligent and Human-Computer Interaction Technology","volume":"12344 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129999808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Trajectory planning of sorting robot based on improved particle swarm optimization algorithm 基于改进粒子群优化算法的分拣机器人轨迹规划

Conference on Intelligent and Human-Computer Interaction Technology Pub Date : 2022-10-07 DOI: 10.1117/12.2655210

Qiuying Li, Yan Li

引用次数: 1

Studying permanent magnet synchronous motor sensorless control technology 研究永磁同步电机无传感器控制技术

Conference on Intelligent and Human-Computer Interaction Technology Pub Date : 2022-10-07 DOI: 10.1117/12.2655283

Kexin Zhang, Xushuai Han, Yunlei Zhu, Wen Wang

引用次数: 0

Design and power-assistance analysis of a bending-over exoskeleton robot 弯曲外骨骼机器人的设计与动力辅助分析

Conference on Intelligent and Human-Computer Interaction Technology Pub Date : 2022-10-07 DOI: 10.1117/12.2655660

Yeyan Ning, Jun Cai, Yunji Li, Zhenyu Zhang, Chunlei Wang

{"title":"Design and power-assistance analysis of a bending-over exoskeleton robot","authors":"Yeyan Ning, Jun Cai, Yunji Li, Zhenyu Zhang, Chunlei Wang","doi":"10.1117/12.2655660","DOIUrl":"https://doi.org/10.1117/12.2655660","url":null,"abstract":"The stooping and handling exoskeleton robot integrating multi-field technologies such as mechatronics, human-computer interaction, gait analysis and intelligence is an important development direction in the field of robot research and development in recent years. The boosting efficiency is the most critical evaluation index in the overall performance of the exoskeleton robot. In this paper, by analyzing the changes of the human lumbar spine force in the state of normal bending and carrying under the state of natural motion cycle, the state of wearing the exoskeleton without assistance, and the state of wearing exoskeleton assistance, this paper establishes a bending and carrying model, completes the force analysis, and deduces the power-assisting efficiency. Compare the calculation formula, and design a wearable stooping exoskeleton robot based on this, and conduct EMG experiment data in three states to collect the changes of the user's biomechanical signals. The percentage of EMG signal amplitude of the erector spinae muscles of the waist in the state decreased by 39.3%, verifying its beneficial effect on users.","PeriodicalId":312603,"journal":{"name":"Conference on Intelligent and Human-Computer Interaction Technology","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127413841","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The construction of intervention mode for people with depression based on human-computer interaction 基于人机交互的抑郁症患者干预模式构建

Conference on Intelligent and Human-Computer Interaction Technology Pub Date : 2022-10-07 DOI: 10.1117/12.2655362

Yiyang Chen

{"title":"The construction of intervention mode for people with depression based on human-computer interaction","authors":"Yiyang Chen","doi":"10.1117/12.2655362","DOIUrl":"https://doi.org/10.1117/12.2655362","url":null,"abstract":"For most of people, the burden caused by COVID-19 is not only physical, but also spiritual. Several research studies have shown that the negative emotions caused by COVID-19 have increased significantly worldwide, but there are not effective emotional interventions for people in most countries. Therefore, this negative emotional trend is likely to expand further and cause more adverse effects, such as pathological depression. By applying python to crawl the posts of depressed patients on Chinese social media platforms, and using natural language processing to quantitatively analyze the words with high frequency, this paper summarizes the text characteristics and depression degrees of depressives' posts on Chinese social media platforms, so as to present a preliminary psychological intervention mode. Then, the paper proposes a more targeted psychological intervention mode for depressives with different characteristics based on the paradigm of human-computer interaction and the results of the questionnaire. The study finds that the patients with sufficient self-regulation abilities and the patients without self-regulation abilities do not meet the high-frequency word extraction results, while patients with insufficient self-regulation abilities do. Additionally, for these three types of patients, different psychological intervention modes can be established based on different interaction paradigms.","PeriodicalId":312603,"journal":{"name":"Conference on Intelligent and Human-Computer Interaction Technology","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125499603","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Hybrid control of force feedback and position feedback for bilateral teleoperation of underwater manipulator 水下机械臂双向遥操作力反馈与位置反馈混合控制

Conference on Intelligent and Human-Computer Interaction Technology Pub Date : 2022-10-07 DOI: 10.1117/12.2655284

Ni Liu, Yonglin Zhang, Mengyu Wu

{"title":"Hybrid control of force feedback and position feedback for bilateral teleoperation of underwater manipulator","authors":"Ni Liu, Yonglin Zhang, Mengyu Wu","doi":"10.1117/12.2655284","DOIUrl":"https://doi.org/10.1117/12.2655284","url":null,"abstract":"Aiming at the problems of external disturbance such as underwater ocean current and joint friction of master-slave manipulator in underwater teleoperation system, the bilateral control algorithm of master-slave manipulator was optimized under the hybrid control structure of force feedback and position feedback. In order to track the interaction force between the master manipulator and the slave manipulator, the grey predictive fuzzy control with error compensation is used to adjust the force feedback error, and it is mixed with the traditional PID control to achieve better control effect. In order to track the position of the master for the slave manipulator, a fuzzy adaptive system that based on the traditional sliding mode control, is used to adjust the switching gain. Estimate the upper bound of the external interference, and a robust term is designed to suppress the error estimation. The stability and convergence of the optimized system are proved by Lyapunov stability theory. Comparative simulation experiments on MATLAB/Simulink platform were carried out to verify the effectiveness of the optimization algorithm.","PeriodicalId":312603,"journal":{"name":"Conference on Intelligent and Human-Computer Interaction Technology","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121096395","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Semantic aggregation for accurate and efficient object detection 语义聚合用于准确高效的目标检测

Conference on Intelligent and Human-Computer Interaction Technology Pub Date : 2022-10-07 DOI: 10.1117/12.2655778

Zhipeng Duan, Jing Wang, Shu Zhan, Zhenping Ruan, Fei Li, Zhen Yang

{"title":"Semantic aggregation for accurate and efficient object detection","authors":"Zhipeng Duan, Jing Wang, Shu Zhan, Zhenping Ruan, Fei Li, Zhen Yang","doi":"10.1117/12.2655778","DOIUrl":"https://doi.org/10.1117/12.2655778","url":null,"abstract":"Single Shot Multibox Detector (SSD) uses multi-scale feature maps to detect and recognize objects, which greatly improves the performance of single-stage approaches, but it is still not conducive to detecting small objects. Researchers focus on enhancing features on the feature pyramid. However, many networks simply merge several feature maps, ignoring fully aggregating the semantics among different scale features. On this basis, this paper proposes an efficient semantic aggregation module and a lightweight feature combination module, which can significantly improve the detection accuracy based on SSD. In the semantic aggregation module, the feature maps of different sizes are adjusted and integrated through different channels to obtain the enhanced features with rich semantic information, which can improve the discrimination and expression ability of the features. In the feature combination module, the detector can fully utilize the multi-scale convolution layers in the feature pyramid to produce more descriptive and representative enhanced features with rich semantics. Our proposed network with 512×512 input size can respectively achieve 82.6% mAP and 81.3% mAP (mean Average Precision) in VOC2007 test and VOC2012 test datasets. Some experiments and ablation studies show that this method is superior to many advanced detectors in accuracy and speed.","PeriodicalId":312603,"journal":{"name":"Conference on Intelligent and Human-Computer Interaction Technology","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114267375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0