针对越来越多的年轻人使用电脑进行办公的时间越来越长,坐姿不正确导致的颈肩腰部疾病发病率及视力下降的问题,设计了一种不需要额外佩戴智能硬件的坐姿检测技术。该方案使用Intel最新的Real Sense 3D摄像头进行画面采集,通过对三维数...针对越来越多的年轻人使用电脑进行办公的时间越来越长,坐姿不正确导致的颈肩腰部疾病发病率及视力下降的问题,设计了一种不需要额外佩戴智能硬件的坐姿检测技术。该方案使用Intel最新的Real Sense 3D摄像头进行画面采集,通过对三维数据的实时分析,准确的判断出用户的坐姿情况,相对于智能硬件的解决方案可以大幅度提高准确度,市场上新出的笔记本电脑中带有Real Sense的型号也较多,具有较好的应用前景。展开更多
该设计是基于Intel Real Sense的物品展示系统的研究与实现,这里的展示系统主要是展示汽车模型的外观,内部结构,汽车和汽车展厅形成一个三维空间并且汽车和汽车展厅都是动态的,通过手部的动作来实现基本的控制,包括打开车门观看车内的结...该设计是基于Intel Real Sense的物品展示系统的研究与实现,这里的展示系统主要是展示汽车模型的外观,内部结构,汽车和汽车展厅形成一个三维空间并且汽车和汽车展厅都是动态的,通过手部的动作来实现基本的控制,包括打开车门观看车内的结构,让你有一种身临其境的感觉,感觉真实地站在展厅里面欣赏汽车。展开更多
Accurate and rapid wheat morphology reconstruction and trait collection are essential for selecting varieties,scientific cultivation,and precise management.A single perspective is limited by environmental obstructions...Accurate and rapid wheat morphology reconstruction and trait collection are essential for selecting varieties,scientific cultivation,and precise management.A single perspective is limited by environmental obstructions,hindering the collection of high-throughput phenotype data for wheat plants.Therefore,a rapid reconstruction method of multi-view threedimensional point cloud is proposed to realize the high-throughput and accurate identification of wheat phenotype.Firstly,taking wheat at the tillering stage as the experimental object,a multi-view acquisition system based on a RealSense sensor was constructed,and the point cloud data of wheat were obtained from 16 views.Secondly,a joint photometric and geometric objective was optimized,and space location was registered by colored Point Cloud Registration(colored)and Iterative Closest Point(ICP)algorithms.Furthermore,the Multiple View Stereo(MVS)algorithm was used to combine the depth image,RGB image,and spatial position obtained by coarse registration to enable the fine registration of multi-viewpoint clouds.Compared with the traditional Structure From Motion(SFM)-MVS algorithm,our proposed method is much faster,with an average reconstruction time of 33.82 s.Moreover,the wheat plant height,leaf length,leaf width,leaf area,and leaf angle of wheat were calculated based on the three-dimensional point cloud of the wheat plant.The experimental results showed that the determination coefficients of the method are 0.996,0.958,0.956,0.984,and 0.849,respectively.Finally,phenotypic information such as compact degree,convex hull volume,and average leaf area of different wheat varieties was analyzed and identified,proving that the method could capture the phenotypic differences between varieties and individuals.The proposed method provides a rapid approach to quantify wheat phenotypic traits,aiding breeding,scientific cultivation,and environmental management.展开更多
Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone t...Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone to errors and lacks consistency,emphasizing the need for a reliable and automated inspection system.Leveraging both object detection and image segmentation approaches,this research proposes a vision-based solution for the detection of various kinds of tools in the toolkit using deep learning(DL)models.Two Intel RealSense D455f depth cameras were arranged in a top down configuration to capture both RGB and depth images of the toolkits.After applying multiple constraints and enhancing them through preprocessing and augmentation,a dataset consisting of 3300 annotated RGB-D photos was generated.Several DL models were selected through a comprehensive assessment of mean Average Precision(mAP),precision-recall equilibrium,inference latency(target≥30 FPS),and computational burden,resulting in a preference for YOLO and Region-based Convolutional Neural Networks(R-CNN)variants over ViT-based models due to the latter’s increased latency and resource requirements.YOLOV5,YOLOV8,YOLOV11,Faster R-CNN,and Mask R-CNN were trained on the annotated dataset and evaluated using key performance metrics(Recall,Accuracy,F1-score,and Precision).YOLOV11 demonstrated balanced excellence with 93.0%precision,89.9%recall,and a 90.6%F1-score in object detection,as well as 96.9%precision,95.3%recall,and a 96.5%F1-score in instance segmentation with an average inference time of 25 ms per frame(≈40 FPS),demonstrating real-time performance.Leveraging these results,a YOLOV11-based windows application was successfully deployed in a real-time assembly line environment,where it accurately processed live video streams to detect and segment tools within toolkits,demonstrating its practical effectiveness in industrial automation.The application is capable of precisely measuring socket dimensions by utilising edge detection techniques on YOLOv11 segmentation masks,in addition to detection and segmentation.This makes it possible to do specification-level quality control right on the assembly line,which improves the ability to examine things in real time.The implementation is a big step forward for intelligent manufacturing in the Industry 4.0 paradigm.It provides a scalable,efficient,and accurate way to do automated inspection and dimensional verification activities.展开更多
Non-destructive plant growth parameters measurement is an important concern in automatic-seedling transplanting.Recently,several image-basedmonitoring approaches have been proposed and potentially developed for severa...Non-destructive plant growth parameters measurement is an important concern in automatic-seedling transplanting.Recently,several image-basedmonitoring approaches have been proposed and potentially developed for several agricultural applications.The presented study proposed and developed a RealSense-based machine vision system for the close-shot seedling-lump integrated monitoring.The strategy was based on the close-shot depth information.Further,the point cloud clustering and suitable algorithms were applied to obtain the segmentation of 3D seedling models.In addition,the data processing pipeline was developed to assess the differentmorphological parameter of 4 different seedling varieties.The experiments were carried out with 4 different seedling varieties(pepper,tomato,cucumber,and lettuce)and trained under different light conditions(light and dark).Moreover,analysis results showed that therewas not significantly different(p<0.05)found towards light and dark environments due to close-shot near-infrared detection.However,the results revealed that the stem diameter relationship between RealSense and the manual method was found for R^2=0.68 cucumber,R^2=0.54 tomato,R^2=0.35 pepper,and R^2=0.58 lettuce seedlings.Whereas,the seedling height relationship between RealSense and the manual methodwas found higher than R^2=0.99,0.99,0.99,and 0.99 for pepper,tomato,cucumber,and lettuce,respectively.Based on the experiment results,it was concluded that the RGB-D integrated monitoring system with the purposed method could be practiced for nursery seedlings most promisingly without high labour requirements in terms of ease of use.The system revealed a good sturdiness and relevance for plant growth monitoring.Additionally,it has the perspective for future practical value to real-time vision servo operations for transplanting robots.展开更多
文摘针对越来越多的年轻人使用电脑进行办公的时间越来越长,坐姿不正确导致的颈肩腰部疾病发病率及视力下降的问题,设计了一种不需要额外佩戴智能硬件的坐姿检测技术。该方案使用Intel最新的Real Sense 3D摄像头进行画面采集,通过对三维数据的实时分析,准确的判断出用户的坐姿情况,相对于智能硬件的解决方案可以大幅度提高准确度,市场上新出的笔记本电脑中带有Real Sense的型号也较多,具有较好的应用前景。
文摘该设计是基于Intel Real Sense的物品展示系统的研究与实现,这里的展示系统主要是展示汽车模型的外观,内部结构,汽车和汽车展厅形成一个三维空间并且汽车和汽车展厅都是动态的,通过手部的动作来实现基本的控制,包括打开车门观看车内的结构,让你有一种身临其境的感觉,感觉真实地站在展厅里面欣赏汽车。
基金financially supported by Shandong Provincial Key Research and Development Program(Grant No.2022LZGCQY002,2021LZGC013,2023TZXD004).
文摘Accurate and rapid wheat morphology reconstruction and trait collection are essential for selecting varieties,scientific cultivation,and precise management.A single perspective is limited by environmental obstructions,hindering the collection of high-throughput phenotype data for wheat plants.Therefore,a rapid reconstruction method of multi-view threedimensional point cloud is proposed to realize the high-throughput and accurate identification of wheat phenotype.Firstly,taking wheat at the tillering stage as the experimental object,a multi-view acquisition system based on a RealSense sensor was constructed,and the point cloud data of wheat were obtained from 16 views.Secondly,a joint photometric and geometric objective was optimized,and space location was registered by colored Point Cloud Registration(colored)and Iterative Closest Point(ICP)algorithms.Furthermore,the Multiple View Stereo(MVS)algorithm was used to combine the depth image,RGB image,and spatial position obtained by coarse registration to enable the fine registration of multi-viewpoint clouds.Compared with the traditional Structure From Motion(SFM)-MVS algorithm,our proposed method is much faster,with an average reconstruction time of 33.82 s.Moreover,the wheat plant height,leaf length,leaf width,leaf area,and leaf angle of wheat were calculated based on the three-dimensional point cloud of the wheat plant.The experimental results showed that the determination coefficients of the method are 0.996,0.958,0.956,0.984,and 0.849,respectively.Finally,phenotypic information such as compact degree,convex hull volume,and average leaf area of different wheat varieties was analyzed and identified,proving that the method could capture the phenotypic differences between varieties and individuals.The proposed method provides a rapid approach to quantify wheat phenotypic traits,aiding breeding,scientific cultivation,and environmental management.
基金National Science and Technology Council,the Republic of China,under grants NSTC 113-2221-E-194-011-MY3 and Research Center on Artificial Intelligence and Sustainability,National Chung Cheng University under the research project grant titled“Generative Digital Twin System Design for Sustainable Smart City Development in Taiwan.
文摘Modern manufacturing processes have become more reliant on automation because of the accelerated transition from Industry 3.0 to Industry 4.0.Manual inspection of products on assembly lines remains inefficient,prone to errors and lacks consistency,emphasizing the need for a reliable and automated inspection system.Leveraging both object detection and image segmentation approaches,this research proposes a vision-based solution for the detection of various kinds of tools in the toolkit using deep learning(DL)models.Two Intel RealSense D455f depth cameras were arranged in a top down configuration to capture both RGB and depth images of the toolkits.After applying multiple constraints and enhancing them through preprocessing and augmentation,a dataset consisting of 3300 annotated RGB-D photos was generated.Several DL models were selected through a comprehensive assessment of mean Average Precision(mAP),precision-recall equilibrium,inference latency(target≥30 FPS),and computational burden,resulting in a preference for YOLO and Region-based Convolutional Neural Networks(R-CNN)variants over ViT-based models due to the latter’s increased latency and resource requirements.YOLOV5,YOLOV8,YOLOV11,Faster R-CNN,and Mask R-CNN were trained on the annotated dataset and evaluated using key performance metrics(Recall,Accuracy,F1-score,and Precision).YOLOV11 demonstrated balanced excellence with 93.0%precision,89.9%recall,and a 90.6%F1-score in object detection,as well as 96.9%precision,95.3%recall,and a 96.5%F1-score in instance segmentation with an average inference time of 25 ms per frame(≈40 FPS),demonstrating real-time performance.Leveraging these results,a YOLOV11-based windows application was successfully deployed in a real-time assembly line environment,where it accurately processed live video streams to detect and segment tools within toolkits,demonstrating its practical effectiveness in industrial automation.The application is capable of precisely measuring socket dimensions by utilising edge detection techniques on YOLOv11 segmentation masks,in addition to detection and segmentation.This makes it possible to do specification-level quality control right on the assembly line,which improves the ability to examine things in real time.The implementation is a big step forward for intelligent manufacturing in the Industry 4.0 paradigm.It provides a scalable,efficient,and accurate way to do automated inspection and dimensional verification activities.
基金Theworkwas supported by grants fromthe Jiangsu Agricultural Science and Technology Innovation Fund(CX(16)1044)the Natural Science Foundation of Colleges in Jiangsu Province(16KJA210002)+1 种基金the Project of Six Talent Peaks in Jiangsu Province(JXQC-008)a Project Funded by the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD-2018-87).
文摘Non-destructive plant growth parameters measurement is an important concern in automatic-seedling transplanting.Recently,several image-basedmonitoring approaches have been proposed and potentially developed for several agricultural applications.The presented study proposed and developed a RealSense-based machine vision system for the close-shot seedling-lump integrated monitoring.The strategy was based on the close-shot depth information.Further,the point cloud clustering and suitable algorithms were applied to obtain the segmentation of 3D seedling models.In addition,the data processing pipeline was developed to assess the differentmorphological parameter of 4 different seedling varieties.The experiments were carried out with 4 different seedling varieties(pepper,tomato,cucumber,and lettuce)and trained under different light conditions(light and dark).Moreover,analysis results showed that therewas not significantly different(p<0.05)found towards light and dark environments due to close-shot near-infrared detection.However,the results revealed that the stem diameter relationship between RealSense and the manual method was found for R^2=0.68 cucumber,R^2=0.54 tomato,R^2=0.35 pepper,and R^2=0.58 lettuce seedlings.Whereas,the seedling height relationship between RealSense and the manual methodwas found higher than R^2=0.99,0.99,0.99,and 0.99 for pepper,tomato,cucumber,and lettuce,respectively.Based on the experiment results,it was concluded that the RGB-D integrated monitoring system with the purposed method could be practiced for nursery seedlings most promisingly without high labour requirements in terms of ease of use.The system revealed a good sturdiness and relevance for plant growth monitoring.Additionally,it has the perspective for future practical value to real-time vision servo operations for transplanting robots.
