With the remarkable advancements in machine vision research and its ever-expanding applications,scholars have increasingly focused on harnessing various vision methodologies within the industrial realm.Specifically,de...With the remarkable advancements in machine vision research and its ever-expanding applications,scholars have increasingly focused on harnessing various vision methodologies within the industrial realm.Specifically,detecting vehicle floor welding points poses unique challenges,including high operational costs and limited portability in practical settings.To address these challenges,this paper innovatively integrates template matching and the Faster RCNN algorithm,presenting an industrial fusion cascaded solder joint detection algorithm that seamlessly blends template matching with deep learning techniques.This algorithm meticulously weights and fuses the optimized features of both methodologies,enhancing the overall detection capabilities.Furthermore,it introduces an optimized multi-scale and multi-template matching approach,leveraging a diverse array of templates and image pyramid algorithms to bolster the accuracy and resilience of object detection.By integrating deep learning algorithms with this multi-scale and multi-template matching strategy,the cascaded target matching algorithm effectively accurately identifies solder joint types and positions.A comprehensive welding point dataset,labeled by experts specifically for vehicle detection,was constructed based on images from authentic industrial environments to validate the algorithm’s performance.Experiments demonstrate the algorithm’s compelling performance in industrial scenarios,outperforming the single-template matching algorithm by 21.3%,the multi-scale and multitemplate matching algorithm by 3.4%,the Faster RCNN algorithm by 19.7%,and the YOLOv9 algorithm by 17.3%in terms of solder joint detection accuracy.This optimized algorithm exhibits remarkable robustness and portability,ideally suited for detecting solder joints across diverse vehicle workpieces.Notably,this study’s dataset and feature fusion approach can be a valuable resource for other algorithms seeking to enhance their solder joint detection capabilities.This work thus not only presents a novel and effective solution for industrial solder joint detection but lays the groundwork for future advancements in this critical area.展开更多
A magnetic field sensor with a magnetic fluid(MF)-coated intermodal interferometer is proposed and experimentally demonstrated. The interferometer is formed by sandwiching a segment of single mode fiber(SMF) between a...A magnetic field sensor with a magnetic fluid(MF)-coated intermodal interferometer is proposed and experimentally demonstrated. The interferometer is formed by sandwiching a segment of single mode fiber(SMF) between a segment of multi-mode fiber(MMF) and a spherical structure. It can be considered as a cascade of the traditional SMF-MMF-SMF structure and MMF-SMF-sphere structure. The transmission spectral characteristics change with the variation of applied magnetic field. The experimental results exhibit that the magnetic field sensitivities for wavelength and transmission loss are 0.047 nm/m T and 0.215 d B/m T for the interference dip around 1 535.36 nm. For the interference dip around 1548.41 nm,the sensitivities are 0.077 nm/m T and 0.243 d B/m T. Simultaneous measurement can be realized according to the different spectral responses.展开更多
U-Net has been widely applied in semantic segmentation tasks,but it faces challenges in the semantic segmentation of high-resolution remote sensing images due to the loss of boundary information during the downsamplin...U-Net has been widely applied in semantic segmentation tasks,but it faces challenges in the semantic segmentation of high-resolution remote sensing images due to the loss of boundary information during the downsampling process and the inherent blurriness of object boundaries in remote sensing images.We propose an advanced U-Net variant model that addresses these issues.By introducing the CBAM attention mechanism,we enhance the extraction of boundary information during the downsampling process,and by incorporating a cascaded edge detection module,we significantly improve the model’s boundary segmentation performance.As a result,the model demonstrates excellent performance in the segmentation of high-resolution remote sensing images.The results indicate that our proposed model outperforms other baseline models and exhibits superior performance.展开更多
基金supported in part by the National Key Research Project of China under Grant No.2023YFA1009402General Science and Technology Plan Items in Zhejiang Province ZJKJT-2023-02.
文摘With the remarkable advancements in machine vision research and its ever-expanding applications,scholars have increasingly focused on harnessing various vision methodologies within the industrial realm.Specifically,detecting vehicle floor welding points poses unique challenges,including high operational costs and limited portability in practical settings.To address these challenges,this paper innovatively integrates template matching and the Faster RCNN algorithm,presenting an industrial fusion cascaded solder joint detection algorithm that seamlessly blends template matching with deep learning techniques.This algorithm meticulously weights and fuses the optimized features of both methodologies,enhancing the overall detection capabilities.Furthermore,it introduces an optimized multi-scale and multi-template matching approach,leveraging a diverse array of templates and image pyramid algorithms to bolster the accuracy and resilience of object detection.By integrating deep learning algorithms with this multi-scale and multi-template matching strategy,the cascaded target matching algorithm effectively accurately identifies solder joint types and positions.A comprehensive welding point dataset,labeled by experts specifically for vehicle detection,was constructed based on images from authentic industrial environments to validate the algorithm’s performance.Experiments demonstrate the algorithm’s compelling performance in industrial scenarios,outperforming the single-template matching algorithm by 21.3%,the multi-scale and multitemplate matching algorithm by 3.4%,the Faster RCNN algorithm by 19.7%,and the YOLOv9 algorithm by 17.3%in terms of solder joint detection accuracy.This optimized algorithm exhibits remarkable robustness and portability,ideally suited for detecting solder joints across diverse vehicle workpieces.Notably,this study’s dataset and feature fusion approach can be a valuable resource for other algorithms seeking to enhance their solder joint detection capabilities.This work thus not only presents a novel and effective solution for industrial solder joint detection but lays the groundwork for future advancements in this critical area.
基金supported by the National Natural Science Foundation of China(No.61475118)the National High-Tech Research and Development Program of China(863 Program)(No.2013AA014201)the Opened Fund of the State Key Laboratory on Integrated Optoelectronics(No.IOSKL2015KF06)
文摘A magnetic field sensor with a magnetic fluid(MF)-coated intermodal interferometer is proposed and experimentally demonstrated. The interferometer is formed by sandwiching a segment of single mode fiber(SMF) between a segment of multi-mode fiber(MMF) and a spherical structure. It can be considered as a cascade of the traditional SMF-MMF-SMF structure and MMF-SMF-sphere structure. The transmission spectral characteristics change with the variation of applied magnetic field. The experimental results exhibit that the magnetic field sensitivities for wavelength and transmission loss are 0.047 nm/m T and 0.215 d B/m T for the interference dip around 1 535.36 nm. For the interference dip around 1548.41 nm,the sensitivities are 0.077 nm/m T and 0.243 d B/m T. Simultaneous measurement can be realized according to the different spectral responses.
文摘U-Net has been widely applied in semantic segmentation tasks,but it faces challenges in the semantic segmentation of high-resolution remote sensing images due to the loss of boundary information during the downsampling process and the inherent blurriness of object boundaries in remote sensing images.We propose an advanced U-Net variant model that addresses these issues.By introducing the CBAM attention mechanism,we enhance the extraction of boundary information during the downsampling process,and by incorporating a cascaded edge detection module,we significantly improve the model’s boundary segmentation performance.As a result,the model demonstrates excellent performance in the segmentation of high-resolution remote sensing images.The results indicate that our proposed model outperforms other baseline models and exhibits superior performance.
