首页 > 最新文献

2022 7th International Conference on Multimedia and Image Processing最新文献

英文 中文
Structure design of the shutter with slider-crank mechanism 曲柄滑块机构快门的结构设计
Pub Date : 2022-01-14 DOI: 10.1145/3517077.3517119
F. Jiaqi
In order to realize the miniaturization and lightweight of the infrared nonuniform correction shutter, the crank slider mechanism is used to design. Firstly, the shutter blade is used as the slider and the driving mechanism is used as the crank, and the motion analysis is carried out. The transmission angle of the crank slider mechanism is calculated to be no less than 66.42 °. Then, the slider, connecting rod and crank are analyzed respectively, the force system and motion equation are established, and the driving torque of the shutter is calculated. The design results show that the volume, weight and driving torque of the same target product are reduced by 1 / 3, 1 / 2 and 1 / 2, respectively, compared with the direct motion rotary shutter commonly used in nonuniform correction of infrared camera. The design goal is achieved.
为了实现红外不均匀校正快门的小型化和轻量化,采用曲柄滑块机构进行设计。首先,以快门叶片为滑块,驱动机构为曲柄,进行运动分析;曲柄滑块机构的传动角计算不小于66.42°。然后,分别对滑块、连杆和曲柄进行了分析,建立了快门的受力系统和运动方程,计算了快门的驱动力矩。设计结果表明,与红外相机非均匀校正中常用的直动旋转式快门相比,同一目标产品的体积、重量和驱动力矩分别减小了1 / 3、1 / 2和1 / 2。实现了设计目标。
{"title":"Structure design of the shutter with slider-crank mechanism","authors":"F. Jiaqi","doi":"10.1145/3517077.3517119","DOIUrl":"https://doi.org/10.1145/3517077.3517119","url":null,"abstract":"In order to realize the miniaturization and lightweight of the infrared nonuniform correction shutter, the crank slider mechanism is used to design. Firstly, the shutter blade is used as the slider and the driving mechanism is used as the crank, and the motion analysis is carried out. The transmission angle of the crank slider mechanism is calculated to be no less than 66.42 °. Then, the slider, connecting rod and crank are analyzed respectively, the force system and motion equation are established, and the driving torque of the shutter is calculated. The design results show that the volume, weight and driving torque of the same target product are reduced by 1 / 3, 1 / 2 and 1 / 2, respectively, compared with the direct motion rotary shutter commonly used in nonuniform correction of infrared camera. The design goal is achieved.","PeriodicalId":233686,"journal":{"name":"2022 7th International Conference on Multimedia and Image Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115343708","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
An Efficient Mixed Bit-width Searching Strategy for CNN Quantization based on BN Scale Factors 基于BN尺度因子的CNN量化混合位宽搜索策略
Pub Date : 2022-01-14 DOI: 10.1145/3517077.3517108
Xuecong Han, Xulin Zhou, Zhongjian Ma
In recent years, the rapid development of mixed-precision quantification technology has greatly reduced the scale of the model and the amount of calculation. However, the previous mixed bit-width strategies are too complicated, such as reinforcement learning strategies and Hessian matrix strategies. This paper proposes an efficient mixed bit-width searching strategy, which measures the sensitivity of the convolutional layer by the scale factors of the BN layer. The advantage of this strategy is that the parameters of the pre-trained model are used and no extra computation is introduced, which greatly simplifies the complexity of the bit-width selection strategy. In this paper, Resnet18 and Resnet50 models are used to conduct comparative experiments, and the differences between the proposed strategy and several previous algorithms are compared in terms of accuracy, model size and computation amount. It is verified that the accuracy of quantization in this paper is reduced within 2% compared with FP32 baseline, and the accuracy is reduced with about 0.5% compared with HAWQ. Overall, the performance is similar to that of HAWQ. This paper also compares the calculation complexity of the quantized bit-width of HAWQ-V3 with the calculation complexity of the quantized bit-width of this paper, which proves that the computational complexity of the strategy in this paper is far less than that of HAWQ-V3.
近年来,混合精度量化技术的快速发展,大大降低了模型的规模和计算量。然而,以往的混合位宽策略过于复杂,如强化学习策略和Hessian矩阵策略。本文提出了一种高效的混合位宽搜索策略,该策略通过BN层的尺度因子来衡量卷积层的灵敏度。该策略的优点是使用预训练模型的参数,不引入额外的计算量,大大简化了位宽选择策略的复杂度。本文使用Resnet18和Resnet50模型进行对比实验,比较本文提出的策略与之前几种算法在准确率、模型大小、计算量等方面的差异。验证了本文量化的精度与FP32基线相比降低了2%以内,与HAWQ相比降低了0.5%左右。总体而言,性能与HAWQ相似。本文还将HAWQ-V3量化位宽的计算复杂度与本文量化位宽的计算复杂度进行了比较,证明本文策略的计算复杂度远远小于HAWQ-V3。
{"title":"An Efficient Mixed Bit-width Searching Strategy for CNN Quantization based on BN Scale Factors","authors":"Xuecong Han, Xulin Zhou, Zhongjian Ma","doi":"10.1145/3517077.3517108","DOIUrl":"https://doi.org/10.1145/3517077.3517108","url":null,"abstract":"In recent years, the rapid development of mixed-precision quantification technology has greatly reduced the scale of the model and the amount of calculation. However, the previous mixed bit-width strategies are too complicated, such as reinforcement learning strategies and Hessian matrix strategies. This paper proposes an efficient mixed bit-width searching strategy, which measures the sensitivity of the convolutional layer by the scale factors of the BN layer. The advantage of this strategy is that the parameters of the pre-trained model are used and no extra computation is introduced, which greatly simplifies the complexity of the bit-width selection strategy. In this paper, Resnet18 and Resnet50 models are used to conduct comparative experiments, and the differences between the proposed strategy and several previous algorithms are compared in terms of accuracy, model size and computation amount. It is verified that the accuracy of quantization in this paper is reduced within 2% compared with FP32 baseline, and the accuracy is reduced with about 0.5% compared with HAWQ. Overall, the performance is similar to that of HAWQ. This paper also compares the calculation complexity of the quantized bit-width of HAWQ-V3 with the calculation complexity of the quantized bit-width of this paper, which proves that the computational complexity of the strategy in this paper is far less than that of HAWQ-V3.","PeriodicalId":233686,"journal":{"name":"2022 7th International Conference on Multimedia and Image Processing","volume":"181 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115991627","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
Successive statistical iterative reconstruction, 3D-filtering and region growing methods for high-quality 3D visualization of cone-beam CT image 连续统计迭代重建、三维滤波和区域生长方法实现高质量的锥束CT图像三维可视化
Pub Date : 2022-01-14 DOI: 10.1145/3517077.3517081
Jian Dong, Siyuan Zhang, Xiaoxia Yang, Jingyu Zhang
Our study is to improve the accuracy of bone morphology depicted in dental cone-beam computed tomography (CBCT) images. First, successive statistical iterative reconstruction was used to reduce unavoidable streak artefacts. Then 3-dimentional filtering (Gaussian-Laplacian filter) and region growing methods were examined to present clear bone morphology. CBCT examinations were performed with the following principal exposure parameters: I-mode, FOV 10cm in diameter, 120 kV, 15 mA, 0.2 mm slice thickness, and exposure time of 10s. Ordered subset-expectation maximization (OS-EM) algorithm was applied for unavoidable streak artefact reduction. 3D Laplacian sharpening to images preprocessed by Gaussian smoothing was sequentially tested. Region growing method with dilation and erosion was used to segment maxillofacial tissue. Streak artefact induced by metallic prosthetic appliances was reduced by applying successive iterative OS-EM algorithm. Multi-planar reconstruction (MPR) images at left side molar plane and mid-sagittal plane were presented to validate effect of OS-EM algorithm and 3D Gaussian-Laplacian filter. Maxillofacial tissue was segmented and presented to show the effect of region growing method. Streak artefact reducing method, 3D filtering method for image smoothing and sharpening, and region growing method with dilation and erosion were effective to improve accuracy of bone morphology in dental CBCT images.
我们的研究是为了提高牙锥束计算机断层扫描(CBCT)图像中描述的骨形态的准确性。首先,采用逐次统计迭代重建,减少不可避免的条纹伪影;三维滤波(高斯-拉普拉斯滤波)和区域生长方法得到清晰的骨形态。CBCT检查的主要曝光参数为:i模式,视场直径10cm, 120 kV, 15 mA,切片厚度0.2 mm,曝光时间10s。采用有序子集期望最大化(OS-EM)算法对不可避免条纹伪影进行还原。对高斯平滑预处理后的图像进行了三维拉普拉斯锐化实验。采用扩张糜烂区域生长法分割颌面部组织。采用连续迭代OS-EM算法对金属假体矫治器产生的条纹伪影进行了抑制。为了验证OS-EM算法和三维高斯-拉普拉斯滤波的效果,给出了左侧磨牙面和中矢状面多平面重建(MPR)图像。对颌面部组织进行分割,展示区域生长法的效果。条纹伪影减少方法、图像平滑锐化的三维滤波方法和带扩张和侵蚀的区域生长方法可以有效提高牙齿CBCT图像中骨形态的准确性。
{"title":"Successive statistical iterative reconstruction, 3D-filtering and region growing methods for high-quality 3D visualization of cone-beam CT image","authors":"Jian Dong, Siyuan Zhang, Xiaoxia Yang, Jingyu Zhang","doi":"10.1145/3517077.3517081","DOIUrl":"https://doi.org/10.1145/3517077.3517081","url":null,"abstract":"Our study is to improve the accuracy of bone morphology depicted in dental cone-beam computed tomography (CBCT) images. First, successive statistical iterative reconstruction was used to reduce unavoidable streak artefacts. Then 3-dimentional filtering (Gaussian-Laplacian filter) and region growing methods were examined to present clear bone morphology. CBCT examinations were performed with the following principal exposure parameters: I-mode, FOV 10cm in diameter, 120 kV, 15 mA, 0.2 mm slice thickness, and exposure time of 10s. Ordered subset-expectation maximization (OS-EM) algorithm was applied for unavoidable streak artefact reduction. 3D Laplacian sharpening to images preprocessed by Gaussian smoothing was sequentially tested. Region growing method with dilation and erosion was used to segment maxillofacial tissue. Streak artefact induced by metallic prosthetic appliances was reduced by applying successive iterative OS-EM algorithm. Multi-planar reconstruction (MPR) images at left side molar plane and mid-sagittal plane were presented to validate effect of OS-EM algorithm and 3D Gaussian-Laplacian filter. Maxillofacial tissue was segmented and presented to show the effect of region growing method. Streak artefact reducing method, 3D filtering method for image smoothing and sharpening, and region growing method with dilation and erosion were effective to improve accuracy of bone morphology in dental CBCT images.","PeriodicalId":233686,"journal":{"name":"2022 7th International Conference on Multimedia and Image Processing","volume":"494 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117023357","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
Multi-scale Deep Curve Estimation for Low-light Image Enhancement 低光图像增强的多尺度深度曲线估计
Pub Date : 2022-01-14 DOI: 10.1145/3517077.3517087
Xin Zhang, Xia Wang, Gangcheng Jiao, Ye Yang, Hongchang Cheng, Bo Yan
Due to the limitation of the device, pictures taken in low-light environment usually consist of unpleasant deterioration, such as low contrast and color distortion. In this paper, we propose a Multi-scale Deep Curve Estimation network (MSDCE) for low-light image enhancement, which formulates the single low-light image enhancement task as a pixel-wise curve estimation by paired learning. To impose more priors of low-light regions, we propose an inverse illuminance map as part of the Curve Estimation network input. The curve estimation network backbone is composed of multi-scale modules which learns information from multi-scale feature streams and ensures the information exchange across different scales. Compared with several state-of-the-art methods, our method is significantly better. From the perspective of visual evaluation, our MSDCE can effectively improve the contrast and illumination of the image, and ensure the color fidelity of the image. CCS CONCEPTS • Computing methodologies • Artificial intelligence • Computer vision • Computer vision problems • Reconstruction
由于设备的限制,在弱光环境下拍摄的照片通常会出现令人不快的劣化,比如对比度低、色彩失真。本文提出了一种用于弱光图像增强的多尺度深度曲线估计网络(MSDCE),该网络通过配对学习将单个弱光图像增强任务描述为逐像素曲线估计。为了对低光区域施加更多的先验,我们提出了一个逆照度图作为曲线估计网络输入的一部分。曲线估计网络骨干网由多尺度模块组成,从多尺度特征流中学习信息,保证了信息在不同尺度间的交换。与几种最先进的方法相比,我们的方法明显更好。从视觉评价的角度来看,我们的MSDCE可以有效地提高图像的对比度和照度,保证图像的色彩保真度。CCS概念•计算方法•人工智能•计算机视觉•计算机视觉问题•重建
{"title":"Multi-scale Deep Curve Estimation for Low-light Image Enhancement","authors":"Xin Zhang, Xia Wang, Gangcheng Jiao, Ye Yang, Hongchang Cheng, Bo Yan","doi":"10.1145/3517077.3517087","DOIUrl":"https://doi.org/10.1145/3517077.3517087","url":null,"abstract":"Due to the limitation of the device, pictures taken in low-light environment usually consist of unpleasant deterioration, such as low contrast and color distortion. In this paper, we propose a Multi-scale Deep Curve Estimation network (MSDCE) for low-light image enhancement, which formulates the single low-light image enhancement task as a pixel-wise curve estimation by paired learning. To impose more priors of low-light regions, we propose an inverse illuminance map as part of the Curve Estimation network input. The curve estimation network backbone is composed of multi-scale modules which learns information from multi-scale feature streams and ensures the information exchange across different scales. Compared with several state-of-the-art methods, our method is significantly better. From the perspective of visual evaluation, our MSDCE can effectively improve the contrast and illumination of the image, and ensure the color fidelity of the image. CCS CONCEPTS • Computing methodologies • Artificial intelligence • Computer vision • Computer vision problems • Reconstruction","PeriodicalId":233686,"journal":{"name":"2022 7th International Conference on Multimedia and Image Processing","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123582445","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
Submission Research on an Integrated Service System of Self-service Intelligent itinerary-checking , Registration and Charging (I) 自助智能行程查、登记、收费综合服务系统提交研究(一)
Pub Date : 2022-01-14 DOI: 10.1145/3517077.3517116
Wanpeng Tang
This study provides a self-service intelligent itinerary-checking , Registration and Charging service system, including communication terminal software subsystem and monitoring subsystem. The terminal software subsystem is used to respond to the interface operation event request, transmit the terminal status information and service data information to the monitoring subsystem in real time, and receive the remote maintenance instructions of the monitoring subsystem. The monitoring subsystem is used to receive and save the terminal device status information and service data information sent by the terminal software subsystem, perform fault diagnosis, automatic alarm and remote maintenance according to the terminal status information, and perform statistical analysis and query output according to the service data information. This system can meet the current registration, payment, triage, medical guidance, inquiry and printing and other self-help needs, with comprehensive supervision and maintenance of the terminal equipment monitoring subsystem, optimize the business process, improve the quality of service and the utilization of terminal equipment, better solve the problem of difficult to see a doctor.
本研究提供了一个自助智能行程查票、登记和收费服务系统,包括通信终端软件子系统和监控子系统。终端软件子系统用于响应接口运行事件请求,实时向监控子系统传输终端状态信息和业务数据信息,并接收监控子系统的远程维护指令。监控子系统用于接收和保存终端软件子系统发送的终端设备状态信息和业务数据信息,根据终端状态信息进行故障诊断、自动告警和远程维护,并根据业务数据信息进行统计分析和查询输出。本系统能满足当前挂号、缴费、分诊、医疗指导、查询打印等自助需求,具有终端设备监控子系统的全面监督维护,优化业务流程,提高终端设备的服务质量和利用率,更好地解决看病难问题。
{"title":"Submission Research on an Integrated Service System of Self-service Intelligent itinerary-checking , Registration and Charging (I)","authors":"Wanpeng Tang","doi":"10.1145/3517077.3517116","DOIUrl":"https://doi.org/10.1145/3517077.3517116","url":null,"abstract":"This study provides a self-service intelligent itinerary-checking , Registration and Charging service system, including communication terminal software subsystem and monitoring subsystem. The terminal software subsystem is used to respond to the interface operation event request, transmit the terminal status information and service data information to the monitoring subsystem in real time, and receive the remote maintenance instructions of the monitoring subsystem. The monitoring subsystem is used to receive and save the terminal device status information and service data information sent by the terminal software subsystem, perform fault diagnosis, automatic alarm and remote maintenance according to the terminal status information, and perform statistical analysis and query output according to the service data information. This system can meet the current registration, payment, triage, medical guidance, inquiry and printing and other self-help needs, with comprehensive supervision and maintenance of the terminal equipment monitoring subsystem, optimize the business process, improve the quality of service and the utilization of terminal equipment, better solve the problem of difficult to see a doctor.","PeriodicalId":233686,"journal":{"name":"2022 7th International Conference on Multimedia and Image Processing","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131025611","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: 1
On-line intelligent visual identification algorithm of power equipment state under the complex environment based on SIFT 基于SIFT的复杂环境下电力设备状态在线智能视觉识别算法
Pub Date : 2022-01-14 DOI: 10.1145/3517077.3517086
Yun-Fo Liu, Qiang Lyu, Yanjie Zhang, Chao Yang, Qifan Yang, Feng Zhou
At present, the application of computer vision technology in power systems is increasing. The idea of using image processing and machine vision to monitor power equipment is not new. However, the research mainly focuses on the application of computer vision technology in the fields of transmission line environment and insulator detection. Combined the actual conditions of the intelligent grid substation and the need of construction, this paper proposed and studied a kind of identification algorithm based on intelligent computer vision technology, aiming at solving the problem of automatic identification of typical outdoor circuit breakers, disconnectors and indoor switchgear. First, using scale-invariant feature transform (scale invariant feature transform, SIFT) algorithm, the paper accurately positions the area to be detected; second, extracts isolating switch line information and switchgear circle information using randomized Hough transform, and through the k-NN (k-Nearest Neighbour) extracts and ferreting breaker character information; Finally, three kinds of electric power equipment are identified intelligently by threshold setting, and the identification effect and stability of the algorithm are validated in the disconnector and Qing He substation of a 500 kv substation in China.
目前,计算机视觉技术在电力系统中的应用越来越多。利用图像处理和机器视觉来监控电力设备的想法并不新鲜。然而,研究主要集中在计算机视觉技术在输电线路环境和绝缘子检测领域的应用。本文结合智能电网变电站的实际情况和施工需要,提出并研究了一种基于智能计算机视觉技术的识别算法,旨在解决典型室外断路器、隔离器和室内开关柜的自动识别问题。首先,采用尺度不变特征变换(scale invariant feature transform, SIFT)算法,对待检测区域进行精确定位;其次,利用随机化霍夫变换提取隔离开关线信息和开关柜环信息,并通过k-NN (k-Nearest Neighbour)提取和搜索断路器特征信息;最后,通过设置阈值对三种电力设备进行智能识别,并在国内某500kv变电站的隔离器和清河变电站中验证了算法的识别效果和稳定性。
{"title":"On-line intelligent visual identification algorithm of power equipment state under the complex environment based on SIFT","authors":"Yun-Fo Liu, Qiang Lyu, Yanjie Zhang, Chao Yang, Qifan Yang, Feng Zhou","doi":"10.1145/3517077.3517086","DOIUrl":"https://doi.org/10.1145/3517077.3517086","url":null,"abstract":"At present, the application of computer vision technology in power systems is increasing. The idea of using image processing and machine vision to monitor power equipment is not new. However, the research mainly focuses on the application of computer vision technology in the fields of transmission line environment and insulator detection. Combined the actual conditions of the intelligent grid substation and the need of construction, this paper proposed and studied a kind of identification algorithm based on intelligent computer vision technology, aiming at solving the problem of automatic identification of typical outdoor circuit breakers, disconnectors and indoor switchgear. First, using scale-invariant feature transform (scale invariant feature transform, SIFT) algorithm, the paper accurately positions the area to be detected; second, extracts isolating switch line information and switchgear circle information using randomized Hough transform, and through the k-NN (k-Nearest Neighbour) extracts and ferreting breaker character information; Finally, three kinds of electric power equipment are identified intelligently by threshold setting, and the identification effect and stability of the algorithm are validated in the disconnector and Qing He substation of a 500 kv substation in China.","PeriodicalId":233686,"journal":{"name":"2022 7th International Conference on Multimedia and Image Processing","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132385062","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
Speckle suppression and texture preservation in optical coherence tomography images using variational image decomposition 基于变分图像分解的光学相干断层扫描图像的斑点抑制和纹理保存
Pub Date : 2022-01-14 DOI: 10.1145/3517077.3517078
Biyuan Li, Xin Zhao, Jun Zhang
Filtering off speckle noise while preserving fine details for optical coherence tomography(OCT) is particularly challenging. In this paper, an efficient method based on variational image decomposition(VID) is proposed to suppress speckle from OCT retinal images. A new BL-G-BM3D model based on VID is proposed to decompose one OCT retinal image into the background part, the texture part and noise. Each part is described by suitable function space separately and processed individually. The proposed model is able to preserve structural information while sufficiently suppressing speckle noise. We test the proposed method on two raw OCT retinal images with low contrast and high noise level, and compare with four other related and widely used filtering methods in terms of both quantitative evaluation and visual quality.The experimental results have demonstrated the validity of the proposed method.
对于光学相干层析成像(OCT)来说,在保留精细细节的同时过滤掉散斑噪声尤其具有挑战性。本文提出了一种基于变分图像分解(VID)的OCT视网膜图像斑点抑制方法。提出了一种新的基于VID的BL-G-BM3D模型,将OCT视网膜图像分解为背景部分、纹理部分和噪声部分。每个部分分别用合适的函数空间描述,分别处理。该模型能够在充分抑制散斑噪声的同时保留结构信息。我们在两张低对比度、高噪声水平的OCT视网膜原始图像上测试了该方法,并在定量评价和视觉质量方面与其他四种相关的、广泛使用的滤波方法进行了比较。实验结果证明了该方法的有效性。
{"title":"Speckle suppression and texture preservation in optical coherence tomography images using variational image decomposition","authors":"Biyuan Li, Xin Zhao, Jun Zhang","doi":"10.1145/3517077.3517078","DOIUrl":"https://doi.org/10.1145/3517077.3517078","url":null,"abstract":"Filtering off speckle noise while preserving fine details for optical coherence tomography(OCT) is particularly challenging. In this paper, an efficient method based on variational image decomposition(VID) is proposed to suppress speckle from OCT retinal images. A new BL-G-BM3D model based on VID is proposed to decompose one OCT retinal image into the background part, the texture part and noise. Each part is described by suitable function space separately and processed individually. The proposed model is able to preserve structural information while sufficiently suppressing speckle noise. We test the proposed method on two raw OCT retinal images with low contrast and high noise level, and compare with four other related and widely used filtering methods in terms of both quantitative evaluation and visual quality.The experimental results have demonstrated the validity of the proposed method.","PeriodicalId":233686,"journal":{"name":"2022 7th International Conference on Multimedia and Image Processing","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115256866","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
A PCA-aided EV-EGI Method for Registering Volumetric Datasets 一种pca辅助EV-EGI方法配准体积数据集
Pub Date : 2022-01-14 DOI: 10.1145/3517077.3517095
Chun Dong, Timothy S Newman
A method for volumetric dataset registration that utilizes principal component analysis (PCA) and volumetric extended Gaussian image (EGI)-based processing is presented. The method uses PCA to determine an initial coarse estimate of orientation difference between two volumetric datasets. The PCA is based on certain automatically selected (i.e., significant) voxels. The coarse estimate then is refined by a three-stage process that utilizes enhanced volumetric extended Gaussian images (EV-EGIs). These final EV-EGI stages also provide the translational component. The method's combination of steps allows for faster processing at roughly similar accuracy versus prior work based solely on EV-EGIs. Experimental comparisons with Globally optimal Iterative Closest Pointset (Go-ICP) registration are also reported and analyzed.
提出了一种利用主成分分析(PCA)和基于体积扩展高斯图像(EGI)处理的体积数据集配准方法。该方法使用主成分分析法来确定两个体积数据集之间的方向差的初始粗略估计。PCA是基于某些自动选择的(即显著的)体素。然后通过利用增强体积扩展高斯图像(EV-EGIs)的三阶段过程对粗估计进行细化。这些最后的EV-EGI阶段也提供了转译组件。与之前仅基于EV-EGIs的工作相比,该方法的步骤组合允许以大致相似的精度更快地处理。本文还报道并分析了与全局最优迭代最近点集(Go-ICP)配准的实验比较。
{"title":"A PCA-aided EV-EGI Method for Registering Volumetric Datasets","authors":"Chun Dong, Timothy S Newman","doi":"10.1145/3517077.3517095","DOIUrl":"https://doi.org/10.1145/3517077.3517095","url":null,"abstract":"A method for volumetric dataset registration that utilizes principal component analysis (PCA) and volumetric extended Gaussian image (EGI)-based processing is presented. The method uses PCA to determine an initial coarse estimate of orientation difference between two volumetric datasets. The PCA is based on certain automatically selected (i.e., significant) voxels. The coarse estimate then is refined by a three-stage process that utilizes enhanced volumetric extended Gaussian images (EV-EGIs). These final EV-EGI stages also provide the translational component. The method's combination of steps allows for faster processing at roughly similar accuracy versus prior work based solely on EV-EGIs. Experimental comparisons with Globally optimal Iterative Closest Pointset (Go-ICP) registration are also reported and analyzed.","PeriodicalId":233686,"journal":{"name":"2022 7th International Conference on Multimedia and Image Processing","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121808563","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 Autonomous Foot Movement Recognition Based on SVM 基于支持向量机的自主足部运动识别研究
Pub Date : 2022-01-14 DOI: 10.1145/3517077.3517090
Tongning Meng, Li Zhao, Zhiwen Zhang, Xinglin He
In order to improve the effectiveness of rehabilitation of stroke patients, active training can be used to treat and recover the patient's foot dyskinesia. Recognizing the different movement characteristics of the feet is an important part of the active rehabilitation of stroke patients. In this paper, the EMG signals of different movements of the right foot are classified and studied. The EMG signals of three different movement states of the foot resting state, foot stretched 15° and foot stretched 45° are collected, absolute mean and filter common space mode were used for feature extraction of EMG signal, and support vector machine (SVM) was used for classification and recognition after extraction. The experimental results show that the classification accuracy rate of resting state-foot-stretched 45° is 89.9%, which exceeds the classification accuracy rate of resting state-foot-stretched 15° of 86.8%. It shows that when the subjects stretch the foot at 45°, more motion units are activated and the characteristics are more obvious than when the feet are stretched at 15°. Therefore, by classifying the characteristics of EMG signals and identifying different autonomic movements of feet, it can be used as the basis for rehabilitation treatment of stroke patients. At the same time, the average classification accuracy of 15° -45 ° and the resting state -15 ° -45 ° is above 80%, which confirms the feasibility of the signal processing method and support vector machine classification algorithm used in this paper for the study of automatic foot motion recognition.
为了提高脑卒中患者的康复效果,可以采用主动训练来治疗和恢复患者的足部运动障碍。认识足部不同的运动特征是脑卒中患者主动康复的重要组成部分。本文对右脚不同运动的肌电信号进行了分类和研究。采集足部静止状态、足部拉伸15°和足部拉伸45°三种不同运动状态下的肌电信号,采用绝对均值和滤波共空间模式对肌电信号进行特征提取,提取后使用支持向量机(SVM)进行分类识别。实验结果表明,静息状态脚拉伸45°的分类准确率为89.9%,超过静息状态脚拉伸15°的分类准确率86.8%。结果表明,受试者在足部拉伸45°时,激活的运动单元比足部拉伸15°时更多,运动特征更明显。因此,通过对肌电信号的特征进行分类,识别足部不同的自主运动,可以作为脑卒中患者康复治疗的依据。同时,15°-45°和静息状态-15°-45°的平均分类准确率均在80%以上,证实了本文所采用的信号处理方法和支持向量机分类算法用于自动足部运动识别研究的可行性。
{"title":"Research on Autonomous Foot Movement Recognition Based on SVM","authors":"Tongning Meng, Li Zhao, Zhiwen Zhang, Xinglin He","doi":"10.1145/3517077.3517090","DOIUrl":"https://doi.org/10.1145/3517077.3517090","url":null,"abstract":"In order to improve the effectiveness of rehabilitation of stroke patients, active training can be used to treat and recover the patient's foot dyskinesia. Recognizing the different movement characteristics of the feet is an important part of the active rehabilitation of stroke patients. In this paper, the EMG signals of different movements of the right foot are classified and studied. The EMG signals of three different movement states of the foot resting state, foot stretched 15° and foot stretched 45° are collected, absolute mean and filter common space mode were used for feature extraction of EMG signal, and support vector machine (SVM) was used for classification and recognition after extraction. The experimental results show that the classification accuracy rate of resting state-foot-stretched 45° is 89.9%, which exceeds the classification accuracy rate of resting state-foot-stretched 15° of 86.8%. It shows that when the subjects stretch the foot at 45°, more motion units are activated and the characteristics are more obvious than when the feet are stretched at 15°. Therefore, by classifying the characteristics of EMG signals and identifying different autonomic movements of feet, it can be used as the basis for rehabilitation treatment of stroke patients. At the same time, the average classification accuracy of 15° -45 ° and the resting state -15 ° -45 ° is above 80%, which confirms the feasibility of the signal processing method and support vector machine classification algorithm used in this paper for the study of automatic foot motion recognition.","PeriodicalId":233686,"journal":{"name":"2022 7th International Conference on Multimedia and Image Processing","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130766263","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: 1
Design of Mobile Robot Path Planning Algorithm Based on Improved Whale Optimization Algorithm 基于改进鲸鱼优化算法的移动机器人路径规划算法设计
Pub Date : 2022-01-14 DOI: 10.1145/3517077.3517115
Jia Liu, Zhikang Chen, Qiang Liu, Rui Shen, Linlin Hou, Yunxi Zhang
In this paper, an improved whale optimization algorithm (IWOA) is proposed to solve the problem of independent path planning for mobile robots, which makes mobile robots move along the optimal path. By combining inverse initial coding optimization with Levy flight, The classic whale optimization algorithm (WOA) was improved, the optimization ability of WOA and the solving ability of optimal path point are improved, then the local optimal solutions are maximally avoided. Finally, by comparing the IWOA with the path planning effect diagram of the classical WOA through simulation, the feasibility and efficiency of the IWOA in path planning are verified.
本文提出了一种改进的鲸鱼优化算法(IWOA)来解决移动机器人的独立路径规划问题,使移动机器人沿着最优路径运动。将逆初始编码优化与Levy飞行相结合,对经典的鲸鱼优化算法(WOA)进行了改进,提高了WOA的优化能力和最优路径点的求解能力,最大限度地避免了局部最优解。最后,通过仿真将IWOA与经典WOA的路径规划效果图进行对比,验证了IWOA在路径规划中的可行性和有效性。
{"title":"Design of Mobile Robot Path Planning Algorithm Based on Improved Whale Optimization Algorithm","authors":"Jia Liu, Zhikang Chen, Qiang Liu, Rui Shen, Linlin Hou, Yunxi Zhang","doi":"10.1145/3517077.3517115","DOIUrl":"https://doi.org/10.1145/3517077.3517115","url":null,"abstract":"In this paper, an improved whale optimization algorithm (IWOA) is proposed to solve the problem of independent path planning for mobile robots, which makes mobile robots move along the optimal path. By combining inverse initial coding optimization with Levy flight, The classic whale optimization algorithm (WOA) was improved, the optimization ability of WOA and the solving ability of optimal path point are improved, then the local optimal solutions are maximally avoided. Finally, by comparing the IWOA with the path planning effect diagram of the classical WOA through simulation, the feasibility and efficiency of the IWOA in path planning are verified.","PeriodicalId":233686,"journal":{"name":"2022 7th International Conference on Multimedia and Image Processing","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134057307","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: 3
期刊
2022 7th International Conference on Multimedia and Image Processing
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1