Search | Engineering

订阅投稿

首页工程期刊工程焦点工程成就工程前沿关于我们 English

资源类型

期刊论文 62

会议视频 1

年份

2023 7

2022 7

2021 8

2020 11

2019 2

2018 1

2017 4

2016 2

2015 3

2011 3

2009 1

2008 1

2007 4

2006 2

2005 1

2004 2

2003 2

1999 1

展开︾

关键词

可视化仿真 4

实时控制 2

神经假体 2

LM331型电压-频率转换器 1

Visual Basic 6.0 1

k-最近邻分类 1

三维动态 1

三维视觉知识；三维参数模型；心脏病理诊断；数据增强 1

串行通信 1

主动视觉 1

主成分分析 1

交互式可视化标注；主动学习；可视分析 1

人为操作失误 1

人工智能 1

人工智能；深度学习；可解释性模型 1

人的信息处理模型 1

仿真 1

优化 1

展开︾

检索范围：

排序：展示方式：

Design of an enhanced visual odometry by building and matching compressive panoramic landmarks online

Wei LU,Zhi-yu XIANG,Ji-lin LIU

《信息与电子工程前沿（英文）》 2015年第16卷第2期页码 152-165 doi: 10.1631/FITEE.1400139

摘要： Efficient and precise localization is a prerequisite for the intelligent navigation of mobile robots. Traditional visual localization systems, such as visual odometry (VO) and simultaneous localization and mapping (SLAM), suffer from two shortcomings: a drift problem caused by accumulated localization error, and erroneous motion estimation due to illumination variation and moving objects. In this paper, we propose an enhanced VO by introducing a panoramic camera into the traditional stereo-only VO system. Benefiting from the 360° field of view, the panoramic camera is responsible for three tasks: (1) detecting road junctions and building a landmark library online; (2) correcting the robot’s position when the landmarks are revisited with any orientation; (3) working as a panoramic compass when the stereo VO cannot provide reliable positioning results. To use the large-sized panoramic images efficiently, the concept of compressed sensing is introduced into the solution and an adaptive compressive feature is presented. Combined with our previous two-stage local binocular bundle adjustment (TLBBA) stereo VO, the new system can obtain reliable positioning results in quasi-real time. Experimental results of challenging long-range tests show that our enhanced VO is much more accurate and robust than the traditional VO, thanks to the compressive panoramic landmarks built online.

关键词： Visual odometry Panoramic landmark Landmark matching Compressed sensing Adaptive compressive feature

HTML PDF 收藏

Research and application of visual location technology for solder paste printing based on machine vision

Luosi WEI, Zongxia JIAO

《机械工程前沿（英文）》 2009年第4卷第2期页码 184-191 doi: 10.1007/s11465-009-0034-9

摘要： A location system is very important for solder paste printing in the process of surface mount technology (SMT). Using machine vision technology to complete the location mission is new and very efficient. This paper presents an integrated visual location system for solder paste printing based on machine vision. The working principle of solder paste printing is introduced and then the design and implementation of the visual location system are described. In the system, two key techniques are completed by secondary development based on VisionPro. One is accurate image location solved by the pattern-based location algorithms of PatMax. The other one is camera calibration that is achieved by image warping technology through the checkerboard plate. Moreover, the system can provide good performances such as high image locating accuracy with 1/40 sub-pixels, high anti-jamming, and high-speed location of objects whose appearance is rotated, scaled, and/or stretched.

关键词： machine vision visual location solder paste printing VisionPro

HTML PDF 收藏

A visual graphic approach for mobility analysis of parallel mechanisms

Xu PEI, Jingjun YU

《机械工程前沿（英文）》 2011年第6卷第1期页码 92-95 doi: 10.1007/s11465-011-0213-3

HTML PDF 收藏

视觉检测技术及应用

叶声华,邾继贵,王仲,杨学友

《中国工程科学》 1999年第1卷第1期页码 49-52

摘要：

视觉检测技术，尤其是基于三角法的主动和被动视觉检测技术具有非接触、速度快、柔性好等特点，是一种先进的检测手段，适合现代制造业的需要。文章论述了视觉检测技术原理，讨论了已经研制的多个实际视觉检测系统，从不同角度展示了视觉检测技术在现代制造业中广阔的应用前景。

关键词：主动视觉被动视觉检测系统现代制造

HTML PDF 收藏

An autonomous miniature wheeled robot based on visual feedback control

CHEN Haichu

《机械工程前沿（英文）》 2007年第2卷第2期页码 197-200 doi: 10.1007/s11465-007-0033-7

摘要： Using two micro-motors, a novel omni-direction miniature wheeled robot is designed on the basis of the bi-corner driving principle. The robot takes advantage of the Bluetooth technology to wirelessly transmit data at a short distance. Its position and omni-direction motion are precise. A Charge Coupled Device (CCD) camera is used for measuring and for visual navi gation. A control system is developed. The precision of the position is 0.5 mm, the resolution is about 0.05 mm, and the maximum velocity is about 52 mm/s. The visual navigation and control system allow the robot to navigate and track the target and to accomplish autonomous locomotion.

关键词： measuring distance autonomous locomotion advantage navigation

HTML PDF 收藏

基于定量属性的单目标视觉跟踪算法评价体系研究 Article

Wen-jing KANG, Chang LIU, Gong-liang LIU

《信息与电子工程前沿（英文）》 2020年第21卷第3期页码 405-421 doi: 10.1631/FITEE.1900245

摘要：视觉跟踪是计算机视觉领域热门研究课题之一。近年来，很多先进跟踪算法和性能评价基准相继发布，并取得巨大成功。现有评价体系大多定位于衡量整体性能，无法通过针对性的详细论证评估跟踪器的优势和缺点，且很多常用评测指标缺乏令人信服的含义解释。本文从测试数据、测试方法、测试指标3方面深入分析跟踪评价体系的细节。首先，归纳整理了12个反映图像序列不同特性的帧间视觉属性，并首次定量给出其归一化公式。基于这些属性定义，提出两种新的测试方法，即基于相关性的测试和基于权重的测试，使评价体系能更直观、更清晰地评定跟踪器各方面性能。然后，将所提测试方法应用于著名的跟踪挑战赛，即Video Object Tracking (VOT) Challenge 2017。测试结果表明，在目标尺寸快速或剧烈变化时，跟踪器大多表现不佳，即使基于深度学习的先进跟踪器也未能很好解决这一问题。此外发现，中心位置差错（center location error，CLE）性能指标虽未考虑到目标尺度，在实际测试中仍对目标尺寸变化很敏感。

关键词：视觉跟踪；性能评价；视觉属性；计算机视觉

HTML PDF 收藏

交互式可视化标注与主动学习：实验比较 Research

Mohammad CHEGIN, Jürgen BERNARD, Jian CUI, Fatemeh CHEGINI, Alexei SOURIN, Keith Keith, Tobias SCHRECK

《信息与电子工程前沿（英文）》 2020年第21卷第4期页码 524-535 doi: 10.1631/FITEE.1900549

摘要：监督式机器学习方法可自动分类新数据，且对数据分析非常有帮助。监督式机器学习的质量不仅依赖于使用的算法类型，也依赖于用于训练分类器的标注数据集的质量。训练数据集中的标注实例通常依赖于专业分析人员的手工选择与注释，且通常是一个单调与耗时的过程。标签可以在学习过程中为主动学习算法提供有用的输入，以自动确定数据实例的子集。交互式可视化标注技术是有前景的选择，它提供有效的视觉概览，分析人员可从中同时查看数据记录与选择项目标签。将分析人员置于循环中，生成的分类器可得到更高准确率。虽然交互式可视化标注技术的初步结果在某种意义上有前景的，考虑到用户标注可改善监督式学习，但是该技术的许多方面仍有待探索。本文使用mVis工具标注一个多元数据集以比较3种交互式可视化技术（相似图、散点矩阵与平行坐标图）以及主动学习。结果表明3种交互式可视化标注技术的分类准确率均高于主动学习算法，相对于散点矩阵与平行坐标图，用户主观上更偏爱使用相似图标注。用户也可以根据使用的可视化技术采用不同标注策略。

关键词：交互式可视化标注；主动学习；可视分析

HTML PDF 收藏

射频识别在可视化后勤系统中的应用

王爱明,穆晓曦,李艾华

《中国工程科学》 2006年第8卷第8期页码 65-68

摘要：

射频识别技术是一种新型自动识别技术，具有可靠性高、保密性强，方便快捷、非接触等特点。将射频识别技术应用于后勤可视化系统，可以实时获取保障对象的需求及物资供应的类型、数量和流向等信息，从而实现全时段、全方位、全过程的供应保障。介绍了射频识别系统结构及工作原理，同时研究了射频识别技术在后勤可视化系统中的应用，所提出的在运物资可视化系统是根据贴在集装箱和装备上的射频识别标签实现的。

关键词：可视化后勤射频识别在运可视化系统

HTML PDF 收藏

论视觉知识 Perspective

Yun-he PAN

《信息与电子工程前沿（英文）》 2019年第20卷第8期页码 1021-1025 doi: 10.1631/FITEE.1910001

摘要：提出“视觉知识”概念。视觉知识是知识表达的一种新形式. 它与迄今为止人工智能（AI）所用知识表达方法不同. 其中视觉概念具有典型（prototype）与范畴结构、层次结构与动作结构等要素. 视觉概念能构成视觉命题，包括场景结构与动态结构，视觉命题能构成视觉叙事。指出重构计算机图形学成果可实现视觉知识表达及其推理与操作，重构计算机视觉成果可实现视觉知识学习。实现视觉知识表达、推理、学习和应用技术将是AI 2.0取得突破的重要方向之一。

关键词： None

HTML PDF 收藏

MSWNet: A visual deep machine learning method adopting transfer learning based upon ResNet 50 for municipal

《环境科学与工程前沿（英文）》 2023年第17卷第6期 doi: 10.1007/s11783-023-1677-1

摘要：

● MSWNet was proposed to classify municipal solid waste.

关键词： Municipal solid waste sorting Deep residual network Transfer learning Cyclic learning rate Visualization

HTML PDF 收藏

户外空中双机械手抓取设计和视觉伺服 Article

Pablo Ramon-Soria, Begoña C. Arrue, Anibal Ollero

《工程（英文）》 2020年第6卷第1期页码 77-88 doi: 10.1016/j.eng.2019.11.003

摘要：

本文介绍了一种配备有RGB-D摄像机的使用带有双机械手的无人飞行器（unmanned aerial vehicle, UAV）抓取已知物体的系统。空中操纵仍然是一项极具挑战性的任务。本文主要从三个方面对这一任务进行了评价：目标检测与姿态估计、抓取设计、飞行中的抓取动作。人工神经网络（artificial neural network, ANN）首先被用来获得有关物体位置的线索。接下来，使用对齐算法获取对象的六维（six-dimensional, 6D）姿态，并使用扩展的卡尔曼滤波器进行滤波。然后，使用物体的三维（three-dimensional, 3D）模型来估计空中机械手可实现良好抓取的排列清单。检测算法的结果（即对象的姿态）用于更新手臂朝向对象的轨迹。如果由于无人机的振荡而无法达到目标姿态，则算法将切换到下一个可行的抓取。本文介绍了总体方法，给出了每个模块的仿真实验结果和实际实验结果，并提供了视频演示结果。

关键词：空中操纵，抓取设计，视觉伺服

HTML PDF 收藏

NLWSNet: a weakly supervised network for visual sentiment analysis in mislabeled web images

Luo-yang Xue, Qi-rong Mao, Xiao-hua Huang, Jie Chen,mao_qr@ujs.edu.cn

《信息与电子工程前沿（英文）》 2020年第21卷第9期页码 1267-1412 doi: 10.1631/FITEE.1900618

摘要： Large-scale datasets are driving the rapid developments of deep convolutional neural networks for . However, the annotation of large-scale datasets is expensive and time consuming. Instead, it is easy to obtain weakly labeled web images from the Internet. However, noisy labels still lead to seriously degraded performance when we use images directly from the web for training networks. To address this drawback, we propose an end-to-end network, which is robust to mislabeled web images. Specifically, the proposed attention module automatically eliminates the distraction of those samples with incorrect labels by reducing their attention scores in the training process. On the other hand, the special-class activation map module is designed to stimulate the network by focusing on the significant regions from the samples with correct labels in a approach. Besides the process of feature learning, applying regularization to the classifier is considered to minimize the distance of those samples within the same class and maximize the distance between different class centroids. Quantitative and qualitative evaluations on well- and mislabeled web image datasets demonstrate that the proposed algorithm outperforms the related methods.

HTML PDF 收藏

论视觉理解 Perspective

潘云鹤

《信息与电子工程前沿（英文）》 2022年第23卷第9期页码 1287-1289 doi: 10.1631/FITEE.2130000

摘要： 1 Problems and development in the field of visual recognition From the beginning of artificial intelligence (AI), pattern recognition has been an important aspect of the field. In recent years, the maturity of deep neural networks (DNNs) has significantly improved the accuracy of visual recognition. DNN has been widely used in applications such as medical image classification, vehicle identification, and facial recognition, and has thus promoted the development of the AI industry to a climax. However, there are currently critical defects in visual recognition based on DNN technology. For example, these networks usually require a very large amount of labeled training data, and have weak cross-domain transferability and task generalization. Their learning and reasoning processes are still hard to understand, which leads to unexplainable predictions. These challenges present an obstacle to the development of AI research and application. If we look at the current visual recognition technology from a larger and broader perspective, we can find that the above defects are fundamental, because the currently used DNN model needs to be trained with a large amount of labeled visual data, and then used in the process of visual recognition. In essence, it is a classification process based on data statistics and pattern matching (), so it is heavily dependent on training sample distribution. However, to have interpretability and transferability, visual classification is not good enough, while visual understanding becomes indispensable. 2 Three-step model of visual understanding Visual recognition is not equivalent to visual understanding. We propose that there are three steps in visual understanding, of which classification is only the first. After classification, one proceeds to the second step: visual parsing. In the process of visual parsing, the components of the visual object and their structural relationship are further identified and compared. Identification involves finding components and structures in visual data that correspond to the components and structures of known visual concepts. Parsing verifies the correctness of the classification results and establishes the structure of visual object data. After completing visual parsing, one proceeds to the third step: visual simulation. In this step, predictive motion simulation and operations including causal reasoning are carried out on the structure of the visual objects to judge the rationality of meeting physical constraints in reality, so as to verify the previous recognition and parsing results. We can take a picture of a cat as an example to illustrate the modeling process of visual understanding. The process is as follows: 1. Recognition: It is a cat. Extract the visual concept of the cat and proceed to the next step; otherwise, stop here. 2. Parsing: Based on the structure contained in the visual concept, identify whether the cat’s head, body, feet, tail, and their relationships are suitable for the cat concept. If not, return to step 1 for re-identification; if yes, proceed to the next step. 3. Simulation: Simulate various activities of the cat to investigate whether the cat’s activities in various environments can be completed reasonably. If not, return to step 2; if yes, proceed to the next step. 4. End visual understanding: Incorporate the processed structured data into the knowledge about cats. 3 Characteristics of the three-step visual understanding model To further understand the above-mentioned three-step visual understanding model, we will further discuss some of its characteristics: 1. The key step in visual understanding is visual parsing. This is an identification of the components contained in the object according to a conceptual structure based on the visual concept (), obtained by visual recognition. Parsing a visual object, in order from top to bottom, is a process of identifying and constructing visual data from the root of the concept tree to the branches and leaves. 2. Human visual parsing tasks are often aimed only at the main components of concepts. The main components have existing, commonly used names. For subsidiary parts that have not been described in language, such as the area between the cheekbones and chin of the face, only experts specialized in anatomy (such as doctors or artists) have professional concepts and memories. Therefore, visual parsing is a cross-media () process that incorporates multiple knowledge () including vision and language. 3. Visual knowledge () is essential for visual parsing and visual simulation, because the visual concept structure provides a reliable source for component identification and comparison. Parents and teachers play a large role in establishing visual knowledge. When they say to a child, “Look, this is a kitten. Kittens have pointed ears, round eyes, long whiskers, and four short legs. When they run fast and leap high, they can catch a mouse,” they are guiding children in constructing basic visual knowledge in their long-term memory. 4. Visual data that have been understood have actually been structured to form visual knowledge. Such visual knowledge can easily be incorporated into long-term memory. For example, when one sees a cat whose head is very small, or whose fur color and markings are unusual, or who has a particular gait, this information may be included in one’s “cat” memory by expanding the concept of “cat” (). The category of visual concepts is very important, and its extent reflects the general degree of knowledge. In fact, it is not always useful to collect a large amount of sample data to train a DNN model. However, the more widely distributed and balanced the data are within a concept category, the better, because the robustness and generalization ability of the model trained based on such sample data are stronger. 5. The learned visual information can naturally be explained, because it has deep structural cognition; it can also be used for transfer learning because the semantic concepts have cross-media relevance. This semantic information can clearly indicate the reasonable direction of transferable recognition. 4 Advancing visual recognition to visual understanding Visual understanding is important, because it can potentially work with visual knowledge () and multiple knowledge representation () to open a new door to AI research. Visual understanding involves not only in-depth visual recognition, but also thorough learning and application of visual knowledge (). AI researchers have been studying visual recognition for more than half a century. Speech recognition, a research task started in parallel with visual recognition, moved on to analysis of words, sentences, and paragraphs quite early, and has successfully developed human-computer dialogue and machine translation, setting a well-known milestone. Therefore, we suggest that it is necessary to advance visual recognition to visual understanding, and that this is an appropriate time to target this deeper visual intelligence behavior.

HTML PDF 收藏

SuPoolVisor：矿池监管可视分析系统 Research

Jia-zhi XIA, Yu-hong ZHANG, Hui YE, Ying WANG, Guang JIANG, Ying ZHAO, Cong XIE, Xiao-yan KUI, Sheng-hui LIAO, Wei-ping WANG

《信息与电子工程前沿（英文）》 2020年第21卷第4期页码 507-523 doi: 10.1631/FITEE.1900532

摘要：在过去十年中，以比特币为代表的加密货币充分展示其在支付和货币系统中的巨大优势与潜力。矿池被认为是比特币的来源，也是市场稳定的基石。对矿池的监管可帮助监管机构有效评估比特币的整体健康状况。但是，矿池匿名性和分析海量交易的难度限制了更深入的分析。此外，对多源异构数据直观和全面的监管也是一个挑战。本文设计并实现一个交互式可视分析系统SuPoolVisor，它可对矿池进行可视化监管，并支持使用可视推理对矿池去匿名化。SuPoolVisor支持矿池和地址两个级别的分析。在矿池级别，使用排序的河流图呈现矿池算力随时间演变情况，并在其他两个视图中设计特殊图形以说明矿池的影响范围和矿池成员迁移。在地址级别，使用力导向图和大规模序列视图呈现矿池中的动态地址网络。特别地，这两个视图与Radviz视图的组合，可用于矿池成员去匿名化的迭代可视推理过程，这些视图都提供了用于跨视图分析和标识的交互功能。我们与该领域专家紧密合作完成3个真实案例，并在案例中证明SuPoolVisor的有效性和可用性。

关键词：比特币矿池；可视分析；交易数据；可视推理；金融科技

HTML PDF 收藏

基于GIS的混凝土坝施工可视化仿真技术及其应用

李景茹,钟登华

《中国工程科学》 2005年第7卷第8期页码 70-74

摘要：

将可视化技术与仿真技术相结合，提出了基于GIS的混凝土坝施工可视化仿真技术，开发了相应的软件GVSS。GVSS是用于制定和优化混凝土坝施工进度计划的工具，提供了可视化和查询等功能。通过将GVSS应用到实际的混凝土坝施工中，证明了该项技术和软件的有效性。

关键词：可视化仿真地理信息系统（GIS）混凝土坝施工进度优化