|
|
论文:2020,Vol:38,Issue(6):1218-1224 |
|
|
引用本文： |
|
|
张天凡, 李哲, 景啸, 胡斌, 朱亚辉. 基于Hu-DBN的低分辨图案编码识别方法研究[J]. 西北工业大学学报 |
|
|
ZHANG Tianfan, LI Zhe, JING Xiao, HU Bin, ZHU Yahui. Research on Low-Resolution Pattern Coding Recognition Method Based on Hu-DBN[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
| 基于Hu-DBN的低分辨图案编码识别方法研究 |
|
| 张天凡1,2, 李哲1, 景啸1,2, 胡斌2, 朱亚辉3 |
|
1. 湖北工程学院 经济与管理学院, 湖北 孝感 432100;
2. 西北工业大学 自动化学院, 陕西 西安 710072;
3. 陕西学前师范学院, 陕西 西安 710072 |
| 摘要: |
| 图案编码是移动机器人视觉导航中全局定位的关键参照物。通过降低图像编码的影像尺寸和质量有助于减少运算量，以提升算法实时性，但对应特征图像更易受以运动模糊为主的干扰而影响识别的准确性，使得定位失败进而造成整个多智能体控制系统失效。提出了一种优化的低分辨率特征图像码识别方法，在预处理部分将特征图像转换为其Hu不变矩的特征信号矩阵，再将特征图像作为一个特征分量补充到该特征信号矩阵中，通过构建的Hu-DBN神经网络信号分类器对信号矩阵进行学习，从而实现低分辨率自定义图像特征码影像在较高运动容差条件下的准确识别。既避免了经典模式识别依赖模型经验、场景适应性差的问题，同时也避免了直接使用如YOLO等深度学习方法带来的高运算量和识别效率问题。通过移动机器人实例部署展开测试，通过搭载分辨率为640×480图像传感器移动机器人实例展开测试，在0.5 m/s运动速度时平均识别率为96.3％，证明了所提方法的有效性。 |
| 关键词:
图像特征码
低分辨动态影像
Hu不变矩
深度置信网络
移动机器人视觉定位
|
|
| Research on Low-Resolution Pattern Coding Recognition Method Based on Hu-DBN |
|
| ZHANG Tianfan1,2, LI Zhe1, JING Xiao1,2, HU Bin2, ZHU Yahui3 |
|
1. School of Economics and Management, Hubei Engineering University, Xiaogan 432100, China;
2. School of Automation, Northwestern Polytechnical University, Xi'an 710072, China;
3. Shaanxi Xueqian Normal University, Xi'an 710072, China |
| Abstract: |
| The feature image code represented by the two-dimensional code is the key reference for global positioning in the visual navigation of mobile robots. Although reducing the acquired low-resolution image helps to reduce the real-time performance of the algorithm, the acquired feature image is more susceptible to motion blur-based interference and affects the accuracy of recognition, which causes the positioning failure of the whole multi-intelligence, in which the body control system is invalid. In this paper, an optimized low-resolution feature image code recognition method is proposed. In the preprocessing part, the characteristic image is converted into the characteristic signal matrix of Hu invariant moments, and then the characteristic image is added to the characteristic signal matrix as a characteristic component, and then the Hu-DBN neural network signal classifier is used to construct the signal matrix so as to achieve accurate recognition of low-resolution custom image signature images under high motion tolerance conditions. It not only avoids the problem of classical pattern recognition relying on model experience and poor adaptability of the scene, but also avoids the problem of high computational complexity and recognition efficiency of directly deep learning methods such as YOLO. The deployment of the mobile robot instance deployment test shows that the average recognition rate is of 96.3% at a resolution of 640×480@Pixs and motion speed of 0.5 m/s, which proves the effectiveness of the present method. |
| Key words:
calibration plate recognition
low resolution dynamic image
Hu-invariant moment
point diffusion model
mobile robot
|
|
| 收稿日期: 2019-11-20
修回日期:
|
| DOI: 10.1051/jnwpu/20203861218 |
| 基金项目: 国家自然科学基金青年项目（72002067）、教育部人文社会科学研究规划基金（20YJCZH081）、湖北省教育厅科学研究计划重点项目（D20202701）与湖北省教育厅科学研究计划（B2019389）资助 |
| 通讯作者: 李哲(1986-),湖北工程学院副教授,主要从事城市数据分析、复杂网络等研究。e-mail:lizhe_hbeu@vip.163.com
Email：lizhe_hbeu@vip.163.com |
| 作者简介: 张天凡(1982-),湖北工程学院讲师,主要从事图像处理、多智能体控制系统、嵌入式系统等研究。
|
|
| 相关功能 |
|
|
|
|
| 作者相关文章 |
|
| 张天凡 在本刊中的所有文章 |
| 李哲 在本刊中的所有文章 |
| 景啸 在本刊中的所有文章 |
| 胡斌 在本刊中的所有文章 |
| 朱亚辉 在本刊中的所有文章 |
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] ZHANG J, JIA J, ZHU Z, et al. Fine Detection and Classification of Multi-Class Barcode in Complex Environments[C]//International Conference on Multimedia and Expo, 2019:306-311
[2] LIU Y, YANG J, LIU M, et al. Recognition of QR Code with Mobile Phones[C]//Chinese Control and Decision Conference, 2008:203-206
[3] LEE S J, LIM J, TEWOLDE G S, et al. Autonomous Tour Guide Robot by Using Ultrasonic Range Sensors and QR Code Recognition in Indoor Environment[C]//IEEE International Conference on Electro/Information Technology, 2014:410-415
[4] GU Y, ZHANG W. QR Code Recognition Based on Image Processing[C]//International Conference on Information Science and Technology, 2011:733-736
[5] FORMIGA A D, LINS R D, SIMSKE S J, et al. An Assessment of Data Matrix Barcode Recognition under Scaling, Rotation and Cylindrical Warping[C]//ACM Symposium on Applied Computing, 2011:266-267
[6] THIELECKE L, ARANYOSSY T, DAHL A, et al. Limitations and Challenges of Genetic Barcode Quantification[J]. Scientific Reports, 2017, 7(1):43249-43263
[7] HOGPRACHA W, VONGPRADHIP S. Recognition System for QR Code on Moving Car[C]//International Conference on Computer Science and Education, 2015:14-18
[8] GORONZY G, PELKA M, HELLBRUCK H, et al. QRPos:Indoor Positioning System for Self-Balancing Robots Based on QR Codes[C]//International Conference on Indoor Positioning and Indoor Navigation, 2016:1-8
[9] HUANG Q, CHEN W, HUANG X, et al. Data Matrix Code Location Based on Finder Pattern Detection and Bar Code Border Fitting[J]. Mathematical Problems in Engineering, 2012, 2012:1-13
[10] CHEN Y, CHI K, HUA K, et al. Design of Image Barcodes for Future Mobile Advertising[J]. Eurasip Journal on Image and Video Processing, 2017, 2017(1):1-12
[11] NIZAMPATNAM S, SAHA D, CHANDAK R, et al. Dynamic Contrast Enhancement and Flexible Odor Codes[J]. Nature Communications, 2018, 9(1):1-35
[12] HANSEN D K, NASROLLAHI K, RASMUSEN C B, et al. Real-Time Barcode Detection and Classification using Deep Learning[C]//9th International Joint Conference on Computational Intelligence, 2017
[13] ZHANG H, SHI G, LIU L, et al. Detection and Identification Method of Medical Label Barcode Based on Deep Learning[C]//International Conference on Image Processing, 2018:1-6
[14] ANDREY Zharkov, IVAN Zagaynov. Universal Barcode Detector via Semantic Segmentation[C]//2019 International Conference on Document Analysis and Recognition, 2019
[15] REDMON J, FARHADI A. YOLO9000:Better, Faster, Stronger[C]//Computer Vision and Pattern Recognition, 2017:6517-6525
[16] ZHONG P, GONG Z. A Hybrid DBN and CRF Model for Spectral-Spatial Classification of Hyperspectral Images[J]. Statistics, Optimization and Information Computing, 2017, 5(2):75-98
[17] UNIC J, HIROTA K, ROSIN P L, et al. A Hu Moment Invariant as a Shape Circularity Measure[J]. Pattern Recognition, 2010, 43(1):47-57
[18] LI Z, GUO T, BAO F, et al. Teeth Category Classification via Hu Moment Invariant and Extreme Learning Machine[C]. International Conference on Computer Modeling and Simulation, 2018
[19] TRAN V T, ALTHOBIANI F, BALL A, et al. An Approach to Fault Diagnosis of Reciprocating Compressor Valves Using Teager-Kaiser Energy Operator and Deep Belief Networks[J]. Expert Systems with Applications, 2014, 41(9):4113-4122
[20] TAO J, LIU Y, YANG D, et al. Bearing Fault Diagnosis Based on Deep Belief Network and Multisensor Information Fusion[J]. Shock and Vibration, 2016, 2016:1-9
[21] ZHANG L, GAO H, WEN J, et al. A Deep Learning-Based Recognition Method for Degradation Monitoring of Ball Screw with Multi-Sensor Data Fusion[J]. Microelectronics Reliability, 2017, 75:215-222
[22] ZHANG T, ZHOU W, MENG F, et al. Efficiency Analysis and Improvement of an Intelligent Transportation System for the Application in Greenhouse[J]. Electronics, 2019, 8(9):946-971 |
|
|
|
|
|
|
|
