创新驱动的计算机视觉实验教学设计及实验系统研发

创新创业理论研究与实践 ›› 2024, Vol. 7 ›› Issue (10): 18-23.

创新驱动的计算机视觉实验教学设计及实验系统研发

刘艳, 李庆武, 霍冠英, 赵越, 余彬

河海大学信息科学与工程学院,江苏常州 213200

出版日期:2024-05-25 发布日期:2024-07-16
作者简介:刘艳（1984—）,女,重庆人,博士研究生,副教授,研究方向：信息获取与处理、计算机视觉。
基金资助:
教育部产学合作协同育人项目“创新能力培养驱动下的电子技术实践教学体系研究”（231105789103737）; 教育部第三期供需对接就业育人项目“CDIO理念下的教竞产人才培养模式研究” （2024）; 河海大学本科实践教学改革研究项目（重点课题）“创新能力培养驱动的‘智能感知技术’课程群实践教学研究” （2023）

Computer Vision Experimental Teaching Design and Experimental System Development Based on Innovation Driven

LIU Yan, LI Qingwu, HUO Guanying, ZHAO Yue, YU Bin

College of Information Science and Engineering, Hohai University, Changzhou Jiangsu, 213200, China

Online:2024-05-25 Published:2024-07-16

摘要/Abstract

摘要： 计算机视觉课程是电子信息类和计算机类专业智能感知方向的核心课程,该课程要求理论教学与实践教学同步开展,提升学生对课程基本理论的认识、培养学生创新精神与工程应用能力。在常规实验教学内容的基础上,该文创新性地引入双目视觉技术相关实践环节,在学生熟悉并掌握相关视觉处理技术的同时,开展项目式、启发式创新性实验。同时,为满足前置课程学习不一致情况下的教学需求,研发可视化、开放接口的实验系统,开设演示性、操作性、研创性实验项目,不仅可激发学生的学习兴趣,还可为工程性研究与学习提供知识积累和实验环境,培养学生创新与解决复杂工程问题的能力。

关键词: 创新驱动, 计算机视觉, 实践教学, 双目视觉技术, 创新性实验, 实验系统

Abstract: The computer vision is a major curriculum of intelligent perception for electronic information specialty and computer science specialty. The curriculum requires both theoretical teaching and extensive practical teaching to enhance students' understanding of basic theories, innovation spirit and engineering application abilities. Based on the content of computer vision experiment teaching, binocular vision technology is innovatively introduced. Students can familiarize and master visual processing techniques, and conduct project-based and heuristic innovative experiments. To meet the teaching needs of inconsistent pre-course learning, we developed a visual and open interfaces experimental system. With the experimental system, we can conduct demonstrative, operational, and innovative experiments. That not only stimulates students'learning interest, but also provides knowledge accumulation and experimental environment. The teaching design based on our experimental system can effectively cultivate students' ability of innovative practice and solving complex engineering problems.

Key words: Innovation driven, Computer vision, Experimental teaching, Binocular vision technology, Innovative experiment, Experimental system

中图分类号:

G642.3

刘艳, 李庆武, 霍冠英, 赵越, 余彬. 创新驱动的计算机视觉实验教学设计及实验系统研发[J]. 创新创业理论研究与实践, 2024, 7(10): 18-23.

LIU Yan, LI Qingwu, HUO Guanying, ZHAO Yue, YU Bin. Computer Vision Experimental Teaching Design and Experimental System Development Based on Innovation Driven[J]. The Theory and Practice of Innovation and Enntrepreneurship, 2024, 7(10): 18-23.

参考文献

[1] 蒋大成,陈超波,马天力,等.新工科背景下机器视觉课程的问题式教学法改革[J].创新创业理论研究与实践,2023,6(23):58-60.
[2] 易力力,赵庆,邱志伟,等.以解决复杂工程问题为核心的大学生科研训练项目实践[J].实验室研究与探索, 2022,41(5):197-201.
[3] 刘艳,曹光静,朱金秀,等.双目视觉实验平台及教学项目设计[J].实验技术与管理,2020,37(1):44-47,51.
[4] ZHANG Z Y .A flexible new technique for camera calibration[J].IEEE Trans. Pattern Anal. Mach. Intell., 2000,22(11): 1330-1334.
[5] 陈庆光,黄俊超,刘强,等.全视角三维成像实验系统设计[J].实验室研究与探索,2020,39(9):88-92.
[6] 白亮,刘辉,尚振宏.自适应融合层级特征的混合退化图像复原算法[J].计算机辅助设计与图形学学报,2021,33(2):215-222.
[7] 周佳立,陈育,吴超,等.基于标签化匹配区域校正的双目立体匹配算法[J].模式识别与人工智能,2020,33(8): 681-691.
[8] 于俊伟,郭园森,张自豪,等.弱监督显著性目标检测研究进展[J/OL].计算机工程与应用,1-17[2024-05-14].http://kns.cnki.net/kcms/detail/11.2127.TP.20231227.1416.002.html.
[9] KAIMING H E, SUN J, TANG X O.Single image haze removal using dark channel prior[J].IEEE Trans Pattern Anal Mach Intell,2011,33(12):2341-53.
[10] BEZDEK J C. EHRLICH R, FULL W.Fcm: the fuzzy c-means clustering algorithm[J].Comput Geosci, 1984,10(2-3): 191-203.
[11] CHAN T F, VESE L A.Active contours without edges.[J].IEEE Trans Image Process,2001,10(2):266-77.
[12] WANG L, LU H, RUAN X, et al.Deep networks for saliency detection via local estimation and global search[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA,2015: 3183-3192.
[13] MEI X, SUN X, ZHOU M C, et al.On building an accurate stereo matching system on graphics hardware[C]. IEEE International Conference on Computer Vision Workshops (ICCV Workshops), Barcelona, 2011:467-474.
[14] HIRSCHMULLER H.Accurate and efficient stereo processing by semi-global matching and mutual information[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, USA, 2005: 807-814.
[15] ARRANZ A, SANCHEZ A, ALVAR M.Multiresolution energy minimisation framework for stereo matching[J].IET Computer Vision,2012,6(5):425-434.
[16] YANG Q.A non-local cost aggregation method for stereo matching[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI,2012: 1402-1409.