[1]朱齐丹,李小铜,郑天昊.舰载机位姿实时视觉测量算法研究[J].智能系统学报,2021,16(6):1045-1055.[doi:10.11992/tis.202103014]
ZHU Qidan,LI Xiaotong,ZHENG Tianhao.Research on real-time vision measurement algorithm of shipborne aircraft pose[J].CAAI Transactions on Intelligent Systems,2021,16(6):1045-1055.[doi:10.11992/tis.202103014]
点击复制
ZHU Qidan,LI Xiaotong,ZHENG Tianhao.Research on real-time vision measurement algorithm of shipborne aircraft pose[J].CAAI Transactions on Intelligent Systems,2021,16(6):1045-1055.[doi:10.11992/tis.202103014]
舰载机位姿实时视觉测量算法研究
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
16
期数:
2021年第6期
页码:
1045-1055
栏目:
学术论文—机器感知与模式识别
出版日期:
2021-11-05
- Title:
- Research on real-time vision measurement algorithm of shipborne aircraft pose
- Keywords:
- machine vision; shipborne aircraft pose; deep learning; target detection; edge extraction; wireframe matching; GPU acceleration; target segmentation
- 分类号:
- TP391.4
- 摘要:
- 舰载机位姿实时检测对于甲板上的舰载机的运动控制、轨迹规划与防撞等具有重要意义。传统的舰载机调度主要依靠人工判断舰载机位置与航向角进行调度，传统方法不能得出准确数据，还易因为操作员的疏忽与疲劳发生碰撞事故。针对该问题，提出了舰载机位姿实时视觉测量算法。基于YOLO-V4(you only look once version 4)网络以及Canny边缘提取算法对舰载机进行识别分割。创新性地提出一种线框模板匹配算法，通过计算舰载机边缘轮廓与线框模板的匹配度获取最佳位姿。通过并行化与GPU(graphics processing unit)加速，使其满足实时性要求，并在1∶70与1∶14的实物模拟环境中完成测试。结果表明，该算法识别率在95%以上，位置精度在8 mm以内，姿态精度在0.7°以内，速度可达8 Hz。
- Abstract:
- Real-time detection of carrier aircraft pose is of great significance to the movement control, trajectory planning, and collision avoidance of carrier-based aircraft on deck. The traditional scheduling of carrier aircraft mainly relies on the manual judgment of the position and heading angle of the carrier-based aircraft. Traditional methods fail to obtain accurate data and readily cause collisions because of operator negligence and fatigue. Therefore, a real-time visual measurement algorithm for the pose of carrier aircraft is proposed. First, the carrier aircraft is identified and segmented based on the you only look once version 4 (YOLO-V4) network and the Canny edge extraction algorithm. Then, an innovative algorithm for wireframe template matching is proposed, and the best pose is obtained by calculating the matching degree between the contour of the carrier aircraft and the wireframe template. The algorithm meets the real-time requirements through parallelization and graphics processing unit acceleration, and the test is completed in the 1:70 and 1:14 physical simulation environments. The results show that the recognition rate of this algorithm is >95%, the accuracy is within 0.7° and 8 mm, and the speed can reach 8 Hz.
- 参考文献/References:
-
[1] 于鲲, 丛明煜, 戴文聪. 基于三维模型的空间目标视觉位姿测量[J]. 仪器仪表学报, 2019, 40(4): 179-188
YU Kun, CONG Mingyu, DAI Wencong. Spatial target vision pose measurement based on 3D model[J]. Chinese journal of scientific instrument, 2019, 40(4): 179-188
[2] 季涛, 李福东, 杨月全, 等. 基于改进ICP算法和CAD模型库的单目视觉位姿测量[J]. 扬州大学学报(自然科学版), 2019, 22(1): 50-54, 61
JI Tao, LI Fudong, YANG Yuequan, et al. Monocular vision pose measurement based on improved ICP algorithm and CAD model[J]. Journal of Yangzhou University (natural science edition), 2019, 22(1): 50-54, 61
[3] 刘祥. 基于双目视觉的空间非合作目标位姿测量方法[D]. 哈尔滨: 哈尔滨工业大学, 2019: 1-8.
LIU Xiang. Non-cooperative target pose estimation based on stereo vision[D]. Harbin: Harbin Institute of Technology, 2019: 1-8.
[4] 王晓林, 苏松志, 刘晓颖, 等. 一种基于级联神经网络的飞机检测方法[J]. 智能系统学报, 2020, 15(4): 697-704
WANG Xiaolin, SU Songzhi, LIU Xiaoying, et al. Cascade convolutional neural networks for airplane detection[J]. CAAI transactions on intelligent systems, 2020, 15(4): 697-704
[5] 王婷婷, 苍岩, 毕晓君, 等. 改进的Faster R-CNN网络预测尺度参数[J]. 哈尔滨工程大学学报, 2021, 42(3): 426-432
WANG Tingting, CANG Yan, BI Xiaojun, et al. Improved faster R-CNN algorithm for object parameter prediction[J]. Journal of Harbin Engineering University, 2021, 42(3): 426-432
[6] WANG Chen, XU Danfei, ZHU Yuke, et al. DenseFusion: 6D object pose estimation by iterative dense fusion[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA, 2019: 3343-3352.
[7] TEKIN B, SINHA S N, FUA P. Real-time seamless single shot 6D object pose prediction[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA, 2018: 1-2.
[8] 李少飞, 史泽林, 庄春刚. 基于物体点云6D位姿估计的深度学习方法[EB/OL]. [2021-02-19] https://doi.org/10.19678/j.issn.1000-3428.0058768.
LI Shaofei, SHI Zelin, ZHUANG Chungang. Deep learning based 6D object pose estimation using point clouds[EB/OL]. [2021-02-19] https://doi.org/10.19678/j.issn.1000-3428.0058768.
[9] TIAN Meng, ANG JR M H, LEE G H. Shape prior deformation for categorical 6D object pose and size estimation[C]//Proceedings of the 16th European Conference on Computer Vision. Glasgow, UK, 2020: 1-2.
[10] 赵永强, 饶元, 董世鹏, 等. 深度学习目标检测方法综述[J]. 中国图象图形学报, 2020, 25(4): 629-654
ZHAO Yongqiang, RAO Yuan, DONG Shipeng, et al. Survey on deep learning object detection[J]. Chinese journal of image and graphics, 2020, 25(4): 629-654
[11] 李同, 阮士峰, 陈卓, 等. 基于卷积神经网络的目标检测综述[J]. 科技经济导刊, 2020, 28(27): 18-20
LI Tong, RUAN Shifeng, CHEN Zhuo, et al. Overview of target detection based on convolutional neural networks[J]. Technology and economic guide, 2020, 28(27): 18-20
[12] HEI Law, JIA Deng. Cornernet: detecting objects as paired keypoints [C].//Proceedings of the European Conference on Computer Vision (ECCV). Munich, Germany, 2018: 765-781.
[13] ZHU C, HE Y, SAVVIDES M. Feature selective anchor-free module for single-shot object detection [C]. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, USA,2019: 840-849.
[14] ZHOU Xingyi, ZHOU Jiacheng, KR?HENBüHL P. Bottom-up object detection by grouping extreme and center points[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA, 2019: 850-859.
[15] TIAN Z, SHEN C, CHEN H, et al. FCOS: fully convolutional one-stage object detection [C].//2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul, Korea (South), 2019: 9626-9635.
[16] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. Yolov4: Optimal speed and accuracy of object detection[EB/OL]. (2020-04-22)[2021-05-01]. https://arxiv.org/pdf/2004.10934.pdf.
[17] 曹田, 李勃, 任福继, 等. 快速的圆投影图像匹配算法[J]. 智能系统学报, 2020, 15(1): 84-91
CAO Tian, LI Bo, REN Fuji, et al. Fast image matching algorithm based on circular projection[J]. CAAI transactions on intelligent systems, 2020, 15(1): 84-91
[18] 吴清辉. 基于改进SURF特征点的模板匹配算法[J]. 机电工程技术, 2021, 50(6): 208-211
WU Qinghui. Template matching algorithm based on improved SURF feature points[J]. Mechanical & electrical engineering technology, 2021, 50(6): 208-211
[19] 江苏蓬, 向伟, 刘云鹏, 等. 采用多特征共生矩阵的模板匹配[J]. 光学 精密工程, 2021, 29(6): 1459-1467
JIANG Supeng, XIANG Wei, LIU Yunpeng, et al. Template matching algorithm with multi-feature co-occurrence matrix[J]. Optics and precision engineering, 2021, 29(6): 1459-1467
[20] 王丽芳, 吕建平. 小波变换和Canny算子相结合的图像边缘检测算法[J]. 计算机与数字工程, 2014, 42(8): 1480-1483
WANG Lifang, LV Jianping. Image segmentation method based on wavelet transform and Canny operator[J]. Computer and digital engineering, 2014, 42(8): 1480-1483
[21] 张月圆, 曾庆化, 刘建业, 等. 基于Canny的改进图像边缘检测算法[J]. 导航与控制, 2019, 18(1): 84-90
ZHANG Yueyuan, ZENG Qinghua, LIU Jianye, et al. An Improved image edge detection algorithm based on Canny algorithm[J]. Navigation and control, 2019, 18(1): 84-90
[22] 杨福嘉, 郑丽颖. 基于SIFT的新特征提取匹配算法[J]. 应用科技, 2019, 46(2): 94-97, 103
YANG Fujia, ZHENG Liying. New feature extraction matching algorithm based on SIFT[J]. Applied science and technology, 2019, 46(2): 94-97, 103
[23] DAVIS B J, KASZETA R W, CHAMBERS R D, et al. Machine vision tracking of carrier-deck assets for improved launch safety[C]. Proceedings of Signal Processing, Sensor Fusion, and Target Recognition. Baltimore, United States, 2013: 1-11.
[24] 丁科, 谭营. GPU 通用计算及其在计算智能领域的应用[J]. 智能系统学报, 2015, 10(1): 1-11
DING Ke, TAN Ying. A review on general purpose computing on GPUs and its applications in computation-al intelligence[J]. CAAI transactions on intelligent sys-tems, 2015, 10(1): 1-11
[25] 张毅, 沙建松. 基于图优化的移动机器人视觉SLAM[J]. 智能系统学报, 2018, 13(2): 290-295
ZHANG Yi, SHA Jiansong. Visual-SLAM for mobile robot based on graph optimization[J]. CAAI transactions on intelligent systems, 2018, 13(2): 290-295
[26] 李占旗, 高继东, 彭凯, 等. 基于PnP算法的前方车辆测距方法[J]. 国外电子测量技术, 2020, 39(12): 104-108
LI Zhanqi, GAO Jidong, PENG Kai, et al. Method of measurement vehicle distance based on PnP[J]. Foreign electronic measurement technology, 2020, 39(12): 104-108
- 相似文献/References:
-
[1]田国会,吉艳青,李晓磊.家庭智能空间下基于场景的人的行为理解[J].智能系统学报,2010,5(1):57.
TIAN Guo-hui,JI Yan-qing,LI Xiao-lei.Human behaviors understanding based on scene knowledge in home intelligent space[J].CAAI Transactions on Intelligent Systems,2010,5():57.
[2]梁义辉,战强.一种面向无线图像传输的视觉平台[J].智能系统学报,2016,11(5):608.[doi:10.11992/tis.201512014]
LIANG Yihui,ZHAN Qiang.A visual platform for wireless image transmission[J].CAAI Transactions on Intelligent Systems,2016,11():608.[doi:10.11992/tis.201512014]
[3]李霞丽,吴立成,樊艳明.易于硬件实现的压缩感知观测矩阵的研究与构造[J].智能系统学报,2017,12(3):279.[doi:10.11992/tis.201606037]
LI Xiali,WU Licheng,FAN Yanming.Study and construction of a compressed sensing measurement matrix that is easy to implement in hardware[J].CAAI Transactions on Intelligent Systems,2017,12():279.[doi:10.11992/tis.201606037]
[4]郭晓峰,王耀南,周显恩,等.中国象棋机器人棋子定位与识别方法[J].智能系统学报,2018,13(4):517.[doi:10.11992/tis.201709020]
GUO Xiaofeng,WANG Yaonan,ZHOU Xianen,et al.Chess-piece localization and recognition method for Chinese chess robot[J].CAAI Transactions on Intelligent Systems,2018,13():517.[doi:10.11992/tis.201709020]
[5]安果维,王耀南,周显恩,等.基于显著性检测的双目测距系统[J].智能系统学报,2018,13(6):913.[doi:10.11992/tis.201712005]
AN Guowei,WANG Yaonan,ZHOU Xianen,et al.Binocular distance measurement system based on saliency detection[J].CAAI Transactions on Intelligent Systems,2018,13():913.[doi:10.11992/tis.201712005]
[6]张智,毕晓君.基于风格转换的无监督聚类行人重识别[J].智能系统学报,2021,16(1):48.[doi:10.11992/tis.202012014]
ZHANG Zhi,BI Xiaojun.Clustering approach based on style transfer for unsupervised person re-identification[J].CAAI Transactions on Intelligent Systems,2021,16():48.[doi:10.11992/tis.202012014]
[7]赵立明,龙大周,徐晓东,等.工业机器人加工轨迹双目3D激光扫描成像修正方法[J].智能系统学报,2021,16(4):690.[doi:10.11992/tis.202008008]
ZHAO Liming,LONG Dazhou,XU Xiaodong,et al.Binocular 3D laser scanning imaging-based industrial robot machining trajectory correction method[J].CAAI Transactions on Intelligent Systems,2021,16():690.[doi:10.11992/tis.202008008]
[8]谢家阳,王行健,史治国,等.动态云台摄像机无人机检测与跟踪算法[J].智能系统学报,2021,16(5):858.[doi:10.11992/tis.202103032]
XIE Jiayang,WANG Xingjian,SHI Zhiguo,et al.Drone detection and tracking in dynamic pan-tilt-zoom cameras[J].CAAI Transactions on Intelligent Systems,2021,16():858.[doi:10.11992/tis.202103032]
[9]王凤随,陈金刚,王启胜,等.自适应上下文特征的多尺度目标检测算法[J].智能系统学报,2022,17(2):276.[doi:10.11992/tis.202101029]
WANG Fengsui,CHEN Jingang,WANG Qisheng,et al.Multi-scale target detection algorithm based on adaptive context features[J].CAAI Transactions on Intelligent Systems,2022,17():276.[doi:10.11992/tis.202101029]
备注/Memo
收稿日期:2021-03-09。
基金项目:国家自然科学基金项目(61803116)；船舶态势智能感知系统研制项目(MC-201920-X01)
作者简介:朱齐丹，教授，博士生导师，中国自动化学会应用委员会委员，国家绕月探测科学应用专家委员会专家，主要研究方向为智能机器人技术及应用、智能控制系统设计、图像处理与模式识别。主持国家自然科学基金项目、国防973项目、工信部高技木船舶专项项目、科工局国防基础研究重点项目、科技部国际合作项目、海军预研、科研、型号项目等50余项。获国家科技进步二等奖1项、国防科技进步一等奖3项、军队科技进步一等奖1项、黑龙江省科技进步二等奖3项。获发明专利授权20项、软件著作权5项，出版专著4部，发表学术论文200余篇;李小铜，硕士研究生，主要研究方向为图像处理、机器视觉、深度学习;郑天昊，硕士研究生，主要研究方向为计算机视觉、深度学习、机械臂、并行编程
通讯作者:朱齐丹.E-mail:zhuqidan@hrbeu.edu.cn
更新日期/Last Update:
2021-12-25