1.中南林业科技大学机电工程学院，湖南长沙 410004
2.中南林业科技大学材料科学与工程学院，湖南长沙 410004
扫 描 看 全 文
王绍平,严永林,郝晓峰等.基于轻量化级联网络破竹机竹径测量[J].木材科学与技术,2023,37(01):99-107.
WANG Shaoping,YAN Yonglin,HAO Xiaofeng,et al.Bamboo Diameter Measurement by Bamboo-Ripping Machine based on Lightweight Cascade Network[J].Chinese Journal of Wood Science and Technology,2023,37(01):99-107.
针对现有自动破竹机测径方法通用性不强，且难以同时测量厚度的问题，采用YOLOv4-Tiny和MobileNet-SegNet组成级联网络，利用双目视觉进行测距，用最小外接圆获取外径与厚度，构建测量算法。测量系统以USB双目摄像头作为成像设备连接树莓派4B和Movidius神经计算棒，用Python编写主程序，并用OpenVINO异步模式部署模型。以不同距离、角度、竹筒规格展开测量试验。结果表明，算法最优测量距离是30~40 cm，竹筒外径测量平均相对误差为1.43%，厚度测量平均相对误差为8.76%，检测速度为7.1 FPS。本研究可为自动破竹机测径换刀系统设计提供依据。
In order to improve the current diameter measurement method of the automatic bamboo-ripping machine, which is not universal and difficult to achieve thickness measurement simultaneously, this study uses YOLOv4-Tiny and MobileNet-SegNet to form a cascade network, applies binocular vision to measure distance, and conducts the minimum circumcircle to obtain outer diameter and thickness, and constructs a measurement algorithm. The measurement system uses a USB binocular camera as an imaging device to connect Raspberry pi 4B and Movidius neural compute sticks. The main program is written in Python, and the model is deployed by OpenVINO in asynchronous mode. The measurement were carried out at different distances, angles, and bamboo tube specifications. The results show that the optimal measurement distance of the algorithm is 30~40 cm, the average relative error of bamboo outer diameter measurement is 1.43%, the average relative error of thickness measurement is 8.76%, and the detection speed is 7.1 FPS. This study provides a basis for the design of the automatic bamboo-ripping machine with a diameter measuring and tool changing system.
破竹机竹径测量YOLOv4-TinyMobileNet-SegNet异步推理
bamboo-ripping machinemeasurement of bamboo diameterYOLOv4-TinyMobileNet-SegNetasynchronous inferring
马程浩, 傅万四, 周建波, 等. 竹材破竹技术设备发展现状及未来趋势[J]. 木材加工机械, 2016, 27(5): 56-59.
MA C H, FU W S, ZHOU J B, et al. The current status and the future trend of bamboo splitting equipment[J]. Wood Processing Machinery, 2016, 27(5): 56-59.
沈冯峥, 徐康, 李琴, 等. 竹材初加工机械研究现状及发展趋势[J]. 浙江林业科技, 2019, 39(6): 105-110.
SHEN F Z, XU K, LI Q, et al. History and development of primary processing machinery for bamboo[J]. Journal of Zhejiang Forestry Science and Technology, 2019, 39(6): 105-110.
常飞虎, 周建波, 傅万四, 等. 自动进料快速对心数控自动破竹机研制与试验[J]. 中南林业科技大学学报, 2021, 41(3): 177-186.
CHANG F H, ZHOU J B, FU W S, et al. Production and test of automatic feedingfast-to-heart CNC automatic bamboo splitting machine[J]. Journal of Central South University of Forestry & Technology, 2021, 41(3): 177-186.
梁国健. 新型自动化破竹机优化设计与研究[D]. 桂林: 广西师范大学, 2019.
朱峰, 王海丰, 任洪娥. 基于Gabor变换的纹理图像分割算法及应用[J]. 森林工程, 2013, 29(5): 60-63.
ZHU F, WANG H F, REN H E. Research on texture image segmentation algorithm and its application based on Gabor wavelet transform[J]. Forest Engineering, 2013, 29(5): 60-63.
王海丰. 基于机器视觉的剖竹机加工目标检测算法研究[D]. 哈尔滨: 东北林业大学, 2015.
胡嘉沛, 李震, 黄河清, 等. 采用改进YOLOv4-Tiny模型的柑橘木虱识别[J]. 农业工程学报, 2021, 37(17): 197-203.
HU J P, LI Z, HUANG H Q, et al. Citrus psyllid detection based on improved YOLOv4-Tiny model[J]. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(17): 197-203.
Bochkovskiy A, Wang C Y, Liao H Y M. YOLOv4: optimal speed and accuracy of object detection[EB/OL]. 2020: arXiv: 2004.10934. https://arxiv.org/abs/2004.10934https://arxiv.org/abs/2004.10934
谢孟添, 刁云峰, 程文明, 等. 基于U-net和YOLOv4-tiny的锁孔中心定位算法[J]. 起重运输机械, 2021(23): 70-75.
XIE M T, DIAO Y F, CHENG W M, et al. Pinhole center positioning algorithm based on U-net and YOLOv4-tiny[J]. Hoisting and Conveying Machinery, 2021(23): 70-75.
YUN S, HAN D, CHUN S, et al. CutMix: regularization strategy to train strong classifiers with localizable features[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV). October 27 - November 2, 2019, Seoul, Korea (South). IEEE, 2020: 6022-6031.
LIN T Y, Dollár P, Girshick R, et al. Feature pyramid networks for object detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). July 21-26, 2017, Honolulu, HI, USA. IEEE, 2017: 936-944.
ZHENG Z H, WANG P, LIU W, et al. Distance-IoU loss: faster and better learning for bounding box regression[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(7): 12993-13000.
陈莉. 基于机器视觉的双摄像头测距系统的研究与实现[D]. 石家庄: 河北科技大学, 2019.
杜叶挺, 陈广华, 李建伟, 等. 基于双目视觉的原木材积自动检测系统[J]. 北京交通大学学报, 2014, 38(4): 78-82.
DU Y T, CHEN G H, LI J W, et al. Automatic detection system for log volume based on binocular vision[J]. Journal of Beijing Jiaotong University, 2014, 38(4): 78-82.
Badrinarayanan V, Kendall A, Cipolla R. SegNet: a deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12): 2481-2495.
Howard A G, ZHU M L, CHEN B, et al. MobileNets: efficient convolutional neural networks for mobile vision applications[EB/OL]. 2017: arXiv: 1704.04861. https://arxiv.org/abs/1704.04861https://arxiv.org/abs/1704.04861
张兆国, 张振东, 李加念, 等. 采用改进YoloV4模型检测复杂环境下马铃薯[J]. 农业工程学报, 2021, 37(22): 170-178.
ZHANG Z G, ZHANG Z D, LI J N, et al. Potato detection in complex environment based on improved YoloV4 model[J]. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(22): 170-178.
Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation[M]//Lecture Notes in Computer Science. Cham: Springer International Publishing, 2015: 234-241.
SI Y S, LIU G, FENG J. Location of apples in trees using stereoscopic vision[J]. Computers and Electronics in Agriculture, 2015, 112(C): 68-74.
曾令培, 张廷婷, 庞智. 基于机器视觉的番茄横径测量技术研究[J]. 机电信息, 2022(3): 68-71, 76.
颜坤. 基于双目视觉的空间非合作目标姿态测量技术研究[D]. 成都: 中国科学院大学(中国科学院光电技术研究所), 2018.
WU D, LIAO M W, ZHANG W T, et al. YOLOP: You only look once for panoptic driving perception[EB/OL]. 2021: arXiv: 2108.11250. https://arxiv.org/abs/2108.11250https://arxiv.org/abs/2108.11250
Bernabé S, González C, Fernández A, et al. Portability and acceleration of deep learning inferences to detect rapid earthquake damage from VHR remote sensing images using intel OpenVINO toolkit[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14: 6906-6915.
ZHANG Z. A flexible new technique for camera calibration[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(11): 1330-1334.
相关文章
相关作者
相关机构
京公网安备11010802024621
微信公众号