Tree Detection Algorithm Based on Embedded YOLO Lightweight Network

doi:10.1007/s12204-022-2451-4

Abstract

Abstract: To avoid colliding with trees during its operation, a lawn mower robot must detect the trees. Existing tree detection methods suffer from low detection accuracy (missed detection) and the lack of a lightweight model. In this study, a dataset of trees was constructed on the basis of a real lawn environment. According to the theory of channel incremental depthwise convolution and residual suppression, the Embedded-A module is proposed, which expands the depth of the feature map twice to form a residual structure to improve the lightweight degree of the model. According to residual fusion theory, the Embedded-B module is proposed, which improves the accuracy of feature-map downsampling by depthwise convolution and pooling fusion. The Embedded YOLO object detection network is formed by stacking the embedded modules and the fusion of feature maps of different resolutions. Experimental results on the testing set show that the Embedded YOLO tree detection algorithm has 84.17% and 69.91% average precision values respectively for trunk and spherical tree, and 77.04% mean average precision value. The number of convolution parameters is 1.78 × 106, and the calculation amount is 3.85 billion float operations per second. The size of weight file is 7.11 MB, and the detection speed can reach 179 frame/s. This study provides a theoretical basis for the lightweight application of the object detection algorithm based on deep learning for lawn mower robots.

Key words: Embedded YOLO algorithm, lightweight model, machine vision, tree detection, mowing robot

摘要： 草坪割草机器人在工作时需要避免与树木发生碰撞，因此必须检测到树木。现有的树木检测方法存在检测精度低（漏检）和缺乏轻量级模型的问题。本研究基于真实的草坪环境构建了一个树木数据集。根据通道增量深度卷积和残差抑制理论，提出了Embedded-A模块，该模块将特征图的深度扩展两倍，形成残差结构，以提高模型的轻量级程度。根据残差融合理论，提出了Embedded-B模块，该模块通过深度卷积和池化融合提高了特征图下采样的准确性。通过堆叠嵌入模块和不同分辨率特征图的融合，形成了Embedded YOLO目标检测网络。测试集上的实验结果表明，Embedded YOLO树木检测算法对树干和球形树的平均精度值分别为84.17%和69.91%，平均精度均值为77.04%。卷积参数数量为1.78×106，计算量为38.5亿次浮点运算。权重文件大小为7.11MB，检测速度可达179帧/秒。本研究为草坪割草机器人基于深度学习的目标检测算法的轻量级应用提供了理论依据。

关键词: 嵌入式YOLO算法，轻量级模型，机器视觉，树木检测，割草机器人

CLC Number:

TP391.4

LV Feng(吕峰), WANG Xinyan^* (王新彦), LI Lei(李磊), JIANG Quan(江泉), YI Zhengyang(易政洋). Tree Detection Algorithm Based on Embedded YOLO Lightweight Network[J]. J Shanghai Jiaotong Univ Sci, 2024, 29(3): 518-527.

References

[1] LECUN Y, BENGIO Y, HINTON G. Deep learning [J]. Nature, 2015, 521(7553): 436-444.
[2] HUANG J, RATHOD V, SUN C, et al. Speed/accuracy trade-offs for modern convolutional object detectors [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE, 2017: 3296-3297.
[3] GIRSHICK R, DONAHUE J, DARRELL T, et al. Region-based convolutional networks for accurate object detection and segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(1): 142-158.
[4] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation [C]//2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH, USA: IEEE, 2014: 580-587.
[5] GIRSHICK R. Fast R-CNN [C]//2015 IEEE International Conference on Computer Vision. Santiago, Chile: IEEE, 2015: 1440-1448.
[6] REN S Q, HE K M, GIRSHICK R, et al. Faster RCNN: Towards real-time object detection with region proposal networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.
[7] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector [M]//Computer vision-ECCV 2016. Cham: Springer, 2016: 21-37.
[8] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: Unified, real-time object detection [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA: IEEE, 2016: 779-788.
[9] REDMON J, FARHADI A. YOLO9000: better, faster, stronger [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE, 2017: 6517-6525.
[10] REDMON J, FARHADI A. Yolov3: An incremental improvement [EB/OL]. (2018-04-08). https://arxiv.org/abs/1804.02767.
[11] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. Yolov4: Optimal speed and accuracy of object detection [EB/OL]. (2020-04-23). https://arxiv.org/abs/2004.10934.
[12] HOWARD A G, ZHU M, CHEN B, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications [EB/OL]. (2017-04-17). https://arxiv.org/abs/1704.04861.
[13] SANDLER M, HOWARD A, ZHU M L, et al. MobileNetV2: Inverted residuals and linear bottlenecks [C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA: IEEE, 2018: 4510-4520.
[14] HOWARD A, SANDLER M, CHEN B, et al. Searching for MobileNetV3 [C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV ). Seoul, Korea: IEEE, 2019: 1314-1324.
[15] YARAK K, WITAYANGKURN A, KRITIYUTANONT K, et al. Oil palm tree detection and health classification on high-resolution imagery using deep learning [J]. Agriculture, 2021, 11(2): 183.
[16] ITAKURA K, HOSOI F. Automatic tree detection from three-dimensional images reconstructed from 360? spherical camera using YOLO v2 [J]. Remote Sensing, 2020, 12(6): 988.
[17] WEINSTEIN B G, MARCONI S, BOHLMAN S A, et al. Cross-site learning in deep learning RGB tree crown detection [J]. Ecological Informatics, 2020, 56: 101061.
[18] ITAKURA K, HOSOI F. Automated tree detection from 3D lidar images using image processing and machine learning [J]. Applied Optics, 2019, 58(14): 3807-3811.
[19] MAJEED Y, ZHANG J, ZHANG X, et al. Deep learning based segmentation for automated training of apple trees on trellis wires [J]. Computers and Electronics in Agriculture, 2020, 170: 105277.
[20] XI Z X, HOPKINSON C, ROOD S B, et al. See the forest and the trees: Effective machine and deep learning algorithms for wood filtering and tree species classification from terrestrial laser scanning [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 168: 1-16.