A Real-time Low-cost Artificial Intelligence System for Autonomous Spraying in Palm Plantations

In precision crop protection, (target-orientated) object detection in image processing can help navigate Unmanned Aerial Vehicles (UAV, crop protection drones) to the right place to apply the pesticide. Unnecessary application of non-target areas could be avoided. Deep learning algorithms dominantly use in modern computer vision tasks which require high computing time, memory footprint, and power consumption. Based on the Edge Artificial Intelligence, we investigate the main three paths that lead to dealing with this problem, including hardware accelerators, efficient algorithms, and model compression. Finally, we integrate them and propose a solution based on a light deep neural network (DNN), called Ag-YOLO, which can make the crop protection UAV have the ability to target detection and autonomous operation. This solution is restricted in size, cost, flexible, fast, and energy-effective. The hardware is only 18 grams in weight and 1.5 watts in energy consumption, and the developed DNN model needs only 838 kilobytes of disc space. We tested the developed hardware and software in comparison to the tiny version of the state-of-art YOLOv3 framework, known as YOLOv3-Tiny to detect individual palm in a plantation. An average F1 score of 0.9205 at the speed of 36.5 frames per second (in comparison to similar accuracy at 18 frames per second and 8.66 megabytes of the YOLOv3-Tiny algorithm) was reached. This developed detection system is easily plugged into any machines already purchased as long as the machines have USB ports and run Linux Operating System.

[1]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[3]  Junjie Yan,et al.  Quantization Mimic: Towards Very Tiny CNN for Object Detection , 2018, ECCV.

[4]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Charles X. Ling,et al.  Pelee: A Real-Time Object Detection System on Mobile Devices , 2018, NeurIPS.

[6]  Yiran Chen,et al.  Learning Structured Sparsity in Deep Neural Networks , 2016, NIPS.

[7]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[8]  Frédéric Baret,et al.  Using 3D Point Clouds Derived from UAV RGB Imagery to Describe Vineyard 3D Macro-Structure , 2017, Remote. Sens..

[9]  Giuseppe Modica,et al.  Monitoring the vegetation vigor in heterogeneous citrus and olive orchards. A multiscale object-based approach to extract trees' crowns from UAV multispectral imagery , 2020, Comput. Electron. Agric..

[10]  Joseph Redmon,et al.  YOLOv3: An Incremental Improvement , 2018, ArXiv.

[11]  Chaojun Hou,et al.  Optimization of control parameters of droplet density in citrus trees using UAVs and the Taguchi method , 2019, International Journal of Agricultural and Biological Engineering.

[12]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Hong-Yuan Mark Liao,et al.  YOLOv4: Optimal Speed and Accuracy of Object Detection , 2020, ArXiv.

[14]  Xiangyu Zhang,et al.  ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[15]  Yubin Lan,et al.  Current status and trends of plant protection UAV and its spraying technology in China , 2018 .

[16]  Pan Zhang,et al.  Droplet Distribution and control against citrus Leafminer with UAV Spraying , 2017, Int. J. Robotics Autom..

[17]  Tofael Ahamed,et al.  Development of a Recognition System for Spraying Areas from Unmanned Aerial Vehicles Using a Machine Learning Approach , 2019, Sensors.

[18]  Chao Chen,et al.  Fruit Detection and Segmentation for Apple Harvesting Using Visual Sensor in Orchards , 2019, Sensors.

[19]  Wenbin Li,et al.  A Survey of AI Accelerators for Edge Environment , 2020, WorldCIST.

[20]  Shuchang Zhou,et al.  DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients , 2016, ArXiv.

[21]  Chau Yuen,et al.  Cluster Pruning: An Efficient Filter Pruning Method for Edge AI Vision Applications , 2020, IEEE Journal of Selected Topics in Signal Processing.

[22]  Marcello Chiaberge,et al.  Real-Time Apple Detection System Using Embedded Systems With Hardware Accelerators: An Edge AI Application , 2020, IEEE Access.

[23]  Koen E. A. van de Sande,et al.  Selective Search for Object Recognition , 2013, International Journal of Computer Vision.

[24]  Pablo J. Zarco-Tejada,et al.  High-Resolution Airborne UAV Imagery to Assess Olive Tree Crown Parameters Using 3D Photo Reconstruction: Application in Breeding Trials , 2015, Remote. Sens..

[25]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[26]  Yu Tang,et al.  Effects of operation height and tree shape on droplet deposition in citrus trees using an unmanned aerial vehicle , 2018, Comput. Electron. Agric..

[27]  Wei Zhang,et al.  Design of precision variable-rate spray system for unmanned aerial vehicle using automatic control method , 2019, International Journal of Agricultural and Biological Engineering.

[28]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[29]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[30]  Cornelia Weltzien,et al.  Growth Height Determination of Tree Walls for Precise Monitoring in Apple Fruit Production Using UAV Photogrammetry , 2020, Remote. Sens..

[31]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[32]  He Xiongkui,et al.  Recent development of unmanned aerial vehicle for plant protection in East Asia , 2017 .

[33]  Hei Law,et al.  CornerNet: Detecting Objects as Paired Keypoints , 2018, ECCV.

[34]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[35]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[36]  Qi Tian,et al.  CenterNet: Keypoint Triplets for Object Detection , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[37]  Jinya Su,et al.  Experimental evaluation of UAV spraying for peach trees of different shapes: Effects of operational parameters on droplet distribution , 2020, Comput. Electron. Agric..

[38]  Greg J. Stephens,et al.  Towards Dense Object Tracking in a 2D Honeybee Hive , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[39]  Yi Li,et al.  R-FCN: Object Detection via Region-based Fully Convolutional Networks , 2016, NIPS.

[40]  Xiangyu Zhang,et al.  Channel Pruning for Accelerating Very Deep Neural Networks , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[41]  Xiangyu Zhang,et al.  ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design , 2018, ECCV.

[42]  Wenjiang Huang,et al.  Identification of banana fusarium wilt using supervised classification algorithms with UAV-based multi-spectral imagery , 2020, International Journal of Agricultural and Biological Engineering.

[43]  Ross B. Girshick,et al.  Focal Loss for Dense Object Detection , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[44]  Guipeng Chen,et al.  Automated cattle counting using Mask R-CNN in quadcopter vision system , 2020, Comput. Electron. Agric..

[45]  Yufeng Ge,et al.  Design of Plant Protection UAV Variable Spray System Based on Neural Networks , 2019, Sensors.

[46]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[47]  Forrest N. Iandola,et al.  SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size , 2016, ArXiv.

[48]  Zhaohui Zheng,et al.  Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression , 2019, AAAI.

[49]  Pei-Kuei Tsung,et al.  Techology trend of edge AI , 2018, 2018 International Symposium on VLSI Design, Automation and Test (VLSI-DAT).

[50]  Shulin Yang,et al.  The application of unmanned aircraft systems to plant protection in China , 2018, Precision Agriculture.

[51]  Juan Agüera,et al.  Spray and economics assessment of a UAV-based ultra-low-volume application in olive and citrus orchards , 2019, Precision Agriculture.

[52]  Ali Farhadi,et al.  XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks , 2016, ECCV.

[53]  Yiannis Ampatzidis,et al.  UAV-Based Remote Sensing Technique to Detect Citrus Canker Disease Utilizing Hyperspectral Imaging and Machine Learning , 2019, Remote. Sens..

[54]  Zhiqiang Shen,et al.  Learning Efficient Convolutional Networks through Network Slimming , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[55]  Р Ю Чуйков,et al.  Обнаружение транспортных средств на изображениях загородных шоссе на основе метода Single shot multibox Detector , 2017 .

[56]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.