基于树莓派及深度学习的柑橘识别系统设计

doi:10.13733/j.jcam.issn.20955553.2022.09.018

摘要/Abstract

摘要： 随着现代农业技术的发展，柑橘的生产与采收自动化是必然趋势，而柑橘的目标识别是实现采摘自动化的重要环节。提出一种基于树莓派的柑橘识别系统，以树莓派作为软件程序平台，应用Python语言构建卷积神经网络模型，利用TensorFlow平台实现柑橘的识别。通过机器视觉采集柑橘树的相关数据，结合深度学习算法，对柑橘树上的柑橘进行识别及计数。经过测试，识别正确率约为92.4%。此外，利用GPS模块进行识别位置定位，确定区域内的柑橘密度及使用光照强度传感器测量环境光照强度对图像进行直方图均衡化处理，降低光照对柑橘识别的影响。

关键词: 树莓派, 柑橘识别, 卷积神经网络, TensorFlow

Abstract: China is a big fruit producer in the world. With the development of modern agricultural technology, citrus production and harvesting automation is an inevitable trend, and citrus target recognition is an important link to realize harvesting automation. This paper proposes a citrus recognition system based on Raspberry Pi, which uses Raspberry Pi as the software platform. The convolutional neural network model was constructed by Python language, and the citrus recognition was realized by Tensorflow platform. The relevant data of the citrus trees were collected by machine vision, and the citrus on the citrus tree was recognized and counted by combining with the deep learning algorithm. After testing, the recognition accuracy was about 92.4%. In addition, the GPS module was used to locate the recognition position, determine the citrus density in the area, measure the ambient light intensity with the light intensity sensor, and process the image histogram equalization to reduce the impact of light on Citrus recognition.

Key words: Raspberry Pi, citrus recognition, convolution neural network, TensorFlow

中图分类号:

S66： TP391.4

陈品岚, 张小花, 朱立学, 李浩林. 基于树莓派及深度学习的柑橘识别系统设计[J]. 中国农机化学报, 2022, 43(9): 131-136.

Chen Pinlan, Zhang Xiaohua, Zhu Lixue, Li Haolin. . Citrus recognition system design based on Raspberry Pi and deep learning[J]. Journal of Chinese Agricultural Mechanization, 2022, 43(9): 131-136.

参考文献

［1］　
张放. 2019年我国主要水果生产变化简析［J］. 中国果业信息, 2021, 38(3): 23-33.

［2］　
Kurtulmus F, Lee W S, Vardar A. Green citrus detection using ‘eigenfruit’, color and circular Gabor texture features under natural outdoor conditions ［J］. Computers and Electronics in Agriculture, 2011, 78(2): 140-149.

［3］　
Zhang J, He L, Karkee M, et al. Branch detection with apple trees trained in fruiting wall architecture using stereo vision and regionsconvolutional neural network (R-CNN) ［C］. American Society of Agricultural and Biological Engineers, 2017(1).

［4］　
岳有军, 田博凯, 王红君, 等. 基于改进Mask RCNN的复杂环境下苹果检测研究［J］. 中国农机化学报, 2019, 40(10): 128-134.

Yue Youjun, Tian Bokai, Wang Hongijun, et al. Research on apple detection in complex environment based on improved Mask RCNN ［J］. Journal of Chinese Agricultural Mechanization, 2019, 40(10): 128-134.

［5］　
武星, 齐泽宇, 王龙军, 等. 基于轻量化YOLOv3卷积神经网络的苹果检测方法［J］. 农业机械学报, 2020, 51(8): 17-25.

Wu Xing, Qi Zeyu, Wang Longjun, et al. Apple detection method based on lightYOLOv3 convolutional neural network ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(8): 17-25.

［6］　
赵德安, 吴任迪, 刘晓洋, 等. 基于YOLO深度卷积神经网络的复杂背景下机器人采摘苹果定位［J］. 农业工程学报, 2019, 35(3): 164-173.

Zhao Dean, Wu Rendi, Liu Xiaoyang, et al. Apple positioning based on YOLO deep convolutional neural network for picking robot in complex background ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(3): 164 -173.

［7］　
彭红星, 黄博, 邵园园, 等. 自然环境下多类水果采摘目标识别的通用改进SSD模型［J］. 农业工程学报, 2018, 34(16): 155-162.

Peng Hongxing, Huang Bo, Shao Yuanyuan, et al. General improved SSD model for picking object recognition of multiple fruits in natural environment ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(16): 155-162.

［8］　
毕松, 高峰, 陈俊文, 等. 基于深度卷积神经网络的柑橘目标识别方法［J］. 农业机械学报, 2019, 50(5): 181-186.

Bi Song, Gao Feng, Chen Junwen, et al. Detection method of citrus based on deep convolution neural network ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50(5): 181-186.

［9］　
牛犇, 滕运江. 基于树莓派的实时人脸表情识别［J］. 电子信息与软件工程, 2020(1): 135-136.

［10］　
江美玲, 章杰. 基于树莓派的服装识别系统设计［J］. 传感器与微系统, 2020, 40(1): 98-100, 103.

Jiang Meiling, Zhang Jie. Design of clothing identification system based on Raspberry Pi ［J］. Transducer and Microsystem Technologies, 2020, 40(1): 98-100, 103.

［11］　
郭泽方. 基于改进SSD深度学习模型的柑橘实时识别研究［D］. 衡阳: 南华大学, 2020.

Guo Zefang. Realtime citrus detection based on improved SSD deep learning model ［D］. Hengyang: University of South China, 2020.

［12］　
马传金. 基于深度学习的无人机遥感柑橘果实识别［D］. 武汉: 华中师范大学, 2020.

Ma Chuanjin. UAVs remote sensing citrus recognition based on deep learning ［D］. Wuhan: Central China Normal University, 2020.

[1]	高文强, , 肖志云, . 基于Atrous-CDAE-1DCNN的紫丁香高光谱数据的叶绿素含量反演[J]. 中国农机化学报, 2022, 43(7): 158-166.
[2]	史方青, 王虎林, 黄华. 基于卷积神经网络的马铃薯芽眼检测识别研究[J]. 中国农机化学报, 2022, 43(6): 159-165.
[3]	赵腾飞, 胡国玉, 周建平, , 刘广, 陈旭东, 董娅兰. 卷积神经网络算法在核桃仁分类中的研究[J]. 中国农机化学报, 2022, 43(6): 181-189.
[4]	曹金凤, 沈大港, 郭继鸿, 刘鹏, 李策, 兰添贺. 基于CNN和SVM分类优化的大蒜鳞芽朝向识别研究[J]. 中国农机化学报, 2022, 43(5): 134-139.
[5]	雷雪梅, 张光强, 姚旗, 刘伟渭, 邱帅. 基于卷积神经网络的农机图像自动识别研究[J]. 中国农机化学报, 2022, 43(5): 140-147.
[6]	高文强, , 肖志云, . 多尺度特征融合1D—CNN的马铃薯植株高光谱数据地物分类和缺素识别#br#[J]. 中国农机化学报, 2022, 43(3): 111-119.
[7]	董萍, 卫梦华, 时雷, 郭伟. 迁移学习在玉米叶片病害识别中的研究与应用[J]. 中国农机化学报, 2022, 43(3): 146-152.
[8]	魏晨, 国树金, 荆茂焱, 朱鸿瑞, 赵颖. 美国白蛾幼虫网幕图像识别算法及其视觉伺服系统研究[J]. 中国农机化学报, 2022, 43(11): 62-68.
[9]	陈继清, 韦德鹏, 龙腾, 罗天, 王桦彬. 基于卷积神经网络的害虫分类[J]. 中国农机化学报, 2022, 43(11): 188-194.
[10]	郭文娟, 冯全, 李相周. 基于农作物病害检测与识别的卷积神经网络模型研究进展[J]. 中国农机化学报, 2022, 43(10): 157-166.
[11]	石洪康, 肖文福, 黄亮, 胡丛武, 胡光荣, 张剑飞. 基于卷积神经网络的家蚕病害识别研究[J]. 中国农机化学报, 2022, 43(1): 150-.
[12]	王鹤树, 曹丽英, . 基于全卷积神经网络的植物叶片自动分割及表型解析[J]. 中国农机化学报, 2021, 42(8): 161-168.
[13]	陈强;戴军;. 农机驾驶人员疲劳驾驶行为检测研究[J]. 中国农机化学报, 2021, 42(5): 148-152.
[14]	闫建伟;张乐伟;赵源;张富贵;. 改进RetinaNet的刺梨果实图像识别[J]. 中国农机化学报, 2021, 42(3): 78-83.
[15]	谢仕烁;黄伟锋;朱立学;杨尘宇;张世昂;付根平;. 基于改进Floodfill算法的田垄视觉导航系统[J]. 中国农机化学报, 2021, 42(3): 182-188.