| 基于树莓派及深度学习的柑橘识别系统设计 |
| |
| 引用本文： | 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. |
| |
| 作者姓名： | 陈品岚 张小花 朱立学 李浩林 |
| |
| 作者单位： | 1. 仲恺农业工程学院机电工程学院，广州市，510225；
2. 仲恺农业工程学院自动化学院，广州市，510225
|
| |
| 基金项目： | 广东省普通高校特色创新类项目(2019KTSCX064)；广东省农产品保鲜物流共性关键技术研发创新团队(2020KJ145) |
| |
| 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 |
Citrus recognition system design based on Raspberry Pi and deep learning |
| |
| 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. |
| |
| Keywords: | Raspberry Pi citrus recognition convolution neural network TensorFlow |
|
| 点击此处可从《中国农机化学报》浏览原始摘要信息 |
| 点击此处可从《中国农机化学报》下载免费的PDF全文 |
