MmNet: Identifying Mikania micrantha Kunth in the wild via a deep Convolutional Neural Network |
| |
| Authors: | QIAO Xi LI Yan-zhou SU Guang-yuan TIAN Hong-kun ZHANG Shuo SUN Zhong-yu YANG Long WAN Fang-hao QIAN Wan-qiang |
| |
| Affiliation: | 1. Agricultural Genomics Institute at Shenzhen, Chinese Academy of Agricultural Sciences, Shenzhen 518120, P.R.China;2. Key Laboratory of Integrated Pest Management on Crops in South China, Ministry of Agriculture and Rural Affairs/South China Agricultural University, Guangzhou 510642, P.R.China;3. College of Mechanical Engineering, Guangxi University, Nanning 530004, P.R.China;4. Shaanxi Agricultural Machinery Appraisal Station, Xi’an 710065, P.R.China;5. College of Mechanical and Electronic Engineering, Northwest A&F University, Yangling 712100, P.R.China;6. Guangzhou Institude of Geography, Guangdong Academy of Sciences, Guangzhou 510070, P.R.China |
| |
| Abstract: | Mikania micrantha Kunth is an invasive alien weed and known as a plant killer around the world. Accurately and rapidly identifying M. micrantha in the wild is important for monitoring its growth status, as this helps management officials to take the necessary steps to devise a comprehensive strategy to control the invasive weed in the identified area. However, this approach still mainly depends on satellite remote sensing and manual inspection. The cost is high and the accuracy rate and efficiency are low. We acquired color images of the monitoring area in the wild environment using an Unmanned Aerial Vehicle(UAV) and proposed a novel network-MmNet-based on a deep Convolutional Neural Network(CNN) to identify M. micrantha in the images. The network consists of AlexNet Local Response Normalization(LRN), along with the GoogLeNet and continuous convolution of VGG inception models. After training and testing, the identification of 400 testing samples by MmNet is very good, with accuracy of 94.50% and time cost of 10.369 s. Moreover, in quantitative comparative analysis, the proposed MmNet not only has high accuracy and efficiency but also simple construction and outstanding repeatability. Compared with recently popular CNNs, MmNet is more suitable for the identification of M. micrantha in the wild. However, to meet the challenge of wild environments, more M. micrantha images need to be acquired for MmNet training. In addition, the classification labels need to be sorted in more detail. Altogether, this research provides some theoretical and scientific basis for the development of intelligent monitoring and early warning systems for M. micrantha and other invasive species. |
| |
| Keywords: | invasive alien plant image processing deep learning |
| 本文献已被 CNKI ScienceDirect 等数据库收录！ |
| 点击此处可从《农业科学学报(英文版)》浏览原始摘要信息 |
|
点击此处可从《农业科学学报(英文版)》下载全文 |
|
