期刊
COMPUTERS AND ELECTRONICS IN AGRICULTURE
卷 185, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.compag.2021.106134
关键词
Fine-grained crop classification; Deep-learning; Internet of things; Multi-stream cross-level fusion; Precision agriculture
资金
- National Natural Science Foundation of China [62006008]
- National Key Research and Development Program of China [2020YFC1606801, 2017YFC1600605]
- Beijing Municipal Education Commission [KM201910011010]
- Beijing Excellent Talent Training Support Project for Young Top-Notch Team [2018000026833TD01]
- Humanities & Social Sciences of Ministry of Education [19YJC790028]
The MCF-Net model proposed in this paper combines the requirements for identifying different crop species from actual farmland scenes, and utilizes the cross-stage partial network (CSPNet) as the backbone module, three parallel sub-networks, and a cross-level fusion module. By leveraging massive fine-granulometric information, MCF-Net has superior representation ability for distinguishing interclass discrepancies and tolerating intra-class variances.
Precision farming aims to optimizing the crop production process and managing sustainable supply chain practices as more efficient and reasonable as possible. Recently, various advanced technologies, such as deeplearning and internet of things (IoT), have achieved remarkable intelligence progress in realistic agricultural conditions. However, crops species recognition can be considered as fine-grained visual classification (FGVC) problem, suffering the low inter-class discrepancy and high intra-class variances from the subordinate categories, which is more challenging than common basic-level category classification depended on traditional deep neural networks (DNNs). This paper presents a fine-grained visual recognition model named as MCF-Net to classifying different crop species in practical farmland scenes. Proposed MCF-Net is consisted of cross stage partial network (CSPNet) as backbone module, three parallel sub-networks, and cross-level fusion module. With multi-stream hybrid architecture utilizing massive fine-granulometric information, MCF-Net obtains preferable representation ability for distinguishing interclass discrepancy and tolerating intra-class variances. In addition, the end-toend implementation of MCF-Net is optimized by cross-level fusion strategy to accurately identify different crop categories. Several experiments on in-field CropDeepv2 datasets demonstrate that our method favorably against the state-of-the-art methods. The recognition accuracy and F1-score of MCF-Net achieves very competitive results up to 90.6% and 0.962 separately, both of which outperforming contrasted models indicate better recognition accuracy and model stability of our method. Moreover, the overall parameters of MCF-Net are only 807 MByte with achieving a good balance between model's performance and complexity. It is acceptable and suitable to the implementation of IoT platforms in precision agricultural practices.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据