Multi-stream hybrid architecture based on cross-level fusion strategy for fine-grained crop species recognition in precision agriculture
文献类型： 外文期刊
作者： Kong, Jianlei 1 ; Wang, Hongxing 1 ; Wang, Xiaoyi 1 ; Jin, Xuebo 1 ; Fang, Xing 3 ; Lin, Seng 4 ;
作者机构： 1.Beijing Technol & Business Univ, Sch Artificial Intelligence, Beijing 100048, Peoples R China
2.Natl Key Lab Environm Protect Food Chain Pollut P, Beijing 100048, Peoples R China
3.Sichuan Agr Univ, Sch Econ, Chengdu 611130, Peoples R China
4.Beijing Res Ctr Intelligent Equipment Agr, Beijing 100097, Peoples R China
关键词： Fine-grained crop classification; Deep-learning; Internet of things; Multi-stream cross-level fusion; Precision agriculture
期刊名称：COMPUTERS AND ELECTRONICS IN AGRICULTURE （ 影响因子：5.565； 五年影响因子：5.494 ）
ISSN： 0168-1699
年卷期： 2021 年 185 卷
页码：
收录情况： SCI
摘要： 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.
- 相关文献
作者其他论文 更多>>
-
A Variational Bayesian Inference-Based En-Decoder Framework for Traffic Flow Prediction
作者：Kong, Jianlei;Fan, Xiaomeng;Jin, Xuebo;Lin, Sen;Zuo, Min
关键词：Traffic flow prediction; time-series data prediction; variational Bayesian inference; multi-head attention; deep learning; encoder-decoder
-
An Effective Pyramid Neural Network Based on Graph-Related Attentions Structure for Fine-Grained Disease and Pest Identification in Intelligent Agriculture
作者：Lin, Sen;Xiu, Yucheng;Kong, Jianlei;Yang, Chengcai;Zhao, Chunjiang;Zhao, Chunjiang
关键词：smart agriculture; pest and diseases recognition; graph convolution neural network; attention mechanism; mobile computing application
-
Microbiological predictive modeling and risk analysis based on the one-step kinetic integrated Wiener process
作者：Chen, Qian;Zhao, Zhiyao;Wang, Xiaoyi;Chen, Qian;Zhao, Zhiyao;Wang, Xiaoyi;Xiong, Ke;Shi, Ce
关键词：Food safety; Microbiological predictive modeling; Risk analysis; One-step kinetic analysis; Wiener process
-
A Graph-Related High-Order Neural Network Architecture via Feature Aggregation Enhancement for Identification Application of Diseases and Pests
作者：Kong, Jianlei;Yang, Chengcai;Xiao, Yang;Lin, Sen;Ma, Kai;Zhu, Qingzhen
关键词：
-
Deep-Learning Temporal Predictor via Bidirectional Self-Attentive Encoder-Decoder Framework for IOT-Based Environmental Sensing in Intelligent Greenhouse
作者：Jin, Xue-Bo;Zheng, Wei-Zhen;Kong, Jian-Lei;Wang, Xiao-Yi;Zuo, Min;Zhang, Qing-Chuan;Kong, Jian-Lei;Zuo, Min;Zhang, Qing-Chuan;Lin, Seng
关键词：intelligent agricultural greenhouse; environmental factor prediction; deep-learning encoder-decoder; self-attention mechanism; Internet of Things
-
Deep-Stacking Network Approach by Multisource Data Mining for Hazardous Risk Identification in IoT-Based Intelligent Food Management Systems
作者：Kong, Jianlei;Yang, Chengcai;Wang, Jianli;Wang, Xiaoyi;Zuo, Min;Jin, Xuebo;Kong, Jianlei;Zuo, Min;Lin, Sen
关键词：
-
Deep-Learning Forecasting Method for Electric Power Load via Attention-Based Encoder-Decoder with Bayesian Optimization
作者：Jin, Xue-Bo;Zheng, Wei-Zhen;Kong, Jian-Lei;Wang, Xiao-Yi;Bai, Yu-Ting;Su, Ting-Li;Jin, Xue-Bo;Kong, Jian-Lei;Wang, Xiao-Yi;Lin, Seng
关键词：electric power load prediction; deep-learning encoder-decoder framework; gated recurrent neural units; temporal attention; Bayesian optimization
