| 基于多流高斯概率融合网络的病虫害细粒度识别 |
| |
| 引用本文： | 孔建磊,金学波,陶治,王小艺,林森.基于多流高斯概率融合网络的病虫害细粒度识别[J].农业工程学报,2020,36(13):148-157. |
| |
| 作者姓名： | 孔建磊 金学波 陶治 王小艺 林森 |
| |
| 作者单位： | 北京工商大学人工智能学院,北京 100048;国家环境保护食品链污染防治重点实验室,北京 100048;中国轻工业工业互联网与大数据重点实验室,北京 100048;北京工商大学人工智能学院,北京 100048;中国轻工业工业互联网与大数据重点实验室,北京 100048;北京农业智能装备技术研究中心,北京 100097 |
| |
| 基金项目： | 国家重点研发计划(2017YFC1600605)；北京市教育委员会科技计划一般项目(KM201910011010)；国家自然基金项目(61673002, 61903009 ); |
| |
| 摘 要： | 为解决由于现有深度迁移学习无法有效匹配实际农业场景部署应用,而导致大规模、多类别、细粒度的病虫害辨识准确低、泛化鲁棒差等问题,该研究利用农业物联网中多种设备终端获取12.2万张181类病虫害图像,并提出了基于多流概率融合网络MPFN(Multi-stream Gaussian Probability Fusion Network)的病虫害细粒度识别模型。该模型设计多流深度网络并行的细粒度特征提取层,挖掘可区分细微差异的不同级别局部特征表达,经过局部描述特征聚合层和高斯概率融合层的整合优化,发挥多模型融合信息互补及置信耦合的优势,既可以有效区分不同类病虫害的种间微小差异,又可容忍同类病虫害种内明显差异干扰。对比试验表明,该研究MPFN模型对各类病虫害的平均识别准确率达到93.18%,性能优于其他粗粒度及细粒度深度学习方法;而平均单张处理时间为61ms,能够满足农业生产实践中物联网各终端病虫害细粒度图像识别需求,可为智能化病虫害预警防控提供技术应用参考,进而为保障农作物产量和品质安全提供基础。
|
| 关 键 词： | 农业 图像识别 病虫害 深度神经网络 特征聚合 高斯概率融合 |
| 收稿时间： | 2020/3/4 0:00:00 |
| 修稿时间： | 2020/4/2 0:00:00 |
Fine-grained recognition of diseases and pests based on multi-stream Gaussian probability fusion network |
| |
| Kong Jianlei,Jin Xuebo,Tao Zhi,Wang Xiaoyi,Lin Sen.Fine-grained recognition of diseases and pests based on multi-stream Gaussian probability fusion network[J].Transactions of the Chinese Society of Agricultural Engineering,2020,36(13):148-157. |
| |
| Authors: | Kong Jianlei Jin Xuebo Tao Zhi Wang Xiaoyi Lin Sen |
| |
| Institution: | 1. Artificial Intelligence Academy, Beijing Technology and Business University , Beijing 100048, China; 2. National Key Laboratory of Environmental Protection Food Chain Pollution Prevention, Beijing 100048, China; 3. China Light Key laboratory of Industry Internet and Big Data, Beijing 100048, China;; 3. China Light Key laboratory of Industry Internet and Big Data, Beijing 100048, China; 4. Beijing Research Center for Intelligent Agricultural Equipment, Beijing 100097, China; |
| |
| Abstract: | Accurate identification of diseases and insect pests has been the key link to the yield, quality and safety of crops in modern agriculture. However, the same category of diseases and insect pests showed obvious differences in intra-class representation and slight similarities in inter-class representation of various diseases, due to the influence of environmental conditions, disease cycle and damaged tissues. At present, the traditional deep transfer learning methods have been difficult to cope with large-scale, multi-class fine-grained identification of pests and diseases, particularly unsuitable to the practice in complicated scenes. This paper aims to apply multiple source cameras in agricultural Internet of Things (IoT) and different intelligent precision equipment, including picking robots and smart phones, to capture high resolution 122,000 images of insect pests and diseases, covering a total of 181 fine-grained categories, including 49 types pests and 77 types diseases on different plant parts of different crops. A fine-grained recognition model was then proposed for pests and diseases based on the Multi-Stream Gaussian Probability Fusion Network (MPFN). In detail, a data-augmented method was first employed to enlarge the dataset, and then to pretrain the basic VGG19 and ResNet networks on high-quality images, in order to learn common and domain knowledge, as well fine-tuning with professional skill. Next, the refined multiple deep learning networks, including Fast-MPN and NTS-Net with transfer learning, were applied to design a multi-stream feature extractor, utilizing the mixture-granularity information to exploit high-dimensionality features, thereby to distinguish interclass discrepancy and tolerate intra-class variances. Finally, an integrated optimization was developed combining the NetVLAD feature aggregation layer with the gaussian probability fusion layer, in order to fuse various components model with Gaussian distribution as a unified probability representation for the ultimate fine-grained recognition. The input of this module was the various features of multi-models, whereas, the output was the fused classification probability. The end-to-end implementation of framework included an inner loop about the expectation maximization algorithm within an outer loop with the gradient back-propagation optimization of the whole network, indicating multi-model fusion information complementation and confidence for the overall model. The experimental results demonstrated that the MPFN model presented the excellent performance in the average recognition accuracy rate of 93.18% for a total of 181 classes of pests and diseases, indicating 5.6% better than that of the coarse-grained and fine-grained deep learning methods. In terms of test time, the average processing time of the MPFN was 61ms, indicating the basic needs of fine-grained image recognition of pests and diseases at the terminals of the IoT and intelligent equipment. In the contradistinctive analysis, training loss curves and various sub-categories identification showed that the feature aggregation fusion and Gaussian probability fusion can greatly enhance the efficiency of model with the training speed, recognition accuracy and generalized robustness for fine-grained identification of crop pests and diseases in practical scenarios. Therefore, this work can provide a technical application reference for the intelligent recognition of pests and diseases in agricultural production. In the follow-up study, more images will be taken under natural conditions to develop a more robust MPFN model deployed on actual IoTs or equipment for the pre-warning, prevention, and control of crop pests and diseases in modern agriculture. |
| |
| Keywords: | agriculture image recognition diseases and pests deep neural network feature aggregation Gaussian probability fusion |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《农业工程学报》浏览原始摘要信息 |
| 点击此处可从《农业工程学报》下载免费的PDF全文 |
|
