Crop pest classification based on deep convolutional neural network and transfer learning

Insect pests are one of the main factors affecting agricultural product yield. Accurate recognition of insect pests facilitates timely preventive measures to avoid economic losses. However, the existing datasets for the visual classification task mainly focus on common objects, e.g., flowers and dogs. This limits the application of powerful deep learning technology on specific domains like the agricultural field. In this paper, we collect a large-scale dataset named IP102 for insect pest recognition. Specifically, it contains more than 75, 000 images belonging to 102 categories, which exhibit a natural long-tailed distribution. In addition, we annotate about 19, 000 images with bounding boxes for object detection. The IP102 has a hierarchical taxonomy and the insect pests which mainly affect one specific agricultural product are grouped into the same upperlevel category. Furthermore, we perform several baseline experiments on the IP102 dataset, including handcrafted and deep feature based classification methods. Experimental results show that this dataset has the challenges of interand intra- class variance and data imbalance. We believe our IP102 will facilitate future research on practical insect pest control, fine-grained visual classification, and imbalanced learning fields. We make the dataset and pre-trained models publicly available at https://github.com/xpwu95/IP102.

/pdf/ip102-a-large-scale-benchmark-dataset-for-insect-pest-29grczkinw.pdf

IP102: A Large-Scale Benchmark Dataset for Insect Pest Recognition

Regarding the growth of crops, one of the important factors affecting crop yield is insect disasters. Since most insect species are extremely similar, insect detection on field crops, such as rice, soybean and other crops, is more challenging than generic object detection. Presently, distinguishing insects in crop fields mainly relies on manual classification, but this is an extremely time-consuming and expensive process. This work proposes a convolutional neural network model to solve the problem of multi-classification of crop insects. The model can make full use of the advantages of the neural network to comprehensively extract multifaceted insect features. During the regional proposal stage, the Region Proposal Network is adopted rather than a traditional selective search technique to generate a smaller number of proposal windows, which is especially important for improving prediction accuracy and accelerating computations. Experimental results show that the proposed method achieves a heightened accuracy and is superior to the state-of-the-art traditional insect classification algorithms.

https://www.mdpi.com/1424-8220/18/12/4169/pdf

Insect Detection and Classification Based on an Improved Convolutional Neural Network.

Multi-class pest detection is one of the crucial components in pest management involving localization in addition to classification which is much more difficult than generic object detection because of the apparent differences among pest species. This paper proposes a region-based end-to-end approach named PestNet for large-scale multi-class pest detection and classification based on deep learning. PestNet consists of three major parts. First, a novel module channel–spatial attention (CSA) is proposed to be fused into the convolutional neural network (CNN) backbone for feature extraction and enhancement. The second one is called region proposal network (RPN) that is adopted for providing region proposals as potential pest positions based on extracted feature maps from images. Position-sensitive score map (PSSM), the third component, is used to replace fully connected (FC) layers for pest classification and bounding box regression. Furthermore, we apply contextual regions of interest (RoIs) as contextual information of pest features to improve detection accuracy. We evaluate PestNet on our newly collected large-scale pests’ image dataset, Multi-class Pests Dataset 2018 (MPD2018) captured by our designed task-specific image acquisition equipment, covering more than 80k images with over 580k pests labeled by agricultural experts and categorized in 16 classes. The experimental results show that the proposed PestNet performs well on multi-class pest detection with 75.46% mean average precision (mAP), which outperforms the state-of-the-art methods.

PestNet: An End-to-End Deep Learning Approach for Large-Scale Multi-Class Pest Detection and Classification

Crop pest recognition in natural scenes using convolutional neural networks

Multi-level learning features for automatic classification of field crop pests

The invention relates to a pest and disease image generation method based on a generative adversarial network In the prior art, sampling images of pest and disease images are less By using the method of the invention, the above defect is overcome The method comprises the following steps of collecting and preprocessing trained images; based on a deep-convolution neural network model, constructing a discrimination network and a generation network; training the discrimination network and the generation network; and according to the trained generation network, generating the pest and disease images In the invention, according to a few of existing pest and disease images, a lot of pest and disease images which are similar to a reality are generated, a sample image is provided for pest and disease image identification, and problems that the pest and disease images in an actual field are less and acquisition cost is high are solved

Pest and disease image generation method based on generative adversarial network

Conventional pests image classification methods may not be accurate due to the complex farmland background, sunlight and pest gestures. To raise the accuracy, the deep convolutional neural network (DCNN), a concept from Deep Learning, was used in this study to classify crop pests image. On the ground of our experiments, in which LeNet-5 and AlexNet were used to classify pests image, we have analyzed the effects of both convolution kernel and the number of layers on the network, and redesigned the structure of convolutional neural network for crop pests. Further more, 82 common pest types have been classified, with the accuracy reaching 91%. The comparison to conventional classification methods proves that our method is not only feasible but preeminent.

/pdf/a-crop-pests-image-classification-algorithm-based-on-deep-32hmdg771l.pdf

A Crop Pests Image Classification Algorithm Based on Deep Convolutional Neural Network

The invention relates to a method of disease image identification based on hybrid convolutional neural network fused with context information, which solves the defects of low image identification rate and poor robustness as compared with the prior art. The method comprises the steps of collecting and preprocessing training images; constructing and training a hybrid convolutional neural network model; collecting and preprocessing images under test; and inputting a test sample into the hybrid convolutional neural network model after the training is completed, conducting automatic identification of disease images, and identifying the type of the images under test. The method of the invention combines the image information of the disease images and the context information to construct the hybrid convolutional neural network, thus improving the accuracy of the disease identification and enhancing the robustness of the disease identification algorithm.

Method of disease image identification based on hybrid convolutional neural network fused with context information

The invention relates to a pest image classification method based on a grading-prediction convolutional neural network. Compared to the prior art, by using the method of the invention, a defect that a pest image classification correct rate is low is overcome. The method comprises the following steps of collecting and preprocessing training images; marking image sample data; training a classification model based on the grading-prediction convolutional neural network; preprocessing images to be tested; and based on a grading model, automatically carrying out pest image classification. In the invention, a grading prediction framework is adopted; a segmentation result of the images is predicted firstly and then an integral image is combined; and final classification prediction is performed.

Chen Tianjiao

Papers

Multi-level learning features for automatic classification of field crop pests

Pest and disease image generation method based on generative adversarial network

A Crop Pests Image Classification Algorithm Based on Deep Convolutional Neural Network

Method of disease image identification based on hybrid convolutional neural network fused with context information

Pest image classification method based on grading-prediction convolutional neural network