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

Xie, Chengjun; Wang, Rujing; Zhang, Jie; Chen, Peng; Dong, Wei; Li, Rui; Chen, Tianjiao; Chen, Hongbo

doi:10.1016/j.compag.2018.07.014

Cited by 135 publications

(63 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Yet on average it only has 60 samples per class, which is also hard to train a CNN. To tackle this problem, [23,43,2] propose some datasets which contain more than 4, 500 samples in total and 100 samples for each class. However, only the dataset of [43] is available so far.…”

Section: Related Datasetsmentioning

confidence: 99%

“…To tackle this problem, [23,43,2] propose some datasets which contain more than 4, 500 samples in total and 100 samples for each class. However, only the dataset of [43] is available so far. Besides, the background, object pose of the same class of pest images in this dataset [43] are highly similar, making it difficult to cope with the complexities of reallife scenes.…”

Section: Related Datasetsmentioning

confidence: 99%

“…However, only the dataset of [43] is available so far. Besides, the background, object pose of the same class of pest images in this dataset [43] are highly similar, making it difficult to cope with the complexities of reallife scenes. Table 2 illustrates the details of these related datasets.…”

Section: Related Datasetsmentioning

confidence: 99%

“…In Table 2, we compare the IP102 with several existing datasets related to the task of insect pest recognition. Com-pared to the largest datasets [23,43,2], our dataset contains over 14 times more samples. With respect to the class diversity, the largest and least datasets only have 40 and 8 classes, respectively.…”

Section: Comparison With Other Datasetsmentioning

confidence: 99%

See 3 more Smart Citations

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

Zhan

Lai

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

297

137

View full text Add to dashboard Cite

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.

show abstract

Section: Related Datasetsmentioning

confidence: 99%

Section: Related Datasetsmentioning

confidence: 99%

Section: Related Datasetsmentioning

confidence: 99%

Section: Comparison With Other Datasetsmentioning

confidence: 99%

See 2 more Smart Citations

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

Zhan

Lai

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

297

137

View full text Add to dashboard Cite

show abstract

“…Machine learning (ML) also played an important contribution in synergically using both datasets for agricultural applications. Researchers have developed numerous ML algorithms for crop classification using SAR and optical data (Xie et al 2018) (Wang et al 2016). Recently, deep neural networks (DNNs) are making its mark as powerful tool for remote sensing applications.…”

Section: Introduction and Related Workmentioning

confidence: 99%

Comparative Study on Deep Neural Network Models for Crop Classification Using Time Series Polsar and Optical Data

Phartiyal

Singh

2018

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

<p><strong>Abstract.</strong> Crop classification is an important task in many crop monitoring applications. Satellite remote sensing has provided easy, reliable, and fast approaches to crop classification task. In this study, a comparative analysis is made on the performances of various deep neural network (DNN) models for crop classification task using polarimetric synthetic aperture radar (PolSAR) and optical satellite data. For PolSAR data, Sentinel 1 dual pol SAR data is used. Sentinel 2 multispectral data is used as optical data. Five land cover classes including two crop classes of the season are taken. Time series data over the period of one crop cycle is used. Training and testing samples are measured and collected directly from the ground over the study region. Various convolutional neural network (CNN) and long short-term memory (LSTM) models are implemented, analysed, evaluated, and compared. Models are evaluated on the basis of classification accuracy and generalization performance.</p>

show abstract