Crop pest recognition in natural scenes using convolutional neural networks

Li, Yanfen; Wang, Hanxiang; Dang, L. Minh; Sadeghi‐Niaraki, Abolghasem; Moon, Hyeonjoon

doi:10.1016/j.compag.2019.105174

Cited by 139 publications

(48 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several species-specific methods are used in the field to detect and recognize insect species automatically. Camera traps with machine vision [ 42 , 43 , 44 , 45 ] or using color sensors [ 46 ] have high species-specificity. However, these are useful only for sticky traps in which individuals caught can be easily photographed; photographing insects flying into the trap remains a technical challenge.…”

Section: Discussionmentioning

confidence: 99%

Automatic Field Detection of Western Corn Rootworm (Diabrotica virgifera virgifera; Coleoptera: Chrysomelidae) with a New Probe

Tóth

Jósvai

et al. 2020

Insects

View full text Add to dashboard Cite

The Western corn rootworm (WCR), Diabrotica virgifera virgifera LeConte (Coleoptera: Chrysomelidae), is a significant invasive pest of maize plantations in Europe. Integrated pest management demands an adequate monitoring system which detects the activity of insects with high accuracy in real-time. In this study, we show and test a new electronic device (ZooLog KLP), which was developed to detect WCR in the field. The ZooLog KLP consists of a trapping element that attracts insects with its color and species-specific sex pheromone. The other part is an opto-electronic sensor-ring which detects the specimens when they fall into the trap. At detection, the time of catch is recorded and sent to a web interface. In this study, we followed WCR flight patterns for six weeks in two locations, using ZooLog KLP probes. We investigated sensor precision by comparing the number of catches to the number of detections. The tool reached high accuracy (95.84%) in recording WCR. We found a peak in flight activity in August and a bimodal daily pattern. This method may be beneficial in detecting the WCR during their activity, and this new device may serve as a prototype for real-time monitoring systems and improve the management of this pest.

show abstract

Section: Discussionmentioning

confidence: 99%

Automatic Field Detection of Western Corn Rootworm (Diabrotica virgifera virgifera; Coleoptera: Chrysomelidae) with a New Probe

Tóth

Jósvai

et al. 2020

Insects

View full text Add to dashboard Cite

show abstract

“…The In consideration of the limited number of labelled datasets, the concept of transfer learning was applied to retrain the deep learning classifier. This concept is not new and has been previously applied in a number of studies [20,21,26].The vine classification tasks are evaluated in terms of accuracy and efficiency. In transfer learning, the layered architecture of the pre-trained models such as AlexNet, ResNet and VGG (without its final classification layer) can be used as fixed feature extractor to achieve better vine classification performance with a shorter training time [27].…”

Section: Transfer Learning Of Deep Networkmentioning

confidence: 99%

“…Canny edge detection is used to detect the edge in the gray-scale image converted from RGB of insect and suppress the noise, which is a method of data augmentation to facilitate crop pest recognition using transfer learning[20]. Threshold processing, contour detection and watershed algorithm are used to eliminate the influence of natural background on object detection[21]. Is image preprocessing the key to improve the accuracy of detection model?…”

mentioning

confidence: 99%

Identification of grapevine(Vitis vinifera L.)cultivars by vine leaf image via deep learning and mobile devices

Liu

Guo-qian

et al. 2020

Preprint

View full text Add to dashboard Cite

Background Traditional vine variety identification methods usually rely on destructive sampling of vine leaves followed by physical, physiological, biochemical and molecular measurement, which is destructive, time-consuming, labor-intensive and requires experienced grape phenotype analysts. To mitigate these problems, this study aims to develop an application (App) running on Android client to identify wine grape automatically and in real time, which can help the growers to quickly obtain the variety information. Results Experimental results show that all Convolutional Neural Network (CNN) classification algorithms can achieve an accuracy of over 94% for 21 categories on validation data, which proves the feasibility of using transfer learning to identify grape species in field environments. In particular, the classification model with the highest average accuracy is Googlenet (97.4%) with learning rate (0.001), mini-batch size (32) and maximum number of epochs (80). Testing results of the App on Android device also confirms these results. Conclusions An App running on Android client is developed to identify the wine grape in real time and field condition, which can help the growers to quickly obtain the variety information of wine grape. A total of 4200 leaf images were first collected in the field environment, which contain 21 types of typical grapes. Then both image complement preprocessing and data augmentation are adopted to enhance image features and augment the training dataset. On this basis, a number of typical CNN models (including VGG-16, DenseNet, ResNet101, ResNet18, and GoogLeNet) are compared in transfer learning training to identify the suitable one while with model parameter tuning. It is shown that GoogLeNet model outperformed other models in terms of accuracy, model complexity, and robustness with a fine-tuned accuracy of 99.91%. The effect of image complement preprocessing is also assessed by using Grad-CAM algorithm. The developed App is also shown to be feasible for real-life applications with a processing time of less than 1 second.

show abstract

“…Crop pests and diseases are major problems in the agricultural industry that cause significant losses to food production. Nearly half of the world’s crops are lost due to pest infestation and disease [ 1 ]. In Miaoli County, Taiwan, the strawberry, which contributes $1.8 billion annually, is facing similar problems.…”

Section: Introductionmentioning

confidence: 99%

Detection of Strawberry Diseases Using a Convolutional Neural Network

Xiao

Chung²,

et al. 2020

Plants

View full text Add to dashboard Cite

The strawberry (Fragaria × ananassa Duch.) is a high-value crop with an annual cultivated area of ~500 ha in Taiwan. Over 90% of strawberry cultivation is in Miaoli County. Unfortunately, various diseases significantly decrease strawberry production. The leaf and fruit disease became an epidemic in 1986. From 2010 to 2016, anthracnose crown rot caused the loss of 30–40% of seedlings and ~20% of plants after transplanting. The automation of agriculture and image recognition techniques are indispensable for detecting strawberry diseases. We developed an image recognition technique for the detection of strawberry diseases using a convolutional neural network (CNN) model. CNN is a powerful deep learning approach that has been used to enhance image recognition. In the proposed technique, two different datasets containing the original and feature images are used for detecting the following strawberry diseases—leaf blight, gray mold, and powdery mildew. Specifically, leaf blight may affect the crown, leaf, and fruit and show different symptoms. By using the ResNet50 model with a training period of 20 epochs for 1306 feature images, the proposed CNN model achieves a classification accuracy rate of 100% for leaf blight cases affecting the crown, leaf, and fruit; 98% for gray mold cases, and 98% for powdery mildew cases. In 20 epochs, the accuracy rate of 99.60% obtained from the feature image dataset was higher than that of 1.53% obtained from the original one. This proposed model provides a simple, reliable, and cost-effective technique for detecting strawberry diseases.

show abstract

Crop pest recognition in natural scenes using convolutional neural networks

Cited by 139 publications

References 18 publications

Automatic Field Detection of Western Corn Rootworm (Diabrotica virgifera virgifera; Coleoptera: Chrysomelidae) with a New Probe

Automatic Field Detection of Western Corn Rootworm (Diabrotica virgifera virgifera; Coleoptera: Chrysomelidae) with a New Probe

Identification of grapevine(Vitis vinifera L.)cultivars by vine leaf image via deep learning and mobile devices

Detection of Strawberry Diseases Using a Convolutional Neural Network

Contact Info

Product

Resources

About