Redirigiendo al acceso original de articulo en 22 segundos...
Inicio  /  Agriculture  /  Vol: 13 Par: 12 (2023)  /  Artículo
ARTÍCULO
TITULO

Precision Corn Pest Detection: Two-Step Transfer Learning for Beetles (Coleoptera) with MobileNet-SSD

Edmond Maican    
Adrian Iosif and Sanda Maican    

Resumen

Using neural networks on low-power mobile systems can aid in controlling pests while preserving beneficial species for crops. However, low-power devices require simplified neural networks, which may lead to reduced performance. This study was focused on developing an optimized deep-learning model for mobile devices for detecting corn pests. We propose a two-step transfer learning approach to enhance the accuracy of two versions of the MobileNet SSD network. Five beetle species (Coleoptera), including four harmful to corn crops (belonging to genera Anoxia, Diabrotica, Opatrum and Zabrus), and one beneficial (Coccinella sp.), were selected for preliminary testing. We employed two datasets. One for the first transfer learning procedure comprises 2605 images with general dataset classes ?Beetle? and ?Ladybug?. It was used to recalibrate the networks? trainable parameters for these two broader classes. Furthermore, the models were retrained on a second dataset of 2648 images of the five selected species. Performance was compared with a baseline model in terms of average accuracy per class and mean average precision (mAP). MobileNet-SSD-v2-Lite achieved an mAP of 0.8923, ranking second but close to the highest mAP (0.908) obtained by MobileNet-SSD-v1 and outperforming the baseline mAP by 6.06%. It demonstrated the highest accuracy for Opatrum (0.9514) and Diabrotica (0.8066). Anoxia it reached a third-place accuracy (0.9851), close to the top value of 0.9912. Zabrus achieved the second position (0.9053), while Coccinella was reliably distinguished from all other species, with an accuracy of 0.8939 and zero false positives; moreover, no pest species were mistakenly identified as Coccinella. Analyzing the errors in the MobileNet-SSD-v2-Lite model revealed good overall accuracy despite the reduced size of the training set, with one misclassification, 33 non-identifications, 7 double identifications and 1 false positive across the 266 images from the test set, yielding an overall relative error rate of 0.1579. The preliminary findings validated the two-step transfer learning procedure and placed the MobileNet-SSD-v2-Lite in the first place, showing high potential for using neural networks on real-time pest control while protecting beneficial species.

 Artículos similares

       
 
Xiangpeng Fan and Zhibin Guan    
The automatic recognition of crop diseases based on visual perception algorithms is one of the important research directions in the current prevention and control of crop diseases. However, there are two issues to be addressed in corn disease identificat... ver más
Revista: Agriculture

 
Quan Xu, Mengting Jin and Peng Guo    
Timely and accurate information on crop planting structures is crucial for ensuring national food security and formulating economic policies. This study presents a method for high-precision crop classification using time-series UAV (unmanned aerial vehic... ver más
Revista: Agriculture

 
Ruixue Zhu, Fengqi Hao and Dexin Ma    
Object detection in deep learning provides a viable solution for detecting crop-pest-infected regions. However, existing rectangle-based object detection methods are insufficient to accurately detect the shape of pest-infected regions. In addition, the m... ver más
Revista: Agriculture

 
Carlos H. Wachholz de Souza, Erivelto Mercante, Victor H. R. Prudente, Diego D.D. Justina     Pág. 419 - 428
Satellite imagery, in combination with remote sensing techniques, provides a new opportunity for monitoring and assessing crops with lower cost and greater objectivity than traditional surveys. The present research employed Landsat 5/TM satellite imagery... ver más