Real-Time Forestry Pest Detection Method Based on Enhanced Feature Fusion with Deep Learning

The aim of this study is to address the real-time requirements of forestry pest detection and the problem of a low detection rate caused by anchor box redundancy of existing detection methods. This paper proposes a real-time forestry pest detection method based on theanchor-free method that can bala...

Full description

Saved in:
Bibliographic Details
Main Authors: Rui Li, Tong Liu, Yalu Ren
Format: Article
Language:English
Published: Wiley 2022-01-01
Series:Journal of Electrical and Computer Engineering
Online Access:http://dx.doi.org/10.1155/2022/5774306
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832554772204355584
author Rui Li
Tong Liu
Yalu Ren
author_facet Rui Li
Tong Liu
Yalu Ren
author_sort Rui Li
collection DOAJ
description The aim of this study is to address the real-time requirements of forestry pest detection and the problem of a low detection rate caused by anchor box redundancy of existing detection methods. This paper proposes a real-time forestry pest detection method based on theanchor-free method that can balance the detection rate and detection accuracy. Based on the TTFNet method, a mobile feature extraction network is introduced, and the effective feature weights are increased by one-dimensional convolution before feature output to suppress invalid features. For pest detection, data are mostly small-scale targets. An enhanced feature fusion method is proposed to introduce an asymmetric convolution module in multi-scale feature fusion to feature-enhance the feature maps extracted by the backbone network and connect across layers to improve the detection accuracy. To address the degradation of the anchor box position regression loss in the original method, DIOULoss is introduced to optimize the position regression loss function of the anchor box. Finally, data augmentation is performed on a relatively small number of samples in the dataset, the accuracy of the model is improved by 1.94%, the FPS is improved to 1.6 times of the original one, and the training time is slightly increased compared with the preinnovation model. Ablation experiments are designed to demonstrate the effectiveness of the proposed algorithm while being more conducive to deployment on edge devices.
format Article
id doaj-art-f83057bb2e264175948c0a04d80b83f7
institution Kabale University
issn 2090-0155
language English
publishDate 2022-01-01
publisher Wiley
record_format Article
series Journal of Electrical and Computer Engineering
spelling doaj-art-f83057bb2e264175948c0a04d80b83f72025-02-03T05:50:39ZengWileyJournal of Electrical and Computer Engineering2090-01552022-01-01202210.1155/2022/5774306Real-Time Forestry Pest Detection Method Based on Enhanced Feature Fusion with Deep LearningRui Li0Tong Liu1Yalu Ren2School of Computer and CommunicationSchool of Computer and CommunicationSchool of Computer and CommunicationThe aim of this study is to address the real-time requirements of forestry pest detection and the problem of a low detection rate caused by anchor box redundancy of existing detection methods. This paper proposes a real-time forestry pest detection method based on theanchor-free method that can balance the detection rate and detection accuracy. Based on the TTFNet method, a mobile feature extraction network is introduced, and the effective feature weights are increased by one-dimensional convolution before feature output to suppress invalid features. For pest detection, data are mostly small-scale targets. An enhanced feature fusion method is proposed to introduce an asymmetric convolution module in multi-scale feature fusion to feature-enhance the feature maps extracted by the backbone network and connect across layers to improve the detection accuracy. To address the degradation of the anchor box position regression loss in the original method, DIOULoss is introduced to optimize the position regression loss function of the anchor box. Finally, data augmentation is performed on a relatively small number of samples in the dataset, the accuracy of the model is improved by 1.94%, the FPS is improved to 1.6 times of the original one, and the training time is slightly increased compared with the preinnovation model. Ablation experiments are designed to demonstrate the effectiveness of the proposed algorithm while being more conducive to deployment on edge devices.http://dx.doi.org/10.1155/2022/5774306
spellingShingle Rui Li
Tong Liu
Yalu Ren
Real-Time Forestry Pest Detection Method Based on Enhanced Feature Fusion with Deep Learning
Journal of Electrical and Computer Engineering
title Real-Time Forestry Pest Detection Method Based on Enhanced Feature Fusion with Deep Learning
title_full Real-Time Forestry Pest Detection Method Based on Enhanced Feature Fusion with Deep Learning
title_fullStr Real-Time Forestry Pest Detection Method Based on Enhanced Feature Fusion with Deep Learning
title_full_unstemmed Real-Time Forestry Pest Detection Method Based on Enhanced Feature Fusion with Deep Learning
title_short Real-Time Forestry Pest Detection Method Based on Enhanced Feature Fusion with Deep Learning
title_sort real time forestry pest detection method based on enhanced feature fusion with deep learning
url http://dx.doi.org/10.1155/2022/5774306
work_keys_str_mv AT ruili realtimeforestrypestdetectionmethodbasedonenhancedfeaturefusionwithdeeplearning
AT tongliu realtimeforestrypestdetectionmethodbasedonenhancedfeaturefusionwithdeeplearning
AT yaluren realtimeforestrypestdetectionmethodbasedonenhancedfeaturefusionwithdeeplearning