Real-Time Detection for Wheat Head Applying Deep Neural Network
Wheat head detection can estimate various wheat traits, such as density, health, and the presence of wheat head. However, traditional detection methods have a huge array of problems, including low efficiency, strong subjectivity, and poor accuracy. In this paper, a method of wheat-head detection bas...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-12-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/1/191 |
_version_ | 1797543073427750912 |
---|---|
author | Bo Gong Daji Ergu Ying Cai Bo Ma |
author_facet | Bo Gong Daji Ergu Ying Cai Bo Ma |
author_sort | Bo Gong |
collection | DOAJ |
description | Wheat head detection can estimate various wheat traits, such as density, health, and the presence of wheat head. However, traditional detection methods have a huge array of problems, including low efficiency, strong subjectivity, and poor accuracy. In this paper, a method of wheat-head detection based on a deep neural network is proposed to enhance the speed and accuracy of detection. The YOLOv4 is taken as the basic network. The backbone part in the basic network is enhanced by adding dual spatial pyramid pooling (SPP) networks to improve the ability of feature learning and increase the receptive field of the convolutional network. Multilevel features are obtained by a multipath neck part using a top-down to bottom-up strategy. Finally, YOLOv3′s head structures are used to predict the boxes of wheat heads. For training images, some data augmentation technologies are used. The experimental results demonstrate that the proposed method has a significant advantage in accuracy and speed. The mean average precision of our method is 94.5%, and the detection speed is 71 FPS that can achieve the effect of real-time detection. |
first_indexed | 2024-03-10T13:40:29Z |
format | Article |
id | doaj.art-3b85126a00984a3f985d63db8e8aef4e |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T13:40:29Z |
publishDate | 2020-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-3b85126a00984a3f985d63db8e8aef4e2023-11-21T03:06:08ZengMDPI AGSensors1424-82202020-12-0121119110.3390/s21010191Real-Time Detection for Wheat Head Applying Deep Neural NetworkBo Gong0Daji Ergu1Ying Cai2Bo Ma3Key Laboratory of Electronic and Information Engineering (Southwest Minzu University), State Ethnic Affairs Commission, Chengdu 610041, ChinaKey Laboratory of Electronic and Information Engineering (Southwest Minzu University), State Ethnic Affairs Commission, Chengdu 610041, ChinaKey Laboratory of Electronic and Information Engineering (Southwest Minzu University), State Ethnic Affairs Commission, Chengdu 610041, ChinaKey Laboratory of Electronic and Information Engineering (Southwest Minzu University), State Ethnic Affairs Commission, Chengdu 610041, ChinaWheat head detection can estimate various wheat traits, such as density, health, and the presence of wheat head. However, traditional detection methods have a huge array of problems, including low efficiency, strong subjectivity, and poor accuracy. In this paper, a method of wheat-head detection based on a deep neural network is proposed to enhance the speed and accuracy of detection. The YOLOv4 is taken as the basic network. The backbone part in the basic network is enhanced by adding dual spatial pyramid pooling (SPP) networks to improve the ability of feature learning and increase the receptive field of the convolutional network. Multilevel features are obtained by a multipath neck part using a top-down to bottom-up strategy. Finally, YOLOv3′s head structures are used to predict the boxes of wheat heads. For training images, some data augmentation technologies are used. The experimental results demonstrate that the proposed method has a significant advantage in accuracy and speed. The mean average precision of our method is 94.5%, and the detection speed is 71 FPS that can achieve the effect of real-time detection.https://www.mdpi.com/1424-8220/21/1/191deep learningwheat headreal-time object detectionSPP |
spellingShingle | Bo Gong Daji Ergu Ying Cai Bo Ma Real-Time Detection for Wheat Head Applying Deep Neural Network Sensors deep learning wheat head real-time object detection SPP |
title | Real-Time Detection for Wheat Head Applying Deep Neural Network |
title_full | Real-Time Detection for Wheat Head Applying Deep Neural Network |
title_fullStr | Real-Time Detection for Wheat Head Applying Deep Neural Network |
title_full_unstemmed | Real-Time Detection for Wheat Head Applying Deep Neural Network |
title_short | Real-Time Detection for Wheat Head Applying Deep Neural Network |
title_sort | real time detection for wheat head applying deep neural network |
topic | deep learning wheat head real-time object detection SPP |
url | https://www.mdpi.com/1424-8220/21/1/191 |
work_keys_str_mv | AT bogong realtimedetectionforwheatheadapplyingdeepneuralnetwork AT dajiergu realtimedetectionforwheatheadapplyingdeepneuralnetwork AT yingcai realtimedetectionforwheatheadapplyingdeepneuralnetwork AT boma realtimedetectionforwheatheadapplyingdeepneuralnetwork |