A System for Weeds and Crops Identification—Reaching over 10 FPS on Raspberry Pi with the Usage of MobileNets, DenseNet and Custom Modifications
Automated weeding is an important research area in agrorobotics. Weeds can be removed mechanically or with the precise usage of herbicides. Deep Learning techniques achieved state of the art results in many computer vision tasks, however their deployment on low-cost mobile computers is still challen...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-08-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/19/17/3787 |
_version_ | 1797999044566450176 |
---|---|
author | Łukasz Chechliński Barbara Siemiątkowska Michał Majewski |
author_facet | Łukasz Chechliński Barbara Siemiątkowska Michał Majewski |
author_sort | Łukasz Chechliński |
collection | DOAJ |
description | Automated weeding is an important research area in agrorobotics. Weeds can be removed mechanically or with the precise usage of herbicides. Deep Learning techniques achieved state of the art results in many computer vision tasks, however their deployment on low-cost mobile computers is still challenging. The described system contains several novelties, compared both with its previous version and related work. It is a part of a project of the automatic weeding machine, developed by the Warsaw University of Technology and MCMS Warka Ltd. Obtained models reach satisfying accuracy (detecting 47−67% of weed area, misclasifing as weed 0.1−0.9% of crop area) at over 10 FPS on the Raspberry Pi 3B+ computer. It was tested for four different plant species at different growth stadiums and lighting conditions. The system performing semantic segmentation is based on Convolutional Neural Networks. Its custom architecture combines U-Net, MobileNets, DenseNet and ResNet concepts. Amount of needed manual ground truth labels was significantly decreased by the usage of the knowledge distillation process, learning final model which mimics an ensemble of complex models on a large database of unlabeled data. Further decrease of the inference time was obtained by two custom modifications: in the usage of separable convolutions in DenseNet block and in the number of channels in each layer. In the authors’ opinion, the described novelties can be easily transferred to other agrorobotics tasks. |
first_indexed | 2024-04-11T10:58:24Z |
format | Article |
id | doaj.art-28991b0487dd464f892cf804ec8d0c29 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-04-11T10:58:24Z |
publishDate | 2019-08-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-28991b0487dd464f892cf804ec8d0c292022-12-22T04:28:41ZengMDPI AGSensors1424-82202019-08-011917378710.3390/s19173787s19173787A System for Weeds and Crops Identification—Reaching over 10 FPS on Raspberry Pi with the Usage of MobileNets, DenseNet and Custom ModificationsŁukasz Chechliński0Barbara Siemiątkowska1Michał Majewski2Faculty of Mechatronics, Warsaw University of Technology, 00-661 Warsaw, PolandFaculty of Mechatronics, Warsaw University of Technology, 00-661 Warsaw, PolandMCMS Warka Ltd., 05-660 Warka, PolandAutomated weeding is an important research area in agrorobotics. Weeds can be removed mechanically or with the precise usage of herbicides. Deep Learning techniques achieved state of the art results in many computer vision tasks, however their deployment on low-cost mobile computers is still challenging. The described system contains several novelties, compared both with its previous version and related work. It is a part of a project of the automatic weeding machine, developed by the Warsaw University of Technology and MCMS Warka Ltd. Obtained models reach satisfying accuracy (detecting 47−67% of weed area, misclasifing as weed 0.1−0.9% of crop area) at over 10 FPS on the Raspberry Pi 3B+ computer. It was tested for four different plant species at different growth stadiums and lighting conditions. The system performing semantic segmentation is based on Convolutional Neural Networks. Its custom architecture combines U-Net, MobileNets, DenseNet and ResNet concepts. Amount of needed manual ground truth labels was significantly decreased by the usage of the knowledge distillation process, learning final model which mimics an ensemble of complex models on a large database of unlabeled data. Further decrease of the inference time was obtained by two custom modifications: in the usage of separable convolutions in DenseNet block and in the number of channels in each layer. In the authors’ opinion, the described novelties can be easily transferred to other agrorobotics tasks.https://www.mdpi.com/1424-8220/19/17/3787automated weedingmobile convolutional neural netowrkssemantic segmentation |
spellingShingle | Łukasz Chechliński Barbara Siemiątkowska Michał Majewski A System for Weeds and Crops Identification—Reaching over 10 FPS on Raspberry Pi with the Usage of MobileNets, DenseNet and Custom Modifications Sensors automated weeding mobile convolutional neural netowrks semantic segmentation |
title | A System for Weeds and Crops Identification—Reaching over 10 FPS on Raspberry Pi with the Usage of MobileNets, DenseNet and Custom Modifications |
title_full | A System for Weeds and Crops Identification—Reaching over 10 FPS on Raspberry Pi with the Usage of MobileNets, DenseNet and Custom Modifications |
title_fullStr | A System for Weeds and Crops Identification—Reaching over 10 FPS on Raspberry Pi with the Usage of MobileNets, DenseNet and Custom Modifications |
title_full_unstemmed | A System for Weeds and Crops Identification—Reaching over 10 FPS on Raspberry Pi with the Usage of MobileNets, DenseNet and Custom Modifications |
title_short | A System for Weeds and Crops Identification—Reaching over 10 FPS on Raspberry Pi with the Usage of MobileNets, DenseNet and Custom Modifications |
title_sort | system for weeds and crops identification reaching over 10 fps on raspberry pi with the usage of mobilenets densenet and custom modifications |
topic | automated weeding mobile convolutional neural netowrks semantic segmentation |
url | https://www.mdpi.com/1424-8220/19/17/3787 |
work_keys_str_mv | AT łukaszchechlinski asystemforweedsandcropsidentificationreachingover10fpsonraspberrypiwiththeusageofmobilenetsdensenetandcustommodifications AT barbarasiemiatkowska asystemforweedsandcropsidentificationreachingover10fpsonraspberrypiwiththeusageofmobilenetsdensenetandcustommodifications AT michałmajewski asystemforweedsandcropsidentificationreachingover10fpsonraspberrypiwiththeusageofmobilenetsdensenetandcustommodifications AT łukaszchechlinski systemforweedsandcropsidentificationreachingover10fpsonraspberrypiwiththeusageofmobilenetsdensenetandcustommodifications AT barbarasiemiatkowska systemforweedsandcropsidentificationreachingover10fpsonraspberrypiwiththeusageofmobilenetsdensenetandcustommodifications AT michałmajewski systemforweedsandcropsidentificationreachingover10fpsonraspberrypiwiththeusageofmobilenetsdensenetandcustommodifications |