Loading…
Towards weeds identification assistance through transfer learning
•Weed identification using deep learning techniques.•Different pre-processing and transfer learning strategies were evaluated.•The performance of 7 state-of-art deep neural architectures were performed.•A dataset containing annotated crops and weeds has been published.•The methodology proposed can b...
Saved in:
Published in: | Computers and electronics in agriculture 2020-04, Vol.171, p.105306, Article 105306 |
---|---|
Main Authors: | , , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Summary: | •Weed identification using deep learning techniques.•Different pre-processing and transfer learning strategies were evaluated.•The performance of 7 state-of-art deep neural architectures were performed.•A dataset containing annotated crops and weeds has been published.•The methodology proposed can be used by either RGB or multispectral pictures.
Reducing the use of pesticides through selective spraying is an important component towards a more sustainable computer-assisted agriculture. Weed identification at early growth stage contributes to reduced herbicide rates. However, while computer vision alongside deep learning have overcome the performance of approaches that use hand-crafted features, there are still some open challenges in the development of a reliable automatic plant identification system. These type of systems have to take into account different sources of variability, such as growth stages and soil conditions, with the added constraint of the limited size of usual datasets. This study proposes a novel crop/weed identification system that relies on a combination of fine-tuning pre-trained convolutional networks (Xception, Inception-Resnet, VGNets, Mobilenet and Densenet) with the “traditional” machine learning classifiers (Support Vector Machines, XGBoost and Logistic Regression) trained with the previously deep extracted features. The aim of this approach was to avoid overfitting and to obtain a robust and consistent performance. To evaluate this approach, an open access dataset of two crop [tomato (Solanum lycopersicum L.) and cotton (Gossypium hirsutum L.)] and two weed species [black nightshade (Solanum nigrum L.) and velvetleaf (Abutilon theophrasti Medik.)] was generated. The pictures were taken by different production sites across Greece under natural variable light conditions from RGB cameras. The results revealed that a combination of fine-tuned Densenet and Support Vector Machine achieved a micro F1 score of 99.29% with a very low performance difference between train and test sets. Other evaluated approaches also obtained repeatedly more than 95% F1 score. Additionally, our results analysis provides some heuristics for designing transfer-learning based systems to avoid overfitting without decreasing performance. |
---|---|
ISSN: | 0168-1699 1872-7107 |
DOI: | 10.1016/j.compag.2020.105306 |