TY  - CONF
T1  - High Precision Agriculture: An Application Of Improved Machine-Learning Algorithms
A1  - Treboux, Jerome
A1  - Genoud, Dominique
Y1  - 2019
SP  - 103
EP  - 108
PB  - IEEE 2019 6th Swiss Conference on Data Science (SDS)
CY  - Bern, Switzerland
UR  - http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8789854&isnumber=8789845
M2  - doi: 10.1109/SDS.2019.00007
KW  - advanced machine learning methodologies
KW  - aerial images
KW  - Agricultural health
KW  - agriculture
KW  - dataset
KW  - decision tree ensemble
KW  - decision trees
KW  - feature extraction
KW  - high precision agriculture
KW  - Hyper-spectral images
KW  - Image color analysis
KW  - Image recognition
KW  - image recognition algorithms
KW  - improved machine-learning algorithms
KW  - learning (artificial intelligence)
KW  - machine learning
KW  - object detection
KW  - Precision agriculture
KW  - Prediction
KW  - Random Forests
KW  - Roads
N2  - This paper presents the performances of machine learning algorithms on aerial images object detection for high precision agriculture. The dataset used focuses on geotagged pictures of vineyards. We demonstrate that advanced machine learning methodologies like Decision Tree Ensemble, outperform state-of-the-art image recognition algorithms generally used within the agriculture field. The innovative approach described here improve object detection and obtain an accuracy of 94.27% which is an increase of more than 4% compared to the state-of-the-art. Finally, methodology and possible developments for high precision agriculture is discussed in this study.
ER  -