TY - JOUR
T1 - Fusion of pixel and object-based features for weed mapping using unmanned aerial vehicle imagery
AU - Gao, Junfeng
AU - Liao, Wenzhi
AU - Nuyttens, David
AU - Lootens, Peter
AU - Vangeyte, Jürgen
AU - Pizurica, Aleksandra
AU - He, Yong
AU - Pieters, Jan G.
PY - 2018/5/31
Y1 - 2018/5/31
N2 - The developments in the use of unmanned aerial vehicles (UAVs) and advanced imaging sensors provide new opportunities for ultra-high resolution (e.g., less than a 10 cm ground sampling distance (GSD)) crop field monitoring and mapping in precision agriculture applications. In this study, we developed a strategy for interand intra-row weed detection in early season maize fields from aerial visual imagery. More specifically, the Hough transform algorithm (HT) was applied to the orthomosaicked images for inter-row weed detection. A semi-automatic Object-Based Image Analysis (OBIA) procedure was developed with Random Forests (RF) combined with feature selection techniques to classify soil, weeds and maize. Furthermore, the two binary weed masks generated from HT and OBIA were fused for accurate binary weed image. The developed RF classifier was evaluated by 5-fold cross validation, and it obtained an overall accuracy of 0.945, and Kappa value of 0.912. Finally, the relationship of detected weeds and their ground truth densities was quantified by a fitted linear model with a coefficient of determination of 0.895 and a root mean square error of 0.026. Besides, the importance of input features was evaluated, and it was found that the ratio of vegetation length and width was the most significant feature for the classification model. Overall, our approach can yield a satisfactory weed map, and we expect that the obtained accurate and timely weed map from UAV imagery will be applicable to realize site-specific weed management (SSWM) in early season crop fields for reducing spraying non-selective herbicides and costs.
AB - The developments in the use of unmanned aerial vehicles (UAVs) and advanced imaging sensors provide new opportunities for ultra-high resolution (e.g., less than a 10 cm ground sampling distance (GSD)) crop field monitoring and mapping in precision agriculture applications. In this study, we developed a strategy for interand intra-row weed detection in early season maize fields from aerial visual imagery. More specifically, the Hough transform algorithm (HT) was applied to the orthomosaicked images for inter-row weed detection. A semi-automatic Object-Based Image Analysis (OBIA) procedure was developed with Random Forests (RF) combined with feature selection techniques to classify soil, weeds and maize. Furthermore, the two binary weed masks generated from HT and OBIA were fused for accurate binary weed image. The developed RF classifier was evaluated by 5-fold cross validation, and it obtained an overall accuracy of 0.945, and Kappa value of 0.912. Finally, the relationship of detected weeds and their ground truth densities was quantified by a fitted linear model with a coefficient of determination of 0.895 and a root mean square error of 0.026. Besides, the importance of input features was evaluated, and it was found that the ratio of vegetation length and width was the most significant feature for the classification model. Overall, our approach can yield a satisfactory weed map, and we expect that the obtained accurate and timely weed map from UAV imagery will be applicable to realize site-specific weed management (SSWM) in early season crop fields for reducing spraying non-selective herbicides and costs.
KW - UAVs
KW - inter- and intra-row weed detection
KW - feature fusion
KW - OBIA
KW - random forests
KW - hyperparameter tuning
KW - feature evaluation
UR - http://hdl.handle.net/1854/LU-8544720
U2 - 10.1016/j.jag.2017.12.012
DO - 10.1016/j.jag.2017.12.012
M3 - Article
SN - 0303-2434
VL - 67
SP - 43
EP - 53
JO - International Journal of Applied Earth Observations and Geoinformation
JF - International Journal of Applied Earth Observations and Geoinformation
ER -