Generative models-based data labeling for deep networks regression: application to seed maturity estimation from UAV multispectral images
This addresses the challenge of limited labeled data for deep learning in agriculture, specifically for seed maturity monitoring, though it is incremental as it builds on existing UAV and deep learning techniques.
The paper tackles the problem of estimating parsley seed maturity from UAV multispectral images by proposing an automatic data labeling method using parametric and non-parametric models to generate weak labels, which improves neural network generalization and leads to more robust and better-performing deep models.
Monitoring seed maturity is an increasing challenge in agriculture due to climate change and more restrictive practices. Seeds monitoring in the field is essential to optimize the farming process and to guarantee yield quality through high germination. Traditional methods are based on limited sampling in the field and analysis in laboratory. Moreover, they are time consuming and only allow monitoring sub-sections of the crop field. This leads to a lack of accuracy on the condition of the crop as a whole due to intra-field heterogeneities. Multispectral imagery by UAV allows uniform scan of fields and better capture of crop maturity information. On the other hand, deep learning methods have shown tremendous potential in estimating agronomic parameters, especially maturity. However, they require large labeled datasets. Although large sets of aerial images are available, labeling them with ground truth is a tedious, if not impossible task. In this paper, we propose a method for estimating parsley seed maturity using multispectral UAV imagery, with a new approach for automatic data labeling. This approach is based on parametric and non-parametric models to provide weak labels. We also consider the data acquisition protocol and the performance evaluation of the different steps of the method. Results show good performance, and the non-parametric kernel density estimator model can improve neural network generalization when used as a labeling method, leading to more robust and better performing deep neural models.