Automated crop plant counting from very high-resolution aerial imagery
- PDF / 2,603,738 Bytes
- 19 Pages / 439.37 x 666.142 pts Page_size
- 61 Downloads / 214 Views
Automated crop plant counting from very high‑resolution aerial imagery João Valente1,2 · Bilal Sari1 · Lammert Kooistra1 · Henk Kramer3 · Sander Mücher3
© The Author(s) 2020
Abstract Knowing before harvesting how many plants have emerged and how they are growing is key in optimizing labour and efficient use of resources. Unmanned aerial vehicles (UAV) are a useful tool for fast and cost efficient data acquisition. However, imagery need to be converted into operational spatial products that can be further used by crop producers to have insight in the spatial distribution of the number of plants in the field. In this research, an automated method for counting plants from very high-resolution UAV imagery is addressed. The proposed method uses machine vision—Excess Green Index and Otsu’s method—and transfer learning using convolutional neural networks to identify and count plants. The integrated methods have been implemented to count 10 weeks old spinach plants in an experimental field with a surface area of 3.2 ha. Validation data of plant counts were available for 1/8 of the surface area. The results showed that the proposed methodology can count plants with an accuracy of 95% for a spatial resolution of 8 mm/pixel in an area up to 172 m2. Moreover, when the spatial resolution decreases with 50%, the maximum additional counting error achieved is 0.7%. Finally, a total amount of 170 000 plants in an area of 3.5 ha with an error of 42.5% was computed. The study shows that it is feasible to count individual plants using UAV-based off-the-shelf products and that via machine vision/learning algorithms it is possible to translate image data in non-expert practical information. Keywords Plant counting · Crop emergence · UAV RGB imagery · Machine learning · Transfer learning
* João Valente [email protected] 1
Laboratory of Geo‑Information Science and Remote Sensing, Wageningen University & Research, Wageningen, The Netherlands
2
Information Technology Group, Wageningen University & Research, Wageningen, The Netherlands
3
Wageningen Environmental Research, Wageningen University & Research, Wageningen, The Netherlands
13
Vol.:(0123456789)
Precision Agriculture
Introduction Crop monitoring is a critical function within the agricultural production chain. It is important for estimating yield, weed control, phenotyping, or disease detection that have a real impact on the economies of countries and the environment (Hayes and Decker 1996). Improper crop monitoring can lead to a waste of valuable resources such as water and fertilizer. Traditionally crop monitoring required manual labour, as the field manager or the land owner still had to monitor the crops physically. This is time consuming and can be prone to human error (Li et al. 2019). During the last decade, precision agriculture (PA) has aided to decrease the manual labour on the fields by providing crop monitoring solutions that are less subjective, cost-efficient and robust. With recent advancements in technology it has become more feasible to deve
Data Loading...
