Speaker
Description
Addressing food insecurity and optimizing food production in urban farming requires innovative, scalable solutions. This study presents an interdisciplinary approach integrating planning, geography, and data science to develop a drone image-based methodology for vegetable detection and yield estimation on mid-size urban farms. The research focuses on three urban farms located in or near Glassboro, New Jersey, where drone imagery was captured during the summer of 2024 to model three vegetable groups: eggplants, tomatoes, and peppers.
Drone images were processed using advanced computer vision techniques to identify individual plants and estimate their yield. The methodology employed convolutional neural networks (CNNs) trained on annotated imagery to detect plant shapes, orientations, and leaf concentrations characteristic of each vegetable type. A complementary data pipeline incorporated geospatial analysis to map plant distributions and refine yield estimates. Field data were collected concurrently to validate the model outputs, ensuring reliability and adaptability across different urban farming contexts.
The modeling demonstrated robust detection accuracy and precise yield estimations, highlighting its potential for practical application. This approach offers a significant advantage to mid-size urban farmers by providing timely insights into crop health and yield, enabling better planning for harvest and market logistics. Unlike traditional methods, which are labor-intensive and prone to error, drone-based modeling delivers a scalable and cost-effective alternative, reducing the workload for farmers and enhancing decision-making efficiency.
Beyond its direct application to urban farms, this study contributes to addressing larger societal challenges, including food insecurity and sustainable food systems. Mid-sized urban farms often play a critical role in community-based food networks, particularly in areas with limited access to fresh produce. By optimizing yield estimation, farmers can better anticipate supply, reduce waste, and ensure consistent availability of nutritious food. This is particularly important in underserved areas where urban farms may serve as the primary source of fresh vegetables.
From a methodological perspective, this study underscores the power of interdisciplinary collaboration in solving complex real-world problems. The integration of drone technology with advanced data science tools provides a replicable framework that can be adapted for various crops and farming scales. Additionally, this work demonstrates the utility of drone-based modeling in bridging the gap between technology and sustainable agricultural practices.
In conclusion, the proposed drone image-based modeling system offers a promising solution to enhance yield estimation and operational efficiency for mid-size urban farms. Its broader implications extend to improving food security and contributing to sustainable urban agriculture, addressing critical challenges in the global food system.
References
Inoue, Y., 2020. Satellite-and drone-based remote sensing of crops and soils for smart farming–a review. Soil Science and Plant Nutrition, 66(6), pp.798-810.
Oré, G., Alcântara, M.S., Góes, J.A., Oliveira, L.P., Yepes, J., Teruel, B., Castro, V., Bins, L.S., Castro, F., Luebeck, D. and Moreira, L.F., 2020. Crop growth monitoring with drone-borne DInSAR. Remote Sensing, 12(4), p.615.
Nowakowski, A., Mrziglod, J., Spiller, D., Bonifacio, R., Ferrari, I., Mathieu, P.P., Garcia-Herranz, M. and Kim, D.H., 2021. Crop type mapping by using transfer learning. International Journal of Applied Earth Observation and Geoinformation, 98, p.102313.
Nowakowski, A., Spiller, D., Cremer, N., Bonifacio, R., Marszalek, M., Garcia-Herranz, M., Mathieu, P.P. and Kim, D.H., 2021, July. Ai opportunities and challenges for crop type mapping using Sentinel-2 and drone data. In 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS (pp. 258-261). IEEE.
Kalamkar, R.B., Ahire, M.C., Ghadge, P.A., Dhenge, S.A. and Anarase, M.S., 2020. Drone and its Applications in Agriculture. International Journal of Current Microbiology and Applied Sciences, 9(6), pp.3022-3026.
| Keywords | drone; AI, urban farms, crop type, crop yield |
|---|---|
| Best Congress Paper Award | No |
