Photogrammetry and Remote Sensing

- Photogrammetry Tool for Precision Agriculture

Photogrammetry is the science and technology of obtaining reliable information about physical objects and the environment through the process of recording, measuring, and interpreting photographic images and patterns of electromagnetic radiation images and other phenomena.

Traditionally, farming is practiced by performing tasks such as planting or harvesting on a predetermined schedule. However, collecting real-time data can help farmers make the best decisions about planting, fertilizing and harvesting crops. This method is called precision agriculture. In this context, there is growing interest in technological tools adapted to crop management strategies. Therefore, this study aims to analyze and compare photogrammetry-based image processing tools in the agricultural field. 

Additionally, a land case study involved using a drone to take multiple photos and analyzing them using photogrammetry software to obtain an orthophoto. This software can help with relevant biomass analysis, drought stress, irrigation scheduling, forecasting agricultural production, monitoring nutrients, pests and diseases affecting photographed crops.

- Intelligent Remote Sensing for Precision Agriculture

Agriculture-related remote sensing applications are rapidly becoming the norm in precision agriculture. Accurate, consistent and reliable information on field conditions during the growing season optimizes field management for precision agriculture, ensuring sustainable agricultural production and desirable environmental outcomes. 

With more and more available, affordable, and compatible platforms (e.g., Unmanned Aerial Vehicles - UAVs) and recent advances in sensors (e.g., lightweight multispectral, hyperspectral, thermal, and LiDAR), unprecedented High spatial, spectral and temporal resolution images for precision agriculture practices. 

Data collection, processing and analysis based on artificial intelligence (AI) and quantitative modeling have shown some intelligence in precision agriculture, but still face many technological challenges in preprocessing, data extraction and synthesis, quantitative analysis, information transmission, etc. Due to multi-scale, multi-sensor and multi-platform, multi-temporal Earth observation. 

Therefore, new research is needed to develop improved image acquisition and transmission techniques, address various issues related to image preprocessing and cross-sensor integration, simplify data processing for field-level plant condition retrieval, and implement artificial intelligence to support decision-making.