arXiv ·
Researchers in Saudi Arabia have developed a deep learning framework for automated counting and geolocation of palm trees using aerial images. The system uses a Faster R-CNN model trained on a dataset of 10,000 palm tree instances collected in the Kharj region using DJI drones. Geolocation accuracy of 2.8m was achieved using geotagged metadata and photogrammetry techniques.
arXiv ·
Researchers have developed MARTS (Modular Agricultural Robot for Targeted Spraying), a low-cost robotic platform designed for precise disease control in greenhouse tomato production. MARTS integrates a mobile base, a UR5 manipulator, a modular spraying end-effector, and an Intel RealSense RGB-D camera, utilizing a vision-language model for disease detection. Deployed at the SILAL commercial greenhouse in Al Ain, UAE, the robot successfully treated 312 diseased leaves across 12 trials, achieving 92.4% targeting success and a 71% reduction in pesticide volume compared to broadcast spraying. The spraying subsystem costs significantly less than comparable systems, demonstrating the feasibility of accurate leaf-level targeting with commodity hardware. Why it matters: This innovation provides a precise, cost-effective, and environmentally friendly solution for agricultural disease management, reducing pesticide use and worker exposure, with successful application and cost efficiency demonstrated in the UAE.
KAUST ·
KAUST's Hydrology and Land Observation (Halo) lab, led by Matthew McCabe, is using drones and satellites to monitor agricultural water usage in Saudi Arabia. They employ thermal cameras, sensors, and imagery from CubeSats to map crop types, health, and water stress. The team uses machine learning and AI to analyze the images, aiming to promote sustainable water management. Why it matters: This research addresses critical water scarcity issues in the region by providing data-driven insights for more efficient agricultural practices.
arXiv ·
YOLO26-RipeLoc Lite is a new lightweight deep learning architecture designed for simultaneous detection, ripeness classification, and center-point localization of greenhouse tomatoes for robotic harvesting. The model incorporates a Lightweight Feature Pyramid Network, a Ripeness-Aware Attention Module, and a Compact Detection Head for efficient and precise operation. Evaluated on a custom dataset from the SILAL greenhouse in Abu Dhabi, UAE, it achieved a mAP@0.5 of 92.9% with only 2.38 million parameters, outperforming existing YOLO models in accuracy-efficiency. Why it matters: This research provides an efficient and accurate solution for automating a critical agricultural process, enhancing food security and technological capabilities in the region's greenhouse farming.
arXiv ·
The paper introduces a framework for camel farm monitoring using a combination of automated annotation and fine-tune distillation. The Unified Auto-Annotation framework uses GroundingDINO and SAM to automatically annotate surveillance video data. The Fine-Tune Distillation framework then fine-tunes student models like YOLOv8, transferring knowledge from a larger teacher model, using data from Al-Marmoom Camel Farm in Dubai.