Plant Monitoring
Plant monitoring research focuses on developing automated and efficient methods for assessing plant health and growth, primarily to optimize agricultural practices and resource management. Current efforts leverage computer vision, employing deep learning architectures like YOLO and ResNet for image analysis and object detection, alongside machine learning algorithms for data analysis and prediction of plant traits. These advancements enable precise phenotyping, early disease detection, and improved irrigation strategies, ultimately contributing to increased crop yields and sustainable agriculture. Furthermore, the integration of IoT sensors and AI-powered language models facilitates real-time plant monitoring and communication, enhancing human-plant interaction and promoting data-driven decision-making.
Papers
Model Pruning Enables Localized and Efficient Federated Learning for Yield Forecasting and Data Sharing
Andy Li, Milan Markovic, Peter Edwards, Georgios Leontidis
Towards Autonomous Selective Harvesting: A Review of Robot Perception, Robot Design, Motion Planning and Control
Vishnu Rajendran S, Bappaditya Debnath, Bappaditya Debnath, Sariah Mghames, Willow Mandil, Soran Parsa, Simon Parsons, Amir Ghalamzan-E
Machine Vision System for Early-stage Apple Flowers and Flower Clusters Detection for Precision Thinning and Pollination
Salik Ram Khanal, Ranjan Sapkota, Dawood Ahmed, Uddhav Bhattarai, Manoj Karkee