Deep Detection and Segmentation Models for Plant Physiology and Precision Agriculture

Ponente: Ángela Casado García (Grupo PSYCOTRIP, Universidad de La Rioja).

Lugar: Seminario Mirian Andrés (Edificio CCT).

Hora: miércoles 8 de noviembre de 2023, 12:00.

Resumen: In this thesis, we have focused on developing methods to improve the performance of deep object detection models. To achieve such a goal, we have used ensemble methods to devise an algorithm that enhances the accuracy and robustness of object detection models. Moreover, the proposed algorithm is the basis for defining semi-supervised learning techniques that reduce the number of annotated images that are required to train object detection models. In addition, we have simplified the creation and use of detection models by building an easy-to-use graphical interface. The developed methods and tools are not only applicable to object detection problems, but we have generalised them to a different computer vision task that is semantic segmentation. Finally, our work is not only theoretical, but it has also been applied to tackle actual problems in plant physiology and precision agriculture.

Nota: la charla se trata de una prueba de tiempo de la presentación de la Tesis Doctoral que Ángela realizará el día 16 de noviembre a las 10:00 en la Sala de Grados del Edificio CCT.

Smart perception systems in industrial and agricultural domains

PonentesRoberto Marani (Investigador Predoctoral, Istituto di Sistemi e Tecnologie Industriali Intelligenti per il Manifatturiero Avanzato, Intelligent Sensing and Perception Group. Bari, Italia),

Lugar: online (

Hora: miércoles 5 de mayo, 10:00

Resumen: Advanced perception is a key enabling technology for shaping innovation in any physical environment. Low-cost technologies implementing multisensor systems, such as sensor networks and/or visual systems, cooperate with new methodologies assisted by computational intelligence to support people in making decisions in planning and controlling automatic devices for several application fields. The complete design of such systems is the main goal of the Intelligent Sensing and Perception (ISP) group, whose research is mainly targeted at the acquisition, fusion, processing, and interpretation of multisensor data. This talk will present several examples of advanced perception systems endowed with smart abilities for industrial diagnostics, human assistance, and precision agriculture. After a brief presentation of the activities of the ISP group, it will go through two case studies regarding i) innovative quality control procedures for defect detection in aeronautic structures and ii) image acquisition and processing for on-field yield analysis in precision agriculture. Possible opportunities for further cooperation in the very next future will be also presented.