Instance Segmentation: New Technologies, Metrics, and Applications for Computer Vision

Instance segmentation is an advanced technique in computer vision that focuses on identifying and classifying each individual object in an image at pixel level. Unlike Semantic Segmentation, which groups pixels of similar objects without distinguishing between different instances, Instance Segmentation assigns unique labels to each object, even if they are in the same class. This allows not only to detect the presence and category of objects in an image, but also to locate each specific instance and clearly distinguish them from each other.

This problem not only drives the technical and theoretical understanding of how machines see and process digital images, but also has a direct impact on various industries and sectors where computer vision is an essential part of the system.

In this talk, we present current deep learning-based technologies, metrics used for their evaluation, and a review of general and specific datasets in both general and drone-specific contexts. The results of this study provide a compendium of easily implementable deep learning based technologies. This lecture aims to accelerate the process of using and understanding Instance Segmentation technologies for the viewer.

José Manuel Molina López holds a PhD in Telecommunications Engineering from the Universidad Politécnica de Madrid.

He is currently Professor of Computer Science and Artificial Intelligence at Universidad Carlos III de Madrid, the director of the Applied Artificial Intelligence group, and Delegate of the Rector for the Colmenarejo campus.

He previously held the position of director of the graduate program in Computer Science and Technology at Universidad Carlos III de Madrid, director of the Department of Computer Science at Universidad Carlos III de Madrid, Vice Rector of Students, Residences and Cultural Activities, assistant to the vice rector of the Colmenarejo campus and deputy director of the degree of Computer Engineering.

In relation to research, he develops several public and private research projects, focused on the application of Artificial Intelligence techniques to various problems related to engineering, social and biological sciences. He is the author of more than 100 articles in international journals that appear in the JCR, 80 articles in peer-reviewed journals, more than 250 presentations in international conferences, 15 books and more than 15 chapters in collective works.

His areas of interest focus on Artificial Intelligence topics such as Machine Learning, Multiagent Systems, Fuzzy Reasoning, Deep Learning, Evolutionary Computation and Decision Making, and their application to various topics such as data analytics, data fusion, computer vision and the development of Drones, IoT and Ambient Intelligence systems.