Image and video processing technologies are experiencing a rapid revolution driven by the ever growing computational power of edge devices. Applications benefitting from this revolution include self-driving vehicles, multi-robot systems, wide-area surveillance, disaster management and various Internet of Things applications for smart cities and smart homes. This tutorial will offer an overview of the key features and algorithms for modern multi-camera video analytics and will cover the challenges associated to their practical implementation. Participants will learn the key elements of such multi-camera systems and to design accurate and robust algorithms that understand a variety of dynamic scenes, and adapt to different operational conditions. The tutorial will consist of theoretical explanations followed by examples using software that will be distributed to the participants.