Extending generic BPM with computer vision capabilities

Abstract

Leveraging Business Process Management (BPM) is key to enabling business agility in organizations. Video analysis is a nascent technology that allows for innovative sensing and understanding of a large family of tasks across many diverse application domains. This includes interactions between persons, objects, and the environment in domains such as Healthcare and Retail, as well as more general activities (e.g., in video-surveillance or Transportation). It can, therefore, enable better BPM by giving the opportunity to augment, complement, and improve the observation, description, monitoring, triggering, and execution of a broad array of tasks, including new ones that can only be described visually. This may be of particular interests in cyber-physical systems where interactions between human agents and artificial agents can be tracked and managed in the context of various business processes. This paper proposes a way to integrate video data and analysis into the control flow of business processes, in a way that enables the seamless augmentation of business process execution with information from the observable environment.