Shedding Light on Blind Spots: Developing a Reference Architecture to Leverage Video Data for Process Mining
arXiv:2010.11289 · doi:10.1016/j.dss.2022.113794
Abstract
Process mining is one of the most active research streams in business process management. In recent years, numerous methods have been proposed for analyzing structured process data. Yet, in many cases, it is only the digitized parts of processes that are directly captured from process-aware information systems, and manual activities often result in blind spots. While the use of video cameras to observe these activities could help to fill this gap, a standardized approach to extracting event logs from unstructured video data remains lacking. Here, we propose a reference architecture to bridge the gap between computer vision and process mining. Various evaluation activities (i.e., competing artifact analysis, prototyping, and real-world application) ensured that the proposed reference architecture allows flexible, use-case-driven, and context-specific instantiations. Our results also show that an exemplary software prototype instantiation of the proposed reference architecture is capable of automatically extracting most of the process-relevant events from unstructured video data.
References in corpus (8)
- Deep Learning in Neural Networks: An Overview
- The Kinetics Human Action Video Dataset
- Deep Learning in Video Multi-Object Tracking: A Survey
- An Empirical Evaluation of Deep Learning on Highway Driving
- Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding
- Predictive Process Monitoring Methods: Which One Suits Me Best?
- Privacy and Confidentiality in Process Mining -- Threats and Research Challenges
- AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions