Automotive Interior Sensing - Towards a Synergetic Approach between Anomaly Detection and Action Recognition Strategies

• Type: Article in International Conference Proceedings Book
• Date: 2020

Authors

Augusto, P (Author) Other; Jaime S Cardoso (Author) FEUP; Fonseca, J (Author) Other

Conference proceedings International

Title: 4th IEEE International Conference on Image Processing, Applications and Systems, IPAS 2020, Virtual Event, Italy, December 9-11, 2020

Pages: 162-167

4th IEEE International Conference on Image Processing, Applications and Systems, IPAS 2020

9 December 2020 through 11 December 2020

Indexing

Scopus - 2 Citations

Other information

Authenticus ID: P-00V-QX9

DOI: 10.1109/ipas50080.2020.9334942

Abstract (EN): With the appearance of Shared Autonomous Vehicles there will no longer be a driver responsible for maintaining the car interior and well-being of passengers. To counter this, it is imperative to have a system that is able to detect any abnormal behaviors, more specifically, violence between passengers. Traditional action recognition algorithms build models around known interactions but activities can be so diverse, that having a dataset that incorporates most use cases is unattainable. While action recognition models are normally trained on all the defined activities and directly output a score that classifies the likelihood of violence, video anomaly detection algorithms present themselves as an alternative approach to build a good discriminative model since usually only non-violent examples are needed. This work focuses on anomaly detection and action recognition algorithms trained, validated and tested on a subset of human behavior video sequences from Bosch's internal datasets. The anomaly detection network architecture defines how to properly reconstruct normal frame sequences so that during testing, each sequence can be classified as normal or abnormal based on its reconstruction error. With these errors, regularity scores are inferred showing the predicted regularity of each frame. The resulting framework is a viable addition to traditional action recognition algorithms since it can work as a tool for detecting unknown actions, strange/violent behaviors and aid in understanding the meaning of such human interactions.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 5