Video object detection for privacy-preserving patient monitoring in intensive care

TL;DR

This paper introduces a novel method for improving video object detection in privacy-sensitive, blurred ICU footage by exploiting temporal information, resulting in higher detection accuracy and faster training.

Contribution

The authors propose a new approach that leverages temporal consistency by repurposing color channels, enhancing detection performance with off-the-shelf detectors under privacy constraints.

Findings

Outperforms YOLOv5 baseline by +1.7% mAP@.5

Training is over ten times faster on proprietary data

Effective in preliminary experiments for privacy-preserving video analysis

Abstract

Patient monitoring in intensive care units, although assisted by biosensors, needs continuous supervision of staff. To reduce the burden on staff members, IT infrastructures are built to record monitoring data and develop clinical decision support systems. These systems, however, are vulnerable to artifacts (e.g. muscle movement due to ongoing treatment), which are often indistinguishable from real and potentially dangerous signals. Video recordings could facilitate the reliable classification of biosignals using object detection (OD) methods to find sources of unwanted artifacts. Due to privacy restrictions, only blurred videos can be stored, which severely impairs the possibility to detect clinically relevant events such as interventions or changes in patient status with standard OD methods. Hence, new kinds of approaches are necessary that exploit every kind of available information due to the reduced information content of blurred footage and that are at the same time easily implementable within the IT infrastructure of a normal hospital. In this paper, we propose a new method for exploiting information in the temporal succession of video frames. To be efficiently implementable using off-the-shelf object detectors that comply with given hardware constraints, we repurpose the image color channels to account for temporal consistency, leading to an improved detection rate of the object classes. Our method outperforms a standard YOLOv5 baseline model by +1.7% mAP@.5 while also training over ten times faster on our proprietary dataset. We conclude that this approach has shown effectiveness in the preliminary experiments and holds potential for more general video OD in the future.