Eyes of Things.

Embedded systems control and monitor a great deal of our reality. While some "classic" features are intrinsically necessary, such as low power consumption, rugged operating ranges, fast response and low cost, these systems have evolved in the last few years to emphasize connectivity functions, thus contributing to the Internet of Things paradigm. A myriad of sensing/computing devices are being attached to everyday objects, each able to send and receive data and to act as a unique node in the Internet. Apart from the obvious necessity to process at least some data at the edge (to increase security and reduce power consumption and latency), a major breakthrough will arguably come when such devices are endowed with some level of autonomous "intelligence". Intelligent computing aims to solve problems for which no efficient exact algorithm can exist or for which we cannot conceive an exact algorithm. Central to such intelligence is Computer Vision (CV), i.e., extracting meaning from images and video. While not everything needs CV, visual information is the richest source of information about the real world: people, places and things. The possibilities of embedded CV are endless if we consider new applications and technologies, such as deep learning, drones, home robotics, intelligent surveillance, intelligent toys, wearable cameras, etc. This paper describes the Eyes of Things (EoT) platform, a versatile computer vision platform tackling those challenges and opportunities.

Facial Image Analysis for Fully Automatic Prediction of Difficult Endotracheal Intubation.

GOAL: Difficult tracheal intubation is a major cause of anesthesia-related injuries with potential life threatening complications. Detection and anticipation of difficult airway in the preoperative period is, thus, crucial for the patients' safety. We propose an automatic face-analysis approach to detect morphological traits related to difficult intubation and improve its prediction. METHODS: For this purpose, we have collected a database of 970 patients including photos, videos, and ground truth data. Specific statistical face models have been learned using the faces in our database providing an automated parametrization of the facial morphology. The most discriminative morphological features are selected through the importance ranking provided by the random forest algorithm. The random forest approach has also been used to train a classifier on these selected features. We compare a threshold tuning method based on class prior with two methods, which learn an optimal threshold on a training set for tackling the inherent imbalanced nature of the database. RESULTS: Our fully automated method achieves an AUC of 81.0% in a simplified experimental setup, where only easy and difficult patients are considered. A further validation on the entire database has proven that our method is applicable for real-world difficult intubation prediction, with AUC = 77.9%. CONCLUSION: The system performance is in line with the state-of-the-art medical diagnosis, based on ratings provided by trained anesthesiologists, whose assessment is guided by an extensive set of criteria. SIGNIFICANCE: We present the first completely automatic and noninvasive difficult intubation detection system that is suitable for use in clinical settings.