I-Corps: Video Based Interface for the Live Labelling of Emotional Responses

这个i-Corps项目的更广泛的影响/商业潜力是提供一种负担得起的、能够实时检测情绪状态的可穿戴设备。目前，很少有方法可以在实时和真实环境中客观地评估情绪状态。建议的软硬件平台可能会被娱乐场所用来增强客户体验，以增加销售，改善场馆管理和安全，并支持调度决策。该系统还可以用于提供观众情绪的实时测量和评估内容偏好。这个i-Corps项目开发了一个以可穿戴设备为中心的软硬件平台，用于无约束、非接触式和实时检测情绪峰值的生理关联。该技术使用个性化信号和视频源数据来提供消费者情绪状态的实时测量。该项目开发了一种将创新的数据收集和分析策略与尖端软件和负担得起的可扩展硬件相结合的方法，用于实时检测基于图像的非接触式情绪状态。该技术提供了一种无线、易于部署和可穿戴的设备，能够以有限的功率进行智能处理，非常适合在现实环境中进行大规模数据采集。最后，该项目还在数据科学方面进行了创新，将来自个人消费者的实时生理信号与聚合视频记录相结合，以对群体参与进行建模和预测行为。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact/commercial potential of this I-Corps project is to provide an affordable, wearable device capable of detecting emotional states in real time. Currently, there are few methods to objectively evaluate emotional states in real time and in real-life settings. The proposed software and hardware platform can potentially be used by entertainment venues to enhance the customer experience to increase sales, improve venue management and safety, and support decision making in scheduling. The system can also be used to provide real time measurements of audience emotion and assess content preferences. This I-Corps project develops a software and hardware platform centered on a wearable device for the unconstrained, contactless and live detection of physiological correlates of peak emotion. The technology uses individualized signals along with video-sourced data to provide real-time measures of consumers' emotional state. The project develops an approach combining innovative data collection and analysis strategies with cutting-edge software and affordable, scalable hardware for contactless, image-based detection of emotional states in real-time. The technology provides a wireless, easy-to-deploy, and wearable device capable of intelligent processing with limited power, well-suited for large scale data acquisition in real-world environments. Finally, this project also innovates in data science by combining real-time physiological signals from individual consumers with aggregate video-recordings in order to model group engagement and predict behavior.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.