Sleep activity is one crucial factor for understanding the quality of human life. However, traditional sleep monitoring systems are not well accepted by users. The main reason is that these systems use cameras or require devices to be attached to human body, which are inconvenient, uncomfortable, and privacy-invasive for users. We need a device-free and non-privacy invasive solution that can monitor people’s sleep activity.
In this project, the student is required to develop a device-free, non-privacy invasive indoor human posture recognition system using low-resolution infrared sensors. The system should recognize postures of sleeping using machine learning models.
The student must implement the system, including embedded hardware and machine learning based posture recognition model.
- The embedded hardware system includes distributed IR sensors deployed in a room, and a central server used for data processing.
- The data processing server is used for machine learning based posture recognition.
In the experiment, the sleeping posture and temperature of the user are aggregated for analyzing the sleeping activity. There are already many existing solutions for posture recognition using neural network models. The challenge is that the IR images have very low resolution. The postures in these images are unclear, and become more fuzzy when the user is under sheet. The student must deploy distributed IR sensors in a room to monitor the sleeping activity of the user from multiple angles. The system should make posture recognition based on the combination of multiple IR images.
- Munkhjargal Gochoo ; Tan-Hsu Tan ; Tsedevdorj Batjargal ; Oleg Seredin ; Shih-Chia Huang. Device-Free Non-Privacy Invasive Indoor Human Posture Recognition Using Low-Resolution Infrared Sensor-Based Wireless Sensor Networks and DCNN. 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC). 7-10 Oct. 2018.
- Munkhjargal Gochoo ; Tan-Hsu Tan ; Shih-Chia Huang ; Tsedevdorj Batjargal ; Jun-Wei Hsieh. Novel IoT-Based Privacy-Preserving Yoga Posture Recognition System Using Low-Resolution Infrared Sensors and Deep Learning. IEEE Internet of Things Journal ( Volume: 6 , Issue: 4 , Aug. 2019 )