Student Session: Turning Over Detecting Using Super-Resolution Thermal Image

A low resolution infrared camera can use to collect the data of our daily activity, and protect privacy. However, pose detection on an extremely low resolution image will be a big challenge to deal with. Many researches show that Super-resolution may improve the accuracy of object detection on low resolution images. In this work, we detect the turning over while sleeping with low-resolution thermal sensors. To improve the accuracy of detection, we fuse the data from multiple sensors and use SRCNN to enhance the resolution. We also propose a method to reduce the noise caused by the residual body temperature on bed after turn over while detect the pose and turning over. The accuracy of pose detection is 65%, and the turning over detection has 50% recall rate and 83% precision.