Nature Paper on Camera-Equipped Toilet

Vice.com: Nature publishes a Stanford University paper on camera usage in the toilet "A mountable toilet system for personalized health monitoring via the analysis of excreta" by Seung-min Park, Daeyoun D. Won, Brian J. Lee, Diego Escobedo, Andre Esteva, Amin Aalipour, T. Jessie Ge, Jung Ha Kim, Susie Suh, Elliot H. Choi, Alexander X. Lozano, Chengyang Yao, Sunil Bodapati, Friso B. Achterberg, Jeesu Kim, Hwan Park, Youngjae Choi, Woo Jin Kim, Jung Ho Yu, Alexander M. Bhatt, Jong Kyun Lee, Ryan Spitler, Shan X. Wang & Sanjiv S. Gambhir. Seoul Song Do Hospital, Salesforce Research, Case Western Reserve University, University of Toronto, Leiden University, Pohang University of Science and Technology, and Catholic University of Korea contributed to this work too.

"The ‘smart’ toilet, which is self-contained and operates autonomously by leveraging pressure and motion sensors, analyses the user’s urine using a standard-of-care colorimetric assay that traces red–green–blue values from images of urinalysis strips, calculates the flow rate and volume of urine using computer vision as a uroflowmeter, and classifies stool according to the Bristol stool form scale using deep learning, with performance that is comparable to the performance of trained medical personnel. Each user of the toilet is identified through their fingerprint and the distinctive features of their anoderm, and the data are securely stored and analysed in an encrypted cloud server. The toilet may find uses in the screening, diagnosis and longitudinal monitoring of specific patient populations."

To estimate the speed, size, and other spatial parameters, the prototype system reconstructs a 3D scene image using a stereo pair of GoPro Hero 7 cameras in 1.2MP 240fps high speed mode. Another two cameras are used for color and shape analysis and a person identification.