Please use this identifier to cite or link to this item:
|Title:||iNEMO : a multi-sensor real-time human activity monitoring system||Authors:||Qian, Siyuan||Keywords:||DRNTU::Engineering||Issue Date:||2013||Abstract:||The iNEMO module family of ST Microelectronics integrates series of sensors with rapid and accurate computation core: offer more comprehensive, succinct and simple packaging solution compare to discrete sensors or components. In this project, a combination of iNEMO module includes LSM330D integrates accelerometer and gyroscope, embedded on the motherboard which bridge the communication between the sensor and end platform. The control motherboard mainly consists of a STM32F103RET6 high-performance ARM Cortex™-M3 microcontroller, a DIL24 socket to mount different allowable sensor devices, and wireless adapter pins for compatible Bluetooth modules. The designed user application intends to develop the real-time human activity monitoring system by acquiring, analyzing the wireless transmitted acceleration and angular detection from the iNEMO inertial module as well as providing the instantaneous momentum information to match with data generated by computer vision image processing. The accomplished system contributes the safety assurance to the elderly, solitary personnel in Singapore. The project has been divided into two branches. One is applying computer vision methodology to process images of indoor human behavior instance. The other branch, which assigned for my final year project, was to implement the serial communication to acquire raw data through Bluetooth transmission, eliminate of preliminary noise and covert acceleration to velocity of movement. The emphases of the project are on the spontaneous serial port data transmissions, and real-time momentum data collections. The accuracy of processed momentum data with noise elimination by using kalman filter will affect the functionally of the application and matching with the other part of project. Furthermore, the conversion of data is required as the matching data from computer vision is in pixel unit. The project can work independently to provide supporting data for any other relevant projects.||URI:||http://hdl.handle.net/10356/53407||Rights:||Nanyang Technological University||Fulltext Permission:||restricted||Fulltext Availability:||With Fulltext|
|Appears in Collections:||EEE Student Reports (FYP/IA/PA/PI)|
Updated on Nov 28, 2020
Updated on Nov 28, 2020
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.