Architecture design for a low-cost and low-complexity foreground object segmentation with Multi-model Background Maintenance algorithm

2009 ◽  
Author(s):  
De-Zhang Peng ◽  
Chung-Yuan Lin ◽  
Wen-Tsai Sheu ◽  
Tsung-Han Tsai
Keyword(s):  
Object Segmentation ◽  
Low Cost ◽  
Low Complexity ◽  
Architecture Design ◽  
Foreground Object ◽  
Model Background ◽  
Background Maintenance

scholarly journals Real-time Foreground Object Segmentation Networks using Long and Short Skip Connections

2021 ◽  
Author(s):  
Cong Lin ◽  
Shijie Zhuang ◽  
Shaodi You ◽  
Xiaoxiang Liu ◽  
Zhiyu Zhu
Keyword(s):  
Real Time ◽  
Object Segmentation ◽  
Foreground Object

scholarly journals Recurrent Neural Network for Human Activity Recognition in Embedded Systems Using PPG and Accelerometer Data

Electronics ◽  
2021 ◽  
Vol 10 (14) ◽  
pp. 1715
Author(s):  
Michele Alessandrini ◽  
Giorgio Biagetti ◽  
Paolo Crippa ◽  
Laura Falaschetti ◽  
Claudio Turchetti
Keyword(s):  
Neural Network ◽  
Embedded System ◽  
Activity Recognition ◽  
Human Activity ◽  
Recurrent Neural Network ◽  
Low Cost ◽  
Low Complexity ◽  
Human Activity Recognition ◽  
Motion Artifacts ◽  
Accelerometer Data

Photoplethysmography (PPG) is a common and practical technique to detect human activity and other physiological parameters and is commonly implemented in wearable devices. However, the PPG signal is often severely corrupted by motion artifacts. The aim of this paper is to address the human activity recognition (HAR) task directly on the device, implementing a recurrent neural network (RNN) in a low cost, low power microcontroller, ensuring the required performance in terms of accuracy and low complexity. To reach this goal, (i) we first develop an RNN, which integrates PPG and tri-axial accelerometer data, where these data can be used to compensate motion artifacts in PPG in order to accurately detect human activity; (ii) then, we port the RNN to an embedded device, Cloud-JAM L4, based on an STM32 microcontroller, optimizing it to maintain an accuracy of over 95% while requiring modest computational power and memory resources. The experimental results show that such a system can be effectively implemented on a constrained-resource system, allowing the design of a fully autonomous wearable embedded system for human activity recognition and logging.

Performance Optimization Based Spectrum Analysis on Optical Fiber Raman Amplifier with Backward Pumping

2012 ◽  
Vol 263-266 ◽  
pp. 1004-1007 ◽  
Author(s):  
Li Ying Liu ◽  
Yan Huang ◽  
Chun Yu Liu ◽  
Xin Ming Zhang ◽  
Jiu Ru Yang
Keyword(s):  
Optical Fiber ◽  
Spectrum Analysis ◽  
Performance Optimization ◽  
Low Cost ◽  
Low Complexity ◽  
Gain Bandwidth ◽  
Raman Amplifier ◽  
Fiber Raman Amplifier ◽  
Output Performance ◽  
Output Characteristics

Optical fiber Raman amplifier (OFRA) with wide and flat gain bandwidth has been widely applied in the fields of optical communication, sensing and measurement. However, the performance optimization is always one of the hot topics in the study of OFRA, because its output characteristics are hardly dependent to some key designing parameters. In this paper, to overcome the problems above, we adopt a spectrum analysis based method to study the output performance of an OFRA system with backward pumping. By simulating the operation of the OFRA system, its output characteristics are first showed easily, with the advantages of real time, low cost, and low complexity. Further, according to the numerical results obtained, the optimal parameters of an OFRA system are determinate, and the performance in terms of output power, signal noise ratio, and the level of gain flatness is improved and optimized obviously.

Sign in / Sign up

Export Citation Format

Share Document