A Spatio-Temporal Ensemble Deep Learning Architecture for Real-Time Defect Detection during Laser Welding on Low Power Embedded Computing Boards.
Christian KnaakJakob von EßenMoritz KrögerFrederic SchulzePeter AbelsArnold GillnerPublished in: Sensors (2021)
Keyphrases
- low power
- vlsi architecture
- deep learning
- defect detection
- real time
- low cost
- high speed
- power consumption
- signal processor
- low power consumption
- single chip
- embedded systems
- unsupervised learning
- cmos technology
- unsupervised feature learning
- machine learning
- weakly supervised
- vlsi implementation
- feature extraction
- moving objects
- image sequences
- power dissipation
- mixed signal
- logic circuits
- gate array
- training set
- training data
- image sensor
- mental models
- text classification
- text mining
- feature selection