Impact of Analog Memories Non-Idealities on the Performance of Foreground Detection Algorithms
- 1 May 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
The high number of memory accesses in background subtraction algorithms constraints the choice of the memory topology of an analog implementation of a hardware-oriented version of the well-known PBAS algorithm (HO-PBAS). As the first step towards the implementation of a CMOS vision chip with per-pixel processing to run the HO-PBAS, this work assesses the impact of the circuit non-idealities of the three main analog memory topologies into the segmentation result on the CDNET database.Keywords
This publication has 9 references indexed in Scilit:
- Low-Power CMOS Vision Sensor for Gaussian Pyramid ExtractionIEEE Journal of Solid-State Circuits, 2016
- Background Modeling and Foreground Detection for Video Surveillance2014
- Traditional and recent approaches in background modeling for foreground detection: An overviewComputer Science Review, 2014
- The Internet of Things—A survey of topics and trendsInformation Systems Frontiers, 2014
- A 33 $\mu$W 64$\,\times\,$64 Pixel Vision Sensor Embedding Robust Dynamic Background Subtraction for Event Detection and Scene InterpretationIEEE Journal of Solid-State Circuits, 2013
- ViBe: A Universal Background Subtraction Algorithm for Video SequencesIEEE Transactions on Image Processing, 2010
- Image Processing Vision Systems: Standard Image Sensors Versus RetinasIEEE Transactions on Instrumentation and Measurement, 2007
- A general-purpose processor-per-pixel analog SIMD vision chipIEEE Transactions on Circuits and Systems I: Regular Papers, 2005
- An 0.5-μm CMOS analog random access memory chip for TeraOPS speed multimedia video processingIEEE Transactions on Multimedia, 1999