Low power high-performance smart camera system based on SCAMP vision sensor

Carey, Stephen J.; Barr, David R. W.; Dudek, Piotr

doi:10.1016/j.sysarc.2013.03.016

Cited by 17 publications

(13 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite the available computational power and the proven functionalities, the power consumption of this system still exceeds the targeted consumption for always-on IoT applications due to the not-optimized processing platform. A similar architecture to the one reported in this work is described in [25]. A low-power smart camera contains a vision chip with a large array of processing elements and a low-power FPGA, which is placed between a digital MCU and the sensor.…”

Section: Related Workmentioning

confidence: 99%

A Sub-mW IoT-Endnode for Always-On Visual Monitoring and Smart Triggering

Rusci

Rossi

Farella

et al. 2017

IEEE Internet Things J.

View full text Add to dashboard Cite

Abstract-This work presents a fully-programmable Internet of Things (IoT) visual sensing node that targets sub-mW power consumption in always-on monitoring scenarios. The system features a spatial-contrast 128x64 binary pixel imager with focalplane processing. The sensor, when working at its lowest power mode (10µW at 10 fps), provides as output the number of changed pixels. Based on this information, a dedicated camera interface, implemented on a low-power FPGA, wakes up an ultralow-power parallel processing unit to extract context-aware visual information. We evaluate the smart sensor on three alwayson visual triggering application scenarios. Triggering accuracy comparable to RGB image sensors is achieved at nominal lighting conditions, while consuming an average power between 193µW and 277µW , depending on context activity. The digital subsystem is extremely flexible, thanks to a fully-programmable digital signal processing engine, but still achieves 19x lower power consumption compared to MCU-based cameras with significantly lower on-board computing capabilities.

show abstract

Section: Related Workmentioning

confidence: 99%

A Sub-mW IoT-Endnode for Always-On Visual Monitoring and Smart Triggering

Rusci

Rossi

Farella

et al. 2017

IEEE Internet Things J.

View full text Add to dashboard Cite

show abstract

“…The interested reader can find a detailed description in [14]. Among these works, the project scamp by P. Dudeck is one of the most well-known [15]. Other contributions in the same vein can be found in [16,17].…”

Section: Previous Workmentioning

confidence: 99%

DreamCam: A modular FPGA-based smart camera architecture

Birem

Berry

2014

Journal of Systems Architecture

View full text Add to dashboard Cite

To cite this version:Merwan Birem, François Berry. DreamCam: A modular FPGA-based smart camera architecture. Journal of Systems Architecture, Elsevier, 2014, 60 (6) b s t r a c tDreamCam is a modular smart camera constructed with the use of an FPGA like main processing board. The core of the camera is an Altera Cyclone-III associated with a CMOS imager and six private Ram blocks. The main novel feature of our work consists in proposing a new smart camera architecture and several modules (IP) to efficiently extract and sort the visual features in real time. In this paper, extraction is performed by a Harris and Stephen filtering associated with customized modules. These modules extract, select and sort visual features in real-time. As a result, DreamCam (with such a configuration) provides a description of each visual feature in the form of its position and the grey-level template around it.

show abstract

“…While changes are rapidly detected and processed via binary spikes, no pixel intensity information is captured. In [5] pixels are processed on the focal plane to remove redundant data and output only salient areas of pixels; by doing so energy consumption is quantifiably reduced. Recently the Chronocam has been introduced.…”

Section: Introductionmentioning

confidence: 99%