A smart sensor-based vision system: implementation and evaluation

Abstract

These days, smart home applications such as concierge service for residents, home appliance control, and so on are attracting attention. To realize these applications, we need a system which recognizes various human activities accurately with a low cost device. There are many studies on the activity recognition in a smart home. We also have proposed an activity recognition technique in a smart home by utilizing digital-output-PIR (passive infrared) sensors, door sensors, and power meters. However, the study has an unsolved issue: we cannot distinguish similar activities happening at the same place, for example, "eating" and "reading" while sitting on a sofa. In order to cope with this challenge, we introduce ALPAS: analog-output-PIR-sensor-based activity recognition technique which recognizes the different activities in the same place. Our technique recognizes user's activity by utilizing machine learning with frequency components of the sensor's output as features. However, because the number of features used in ALPAS is 1000 for each analog PIR-sensor, a large capacity memory is required. To reduce the number of features, we select a part of the sensing data. We call the starting point of the selected data as starting frequency (SF) and ending part as ending frequency (EF). We searched SF and EF using a grid search, and evaluated the recognition accuracy. We evaluated the proposed technique in a smarthome testbed. In the evaluation, five participants performed four different activities while sitting on a sofa. As a result, we achieved F-Measure: 63.9% when the EF is 1.4 Hz, and F-Measure: 50% or lower when the SF is 9.9 Hz or higher.

Aggregate power consumption modeling of live video streaming systems

“…(7) Tuning of parameters must be done based on an energy and bitrate tradeoff. (8) The complexities of inter prediction, intra prediction, RDO mode selection, and sub-pixel search are impacted primarily by the temporal and spatial resolutions (pixel rate).…”

“…Study [8] presented a vision system based on a smart sensor, called PARISI (Programmable Analog Retin-like Image Sensor I). The experiments were based on a sensor circuit with 16 × 16 pixels and 16 analog processing units.…”

“…Prior studies focused primarily on one aspect/phase. In particular, study [8] developed a power consumption model for video capturing for a specific on-chip vision circuit. For wireless video sensor networks (WVSNs), transmission power consumption has been analyzed in [2,11].…”

Sistema Guiado Sem Fio Para Soldagem Mecanizada Supervisionada Com Uso De Iluminação Por Infravermelho Próximo

“…Como uma forma de evitar a radiação luminosa abundante presente no arco de solda, muitos estudos (SMITH et al, 2004;BALFOUR et al, 2006;ELOUARDI et al, 2006;FRANCO, 2007)…”

An ASIP-based control system for Vision Chips with highly parallel signal processing

“…In contrast to the aforementioned sensors, PARIS1 [16], [17] comes with an analog, column-parallel Single Instruction Multiple Data (SIMD) processor. In order to enhance the fill factor and, therefore, the light sensitivity, no processing is performed within the pixel matrix.…”