Low power and privacy preserving sensor platform for occupancy detection
Abstract
A low-cost, low-power, stand-alone sensor platform having a visible-range camera sensor, a thermopile array, a microphone, a motion sensor, and a microprocessor that is configured to perform occupancy detection and counting while preserving the privacy of occupants. The platform is programmed to extract shape/texture from images in spatial domain; motion from video in time domain; and audio features in frequency domain. Embedded binarized neural networks are used for efficient object of interest detection. The platform is also programmed with advanced fusion algorithms for multiple sensor modalities addressing dependent sensor observations. The platform may be deployed for (i) residential use in detecting occupants for autonomously controlling building systems, such as HVAC and lighting systems, to provide energy savings, (ii) security and surveillance, such as to detect loitering and surveil places of interest, (iii) analyzing customer behavior and flows, (iv) identifying high performing stores by retailers.
- Inventors:
- Issue Date:
- Research Org.:
- Syracuse University, Syracuse, NY (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1987225
- Patent Number(s):
- 11605231
- Application Number:
- 16/573,499
- Assignee:
- Syracuse University (Syracuse, NY)
- Patent Classifications (CPCs):
-
G - PHYSICS G06 - COMPUTING G06T - IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
G - PHYSICS G08 - SIGNALLING G08B - SIGNALLING OR CALLING SYSTEMS
- DOE Contract Number:
- AR0000940
- Resource Type:
- Patent
- Resource Relation:
- Patent File Date: 09/17/2019
- Country of Publication:
- United States
- Language:
- English
Citation Formats
Velipasalar, Senem, Chai, Sek Meng, and Nadamuni Raghavan, Aswin. Low power and privacy preserving sensor platform for occupancy detection. United States: N. p., 2023.
Web.
Velipasalar, Senem, Chai, Sek Meng, & Nadamuni Raghavan, Aswin. Low power and privacy preserving sensor platform for occupancy detection. United States.
Velipasalar, Senem, Chai, Sek Meng, and Nadamuni Raghavan, Aswin. Tue .
"Low power and privacy preserving sensor platform for occupancy detection". United States. https://www.osti.gov/servlets/purl/1987225.
@article{osti_1987225,
title = {Low power and privacy preserving sensor platform for occupancy detection},
author = {Velipasalar, Senem and Chai, Sek Meng and Nadamuni Raghavan, Aswin},
abstractNote = {A low-cost, low-power, stand-alone sensor platform having a visible-range camera sensor, a thermopile array, a microphone, a motion sensor, and a microprocessor that is configured to perform occupancy detection and counting while preserving the privacy of occupants. The platform is programmed to extract shape/texture from images in spatial domain; motion from video in time domain; and audio features in frequency domain. Embedded binarized neural networks are used for efficient object of interest detection. The platform is also programmed with advanced fusion algorithms for multiple sensor modalities addressing dependent sensor observations. The platform may be deployed for (i) residential use in detecting occupants for autonomously controlling building systems, such as HVAC and lighting systems, to provide energy savings, (ii) security and surveillance, such as to detect loitering and surveil places of interest, (iii) analyzing customer behavior and flows, (iv) identifying high performing stores by retailers.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Tue Mar 14 00:00:00 EDT 2023},
month = {Tue Mar 14 00:00:00 EDT 2023}
}
Works referenced in this record:
Object Association for Autonomous Vehicles
patent-application, October 2019
- Vallespi-Gonzalez, Carlos; Sen, Abhishek; Gautam, Shivam
- US Patent Application 16/038730; 20190333232
Systems, Methods and Computer Program Products for Identifying Objects in Video Data
patent-application, August 2013
- DeLean, Bruno
- US Patent Application 13/590384; 20130216094
Techniques for Object Acquisition and Tracking
patent-application, June 2017
- Wenus, Jakub; Cahill, Niall; Kelly, Mark
- US Patent Application 14/757947; 20170186291
Quantized Neural Network Training and Inference
patent-application, October 2017
- El-Yaniv, Ran; Hubara, Itay; Soudry, Daniel
- US Patent Application 15/478531; 20170286830
Object Recognition Using Multi-Modal Matching Scheme
patent-application, October 2013
- Visser, Erik; Wang, Haiyin; Siddiqui, Hasib A.
- US Patent Application 13/664295; 20130272548
Identification of Foreign Object Debris
patent-application, October 2013
- Zhou, Pixuan; Ding, Lu; Zhang, Xuemeng
- US Patent Application 13/861121; 20130279750
Flame Image Analysis for Furnace Combustion Control
patent-application, July 2018
- Correia E. Sa Neto, Valmiro; Evenson, Euan J.; Albrecht, Kevin W.
- US Patent Application 15/867166; 20180204317
Notification System
patent-application, August 2016
- Atarashi, Yuichi; Okada, Takashi
- US Patent Application 15/021537; 20160228040
Accelerated Object Recognition in an Image
patent-application, May 2015
- Cebron, Nicolas; Yu, Jie
- US Patent Application 14/553412; 20150146927