Energy-efficient design of an always-on smart visual trigger

被引:0
|
作者
Rusci, Manuele [1 ,2 ]
Rossi, Davide [2 ]
Lecca, Michela [1 ]
Gottardi, Massimo [1 ]
Benini, Luca [2 ,3 ]
Farella, Elisabetta [1 ]
机构
[1] Fdn Bruno Kessler, Trento, Italy
[2] Univ Bologna, DEI, I-40126 Bologna, Italy
[3] Swiss Fed Inst Technol, Integrated Syst Lab, Zurich, Switzerland
关键词
SENSOR NETWORKS;
D O I
暂无
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
In this work, we present the design of an always-on smart visual trigger. To maximize the energy-efficiency, the whole system is kept in stand-by mode until a significant information is detected by the early-processing of the low-power imager. Within two considered scenarios of vehicle detection, the system runs at minimal power consumption for 84% and 39% of the time. When active, the generation of triggers due to relevant events is conducted by analyzing the trajectory of multiple tracked objects. A parallel event-driven implementation speeds-up the digital computation and leads to a duty cycle below 1% over the frame period. The optimized power management is enabled by defining an always-on camera interface for the System-on-Chip (SoC) processor, which is able to individually activate both the sensor and the processor while running at minimal power consumption. In the considered case-study of vehicle detection, an estimated power consumption of up to 2 3 mu W is accounted, depending on the context-activity, and the smart triggers fails one detection over 72 moving vehicles.
引用
收藏
页码:518 / 523
页数:6
相关论文
共 50 条
  • [1] LoTTA: Energy-Efficient Processor for Always-On Applications
    Multanen, Joonas
    Kultala, Heikki
    Jaaskelainen, Pekka
    Viitanen, Timo
    Tervo, Aleksi
    Takala, Jarmo
    [J]. PROCEEDINGS OF THE 2018 IEEE INTERNATIONAL WORKSHOP ON SIGNAL PROCESSING SYSTEMS (SIPS), 2018, : 193 - 198
  • [2] Neural architecture search for energy-efficient always-on audio machine learning
    Daniel T. Speckhard
    Karolis Misiunas
    Sagi Perel
    Tenghui Zhu
    Simon Carlile
    Malcolm Slaney
    [J]. Neural Computing and Applications, 2023, 35 : 12133 - 12144
  • [3] Neural architecture search for energy-efficient always-on audio machine learning
    Speckhard, Daniel T.
    Misiunas, Karolis
    Perel, Sagi
    Zhu, Tenghui
    Carlile, Simon
    Slaney, Malcolm
    [J]. NEURAL COMPUTING & APPLICATIONS, 2023, 35 (16): : 12133 - 12144
  • [4] TASA: Traffic Aware Sleep Algorithm for Energy-Efficient Always-on Home Networks
    In-Yeup, Kong
    [J]. INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND NETWORK SECURITY, 2010, 10 (06): : 105 - 109
  • [5] Skin-conformable photoplethysmogram sensors for energy-efficient always-on cardiovascular monitoring systems
    Kang, Byung Ha
    Park, Kyungho
    Hambsch, Mike
    Hong, Seongin
    Kim, Hyung Tae
    Choi, Dong Hyun
    Lee, Jin Hyeok
    Kim, Sunkook
    Kim, Hyun Jae
    [J]. NANO ENERGY, 2022, 92
  • [6] On how to design smart energy-efficient buildings
    Sciuto, Donatella
    Nacci, Alessandro A.
    [J]. 2014 12TH IEEE INTERNATIONAL CONFERENCE ON EMBEDDED AND UBIQUITOUS COMPUTING (EUC 2014), 2014, : 205 - 208
  • [7] Design and Implementation of an Energy-Efficient Smart Lighting System
    Rahman, Md Mominur
    Abu Shufian
    Ahmed, Koushik
    Najibullah, Md
    Hridoy, Md Momin Miah
    Hossen, Md Tarif
    [J]. 2019 5TH INTERNATIONAL CONFERENCE ON ADVANCES IN ELECTRICAL ENGINEERING (ICAEE), 2019, : 897 - 902
  • [8] A Sub-mW IoT-Endnode for Always-On Visual Monitoring and Smart Triggering
    Rusci, Manuele
    Rossi, Davide
    Farella, Elisabetta
    Benini, Luca
    [J]. IEEE INTERNET OF THINGS JOURNAL, 2017, 4 (05): : 1284 - 1295
  • [9] Energy-efficient design
    Uchiyama, K
    Bose, P
    [J]. IEEE MICRO, 2005, 25 (05) : 6 - 7
  • [10] Energy-efficient digital and wireless IC design for wireless smart sensing
    Zhou, Jun
    Huang, Xiongchuan
    Wang, Chao
    Kim, Tony Tae-Hyoung
    Lian, Yong
    [J]. JOURNAL OF SEMICONDUCTORS, 2017, 38 (10)