NDLI: DeepEye: Resource Efficient Local Execution of Multiple Deep Vision Models using Wearable Commodity Hardware

Please wait, while we are loading the content...

Augmenting the Human Experience

BackDoor: Making Microphones Hear Inaudible Sounds

MobileDeepPill: A Small-Footprint Mobile Deep Learning System for Recognizing Unconstrained Pill Images

Enabling High-Precision Visible Light Localization in Today's Buildings

Poster: Multicamera Synchronization for Smartphones using Optimally Modulated Illuminations

ALOHA to the Web

SchrodinText: Strong Protection of Sensitive Textual Content of Mobile Applications

Enabling Gesture-based Interactions with Objects

Glimpse: A Programmable Early-Discard Camera Architecture for Continuous Mobile Vision

Indoor Follow Me Drone

Reptor: Enabling API Virtualization on Android for Platform Openness

Heimdall: A Privacy-Respecting Implicit Preference Collection Framework

Strata: Fine-Grained Acoustic-based Device-Free Tracking

DeepEye: Resource Efficient Local Execution of Multiple Deep Vision Models using Wearable Commodity Hardware

POLI: Long-Range Visible Light Communications Using Polarized Light Intensity Modulation

Poster: Sdguard: An Android Application Implementing Privacy Protection and Ransomware Detection

Matthan: Drone Presence Detection by Identifying Physical Signatures in the Drone's RF Communication

Position and Orientation Agnostic Gesture Recognition Using WiFi

Accelerating Mobile Audio Sensing Algorithms through On-Chip GPU Offloading

iBlink: Smart Glasses for Facial Paralysis Patients

iCharge: User-Interactive Charging of Mobile Devices

Trust but Verify: Auditing the Secure Internet of Things

SoundSifter: Mitigating Overhearing of Continuous Listening Devices

DeepMon: Mobile GPU-based Deep Learning Framework for Continuous Vision Applications

Card-stunt as a Service: Empowering a Massively Packed Crowd for Instant Collective Expressiveness

Poster: MobiTemplate: A Template-based Rapid Cross-Platform Mobile Application Development Environment

System Service Call-oriented Symbolic Execution of Android Framework with Applications to Vulnerability Discovery and Exploit Generation

Object Recognition and Navigation using a Single Networking Device

Enabling Cross-ISA Offloading for COTS Binaries

BigRoad: Scaling Road Data Acquisition for Dependable Self-Driving

Accelerating Mobile Web Loading Using Cellular Link Information

Techu: Open and Privacy-Preserving Crowdsourced GPS for the Masses

BatMapper: Acoustic Sensing Based Indoor Floor Plan Construction Using Smartphones

CELLI: Indoor Positioning Using Polarized Sweeping Light Beams

Poster: Mobile Power Management Using FreeRTOS-based Uninterruptable Generator Supply

BreathPrint: Breathing Acoustics-based User Authentication

Mobile Plus: Multi-device Mobile Platform for Cross-device Functionality Sharing

Characterizing Smartwatch Usage in the Wild

Open Data Kit 2.0: A Services-Based Application Framework for Disconnected Data Management

TrustShadow: Secure Execution of Unmodified Applications with ARM TrustZone

Poster: Charge My Phone As I Instruct

Poster: Docker-Based Self-Organizing IoT Services Architecture for Smarthome

Poster: Improve Push Notification on Smartwatches

Poster: Mobile Photo Data Management as a Platform Service

Poster: Towards Quick Angular Check to Rebuff Forged Position Attacks in Vehicular Communication

Poster: Visual Cue-Based VRU Protection on Smartphones

Poster: A Lightweight Live Migration Platform with Container-based Virtualization for System Resilience

Poster: Application-Layer Optimization of Performance vs Energy in Mobile Network I/O

Poster: Vocal Resonance as a Passive Biometric

Poster: Occupancy State Detection using WiFi Signals

Poster: Smartwatch Knows How Much You Drink

Poster: EPS: Edge-hosted Personal Services for Mobile Users

Poster: HeartFit: An Intuitive Smartphone Application for Well-being of Hypertensive Patients

Poster: Flood Monitoring using Computer Vision

Poster: Impact of Ground Truth Errors on Wi-Fi Localization Accuracy

Poster: Observe. Patternize. Mimic.: Leveraging Patterns in Mobile-User Behavior for Enterprise Applications

Poster: RTDroid: A Real-Time Solution with Android

Poster: Securing Device Inputs for Smartphones Using Hypervisor Based Approach

Poster: Memory Protection in Ultra-Low-Power Multi-Application Wearables

Poster: Android Malware Detection using Multi-Flows and API Patterns

Poster: Camera Images Offloading in Low-resource Wireless Networks

Poster: Redundancy Aided Vehicular Networking

Poster: Twirl:: On the Benefits of Adapting Orientation of a WiFi Access-Point

Poster: Online Map Matching for Passive Indoor Positioning Systems

Poster: Auracle: A Wearable Device for Detecting and Monitoring Eating Behavior

Poster: Characters vs. Words: Observations on Command Design for Brain-Computer Interfaces

Poster: Field Testing Vehicular Networks using OpenC2X

Poster: ARM Errata and their Software Workarounds

Poster: Extensive Evaluation of Emotional Contagion on Smiling Selfies over Social Network

Demo: Mobile Contextual Advertising Platform based on Tiny Text Intelligence

Demo: BlueMountain: An Architecture to Customize Data Management on Mobile Systems

Demo: Fusing Mobile Sensors for Paper Keyboard On-the-Go

Demo: sigSocial: A Novel Social Media Aggregation Service using a Tiny Text Intelligence

Demo: Fully Automated UI Testing System for Large-scale Android Apps Using Multiple Devices

Demo: DeepMon: Building Mobile GPU Deep Learning Models for Continuous Vision Applications

Demo: Card-stunt as a Service: Empowering a Massively Packed Crowd for Instant Collective Expressiveness

Demo: AWSense: A Framework for Collecting Sensing Data from the Apple Watch

Demo: Riding the Non-linearities to Record Ultrasound with Smartphones

Demo: Detecting Group Formations using iBeacon Technology

Demo: Enabling Dynamic Gesture Mapping with UI Events

Demo: iBlink: Smart Glasses for Facial Paralysis Patients

Demo: Reptor: Enabling API Virtualization on Android for Platform Openness

Demo: CELLI: Indoor Positioning using Polarized Sweeping Light Beams

Demo: Live Video Stream Triggers

DeepEye: Resource Efficient Local Execution of Multiple Deep Vision Models using Wearable Commodity Hardware

Content Provider	ACM Digital Library
Author	Lane, Nicholas D. Kawsar, Fahim Mathur, Akhil Boran, Aidan Bhattacharya, Sourav Forlivesi, Claudio
Abstract	Wearable devices with built-in cameras present interesting opportunities for users to capture various aspects of their daily life and are potentially also useful in supporting users with low vision in their everyday tasks. However, state-of-the-art image wearables available in the market are limited to capturing images periodically and do not provide any real-time analysis of the data that might be useful for the wearers. In this paper, we present DeepEye - a match-box sized wearable camera that is capable of running multiple cloud-scale deep learn- ing models locally on the device, thereby enabling rich analysis of the captured images in near real-time without offloading them to the cloud. DeepEye is powered by a commodity wearable processor (Snapdragon 410) which ensures its wearable form factor. The software architecture for DeepEye addresses a key limitation with executing multiple deep learning models on constrained hardware, that is their limited runtime memory. We propose a novel inference software pipeline that targets the local execution of multiple deep vision models (specifically, CNNs) by interleaving the execution of computation-heavy convolutional layers with the loading of memory-heavy fully-connected layers. Beyond this core idea, the execution framework incorporates: a memory caching scheme and a selective use of model compression techniques that further minimizes memory bottlenecks. Through a series of experiments, we show that our execution framework outperforms the baseline approaches significantly in terms of inference latency, memory requirements and energy consumption.
Starting Page	68
Ending Page	81
Page Count	14
File Format	PDF
ISBN	9781450349284
DOI	10.1145/3081333.3081359
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2017-06-16
Publisher Place	New York
Access Restriction	Subscribed
Subject Keyword	Deep learning Computer vision Embedded devices Local execution Wearables
Content Type	Text
Resource Type	Article

Central Library (ISO-9001:2015 Certified)
Indian Institute of Technology Kharagpur
Kharagpur, West Bengal, India | PIN - 721302

See location in the Map
03222 282435
Mail: support@ndl.gov.in

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in