Glimpse: Continuous, Real-Time Object Recognition on Mobile Devices
Glimpse is a continuous, real-time object recognition system for camera-equipped mobile devices. Glimpse captures full-motion video, locates objects of interest, recognizes and labels them, and tracks them from frame to frame for the user. Because the algorithms for object recognition entail signifi...
Main Authors: | , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | en_US |
Published: |
Association for Computing Machinery
2017
|
Online Access: | http://hdl.handle.net/1721.1/110758 https://orcid.org/0000-0002-1455-9652 |
_version_ | 1811073217090027520 |
---|---|
author | Chen, Tiffany Yu-Han Ravindranath, Lenin Deng, Shuo Bahl, Paramvir Balakrishnan, Hari |
author2 | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
author_facet | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Chen, Tiffany Yu-Han Ravindranath, Lenin Deng, Shuo Bahl, Paramvir Balakrishnan, Hari |
author_sort | Chen, Tiffany Yu-Han |
collection | MIT |
description | Glimpse is a continuous, real-time object recognition system for camera-equipped mobile devices. Glimpse captures full-motion video, locates objects of interest, recognizes and labels them, and tracks them from frame to frame for the user. Because the algorithms for object recognition entail significant computation, Glimpse runs them on server machines. When the latency between the server and mobile device is higher than a frame-time, this approach lowers object recognition accuracy. To regain accuracy, Glimpse uses an active cache of video frames on the mobile device. A subset of the frames in the active cache are used to track objects on the mobile, using (stale) hints about objects that arrive from the server from time to time. To reduce network bandwidth usage, Glimpse computes trigger frames to send to the server for recognizing and labeling. Experiments with Android smartphones and Google Glass over Verizon, AT&T, and a campus Wi-Fi network show that with hardware face detection support (available on many mobile devices), Glimpse achieves precision between 96.4% to 99.8% for continuous face recognition, which improves over a scheme performing hardware face detection and server-side recognition without Glimpse's techniques by between 1.8-2.5×. The improvement in precision for face recognition without hardware detection is between 1.6-5.5×. For road sign recognition, which does not have a hardware detector, Glimpse achieves precision between 75% and 80%; without Glimpse, continuous detection is non-functional (0.2%-1.9% precision). |
first_indexed | 2024-09-23T09:30:08Z |
format | Article |
id | mit-1721.1/110758 |
institution | Massachusetts Institute of Technology |
language | en_US |
last_indexed | 2024-09-23T09:30:08Z |
publishDate | 2017 |
publisher | Association for Computing Machinery |
record_format | dspace |
spelling | mit-1721.1/1107582022-09-30T14:51:47Z Glimpse: Continuous, Real-Time Object Recognition on Mobile Devices Chen, Tiffany Yu-Han Ravindranath, Lenin Deng, Shuo Bahl, Paramvir Balakrishnan, Hari Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Deng, Shuo Balakrishnan, Hari Glimpse is a continuous, real-time object recognition system for camera-equipped mobile devices. Glimpse captures full-motion video, locates objects of interest, recognizes and labels them, and tracks them from frame to frame for the user. Because the algorithms for object recognition entail significant computation, Glimpse runs them on server machines. When the latency between the server and mobile device is higher than a frame-time, this approach lowers object recognition accuracy. To regain accuracy, Glimpse uses an active cache of video frames on the mobile device. A subset of the frames in the active cache are used to track objects on the mobile, using (stale) hints about objects that arrive from the server from time to time. To reduce network bandwidth usage, Glimpse computes trigger frames to send to the server for recognizing and labeling. Experiments with Android smartphones and Google Glass over Verizon, AT&T, and a campus Wi-Fi network show that with hardware face detection support (available on many mobile devices), Glimpse achieves precision between 96.4% to 99.8% for continuous face recognition, which improves over a scheme performing hardware face detection and server-side recognition without Glimpse's techniques by between 1.8-2.5×. The improvement in precision for face recognition without hardware detection is between 1.6-5.5×. For road sign recognition, which does not have a hardware detector, Glimpse achieves precision between 75% and 80%; without Glimpse, continuous detection is non-functional (0.2%-1.9% precision). 2017-07-18T15:33:37Z 2017-07-18T15:33:37Z 2015-11 Article http://purl.org/eprint/type/ConferencePaper 9781450336314 http://hdl.handle.net/1721.1/110758 Chen, Tiffany Yu-Han, Lenin Ravindranath, Shuo Deng, Paramvir Bahl, and Hari Balakrishnan. “Glimpse.” Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems -SenSys ’15 (2015). https://orcid.org/0000-0002-1455-9652 en_US http://dx.doi.org/10.1145/2809695.2809711 Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems - SenSys '15 Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Association for Computing Machinery MIT Web Domain |
spellingShingle | Chen, Tiffany Yu-Han Ravindranath, Lenin Deng, Shuo Bahl, Paramvir Balakrishnan, Hari Glimpse: Continuous, Real-Time Object Recognition on Mobile Devices |
title | Glimpse: Continuous, Real-Time Object Recognition on Mobile Devices |
title_full | Glimpse: Continuous, Real-Time Object Recognition on Mobile Devices |
title_fullStr | Glimpse: Continuous, Real-Time Object Recognition on Mobile Devices |
title_full_unstemmed | Glimpse: Continuous, Real-Time Object Recognition on Mobile Devices |
title_short | Glimpse: Continuous, Real-Time Object Recognition on Mobile Devices |
title_sort | glimpse continuous real time object recognition on mobile devices |
url | http://hdl.handle.net/1721.1/110758 https://orcid.org/0000-0002-1455-9652 |
work_keys_str_mv | AT chentiffanyyuhan glimpsecontinuousrealtimeobjectrecognitiononmobiledevices AT ravindranathlenin glimpsecontinuousrealtimeobjectrecognitiononmobiledevices AT dengshuo glimpsecontinuousrealtimeobjectrecognitiononmobiledevices AT bahlparamvir glimpsecontinuousrealtimeobjectrecognitiononmobiledevices AT balakrishnanhari glimpsecontinuousrealtimeobjectrecognitiononmobiledevices |