Semantic Topic Analysis of Traffic Camera Images
Traffic cameras are commonly deployed monitoring components in road infrastructure networks, providing operators visual information about conditions at critical points in the network. However, human observers are often limited in their ability to process simultaneous information sources. Recent adva...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020
|
| Online Access: | https://hdl.handle.net/1721.1/125220 |
| _version_ | 1826189844353646592 |
|---|---|
| author | Liu, Jeffrey Weinert, Andrew J. Amin, Saurabh |
| author2 | Massachusetts Institute of Technology. Department of Civil and Environmental Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Civil and Environmental Engineering Liu, Jeffrey Weinert, Andrew J. Amin, Saurabh |
| author_sort | Liu, Jeffrey |
| collection | MIT |
| description | Traffic cameras are commonly deployed monitoring components in road infrastructure networks, providing operators visual information about conditions at critical points in the network. However, human observers are often limited in their ability to process simultaneous information sources. Recent advancements in computer vision, driven by deep learning methods, have enabled general object recognition, unlocking opportunities for camera-based sensing beyond the existing human observer paradigm. In this paper, we present a Natural Language Processing-inspired approach, entitled Bag-of-Label-Words (BoLW), for analyzing image data sets using exclusively textual labels. The BoLW model represents the data in a conventional matrix form, enabling data compression and decomposition techniques, while preserving semantic interpretability. We apply the Latent Dirichlet Allocation topic model to decompose the label data into a small number of semantic topics. To illustrate our approach, we use freeway camera images collected from the Boston area between December 2017-January 2018. We analyze the cameras' sensitivity to weather events; identify temporal traffic patterns; and analyze the impact of infrequent events, such as the winter holidays and the 'bomb cyclone' winter storm. This study demonstrates the flexibility of our approach, which allows us to analyze weather events and freeway traffic using only traffic camera image labels. |
| first_indexed | 2024-09-23T08:24:25Z |
| format | Article |
| id | mit-1721.1/125220 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T08:24:25Z |
| publishDate | 2020 |
| publisher | IEEE |
| record_format | dspace |
| spelling | mit-1721.1/1252202022-09-23T12:37:47Z Semantic Topic Analysis of Traffic Camera Images Liu, Jeffrey Weinert, Andrew J. Amin, Saurabh Massachusetts Institute of Technology. Department of Civil and Environmental Engineering Lincoln Laboratory Traffic cameras are commonly deployed monitoring components in road infrastructure networks, providing operators visual information about conditions at critical points in the network. However, human observers are often limited in their ability to process simultaneous information sources. Recent advancements in computer vision, driven by deep learning methods, have enabled general object recognition, unlocking opportunities for camera-based sensing beyond the existing human observer paradigm. In this paper, we present a Natural Language Processing-inspired approach, entitled Bag-of-Label-Words (BoLW), for analyzing image data sets using exclusively textual labels. The BoLW model represents the data in a conventional matrix form, enabling data compression and decomposition techniques, while preserving semantic interpretability. We apply the Latent Dirichlet Allocation topic model to decompose the label data into a small number of semantic topics. To illustrate our approach, we use freeway camera images collected from the Boston area between December 2017-January 2018. We analyze the cameras' sensitivity to weather events; identify temporal traffic patterns; and analyze the impact of infrequent events, such as the winter holidays and the 'bomb cyclone' winter storm. This study demonstrates the flexibility of our approach, which allows us to analyze weather events and freeway traffic using only traffic camera image labels. New Jersey Office of Homeland Security and Preparedness under Air Force Contract No. FA8702-15-D-0001 National Science Foundation grants CNS-1239054 and CNS-1453126 2020-05-13T19:25:14Z 2020-05-13T19:25:14Z 2018-11 2020-05-12T18:50:52Z Article http://purl.org/eprint/type/ConferencePaper 9781728103211 9781728103235 https://hdl.handle.net/1721.1/125220 Liu, Jeffrey, Andrew Weinert, and Saurabh Amin. "Semantic Topic Analysis of Traffic Camera Issues." 1st International Conference on Intelligent Transportation Systems, November 2018, Maui, HI, USA, IEEE, 2018. en http://dx.doi.org/10.1109/itsc.2018.8569449 Proceedings of the 2018 21st International Conference on Intelligent Transportation Systems Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf IEEE arXiv |
| spellingShingle | Liu, Jeffrey Weinert, Andrew J. Amin, Saurabh Semantic Topic Analysis of Traffic Camera Images |
| title | Semantic Topic Analysis of Traffic Camera Images |
| title_full | Semantic Topic Analysis of Traffic Camera Images |
| title_fullStr | Semantic Topic Analysis of Traffic Camera Images |
| title_full_unstemmed | Semantic Topic Analysis of Traffic Camera Images |
| title_short | Semantic Topic Analysis of Traffic Camera Images |
| title_sort | semantic topic analysis of traffic camera images |
| url | https://hdl.handle.net/1721.1/125220 |
| work_keys_str_mv | AT liujeffrey semantictopicanalysisoftrafficcameraimages AT weinertandrewj semantictopicanalysisoftrafficcameraimages AT aminsaurabh semantictopicanalysisoftrafficcameraimages |