Crowd-Centric Counting via Unsupervised Learning
Counting targets (people or things) within a monitored area is an important task in emerging wireless applications, including those for smart environments, safety, and security. Conventional device-free radio-based systems for counting targets rely on localization and data association (i.e., individ...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020
|
| Online Access: | https://hdl.handle.net/1721.1/123538 |
| _version_ | 1811094565161009152 |
|---|---|
| author | Morselli, Flavio Bartoletti, Stefania Mazuelas, Santiago Win, Moe Z. Conti, Andrea |
| author2 | Massachusetts Institute of Technology. Laboratory for Information and Decision Systems |
| author_facet | Massachusetts Institute of Technology. Laboratory for Information and Decision Systems Morselli, Flavio Bartoletti, Stefania Mazuelas, Santiago Win, Moe Z. Conti, Andrea |
| author_sort | Morselli, Flavio |
| collection | MIT |
| description | Counting targets (people or things) within a monitored area is an important task in emerging wireless applications, including those for smart environments, safety, and security. Conventional device-free radio-based systems for counting targets rely on localization and data association (i.e., individual-centric information) to infer the number of targets present in an area (i.e., crowd-centric information). However, many applications (e.g., affluence analytics) require only crowd-centric rather than individual-centric information. Moreover, individual-centric approaches may be inadequate due to the complexity of data association. This paper proposes a new technique for crowd-centric counting of device-free targets based on unsupervised learning, where the number of targets is inferred directly from a low-dimensional representation of the received waveforms. The proposed technique is validated via experimentation using an ultra-wideband sensor radar in an indoor environment. |
| first_indexed | 2024-09-23T16:02:05Z |
| format | Article |
| id | mit-1721.1/123538 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T16:02:05Z |
| publishDate | 2020 |
| publisher | IEEE |
| record_format | dspace |
| spelling | mit-1721.1/1235382022-10-02T05:52:08Z Crowd-Centric Counting via Unsupervised Learning Morselli, Flavio Bartoletti, Stefania Mazuelas, Santiago Win, Moe Z. Conti, Andrea Massachusetts Institute of Technology. Laboratory for Information and Decision Systems Counting targets (people or things) within a monitored area is an important task in emerging wireless applications, including those for smart environments, safety, and security. Conventional device-free radio-based systems for counting targets rely on localization and data association (i.e., individual-centric information) to infer the number of targets present in an area (i.e., crowd-centric information). However, many applications (e.g., affluence analytics) require only crowd-centric rather than individual-centric information. Moreover, individual-centric approaches may be inadequate due to the complexity of data association. This paper proposes a new technique for crowd-centric counting of device-free targets based on unsupervised learning, where the number of targets is inferred directly from a low-dimensional representation of the received waveforms. The proposed technique is validated via experimentation using an ultra-wideband sensor radar in an indoor environment. 2020-01-22T19:23:48Z 2020-01-22T19:23:48Z 2019-05 2019-11-04T16:08:02Z Article http://purl.org/eprint/type/ConferencePaper 9781728123738 https://hdl.handle.net/1721.1/123538 Morselli, Flavio et al. "Crowd-Centric Counting via Unsupervised Learning." 2019 IEEE International Conference on Communications Workshops (ICC Workshops) : proceedings : Shanghai, China, 22-24 May 2019, IEEE, 2019 en http://dx.doi.org/10.1109/iccw.2019.8757112 2019 IEEE International Conference on Communications Workshops (ICC Workshops) : proceedings : Shanghai, China, 22-24 May 2019 Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf IEEE Other repository |
| spellingShingle | Morselli, Flavio Bartoletti, Stefania Mazuelas, Santiago Win, Moe Z. Conti, Andrea Crowd-Centric Counting via Unsupervised Learning |
| title | Crowd-Centric Counting via Unsupervised Learning |
| title_full | Crowd-Centric Counting via Unsupervised Learning |
| title_fullStr | Crowd-Centric Counting via Unsupervised Learning |
| title_full_unstemmed | Crowd-Centric Counting via Unsupervised Learning |
| title_short | Crowd-Centric Counting via Unsupervised Learning |
| title_sort | crowd centric counting via unsupervised learning |
| url | https://hdl.handle.net/1721.1/123538 |
| work_keys_str_mv | AT morselliflavio crowdcentriccountingviaunsupervisedlearning AT bartolettistefania crowdcentriccountingviaunsupervisedlearning AT mazuelassantiago crowdcentriccountingviaunsupervisedlearning AT winmoez crowdcentriccountingviaunsupervisedlearning AT contiandrea crowdcentriccountingviaunsupervisedlearning |