Edge neuro-statistical learning for event-based visual motion detection and tracking in roadside safety systems
The Vision Zero Program’s purpose is to reduce traffic-related fatalities and serious injuries while promoting equitable, safe, and healthy mobility for all. Ultimately, the challenge is to detect pedestrians during the day and especially at night to implement safety measures. The current study intr...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2025-01-01
|
| Series: | Neuromorphic Computing and Engineering |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2634-4386/adcbcb |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850156304407986176 |
|---|---|
| author | Cristian Axenie Ertan Halilov Julian Main David Weiss |
| author_facet | Cristian Axenie Ertan Halilov Julian Main David Weiss |
| author_sort | Cristian Axenie |
| collection | DOAJ |
| description | The Vision Zero Program’s purpose is to reduce traffic-related fatalities and serious injuries while promoting equitable, safe, and healthy mobility for all. Ultimately, the challenge is to detect pedestrians during the day and especially at night to implement safety measures. The current study introduces an award-winning low-power solution employing neuromorphic visual sensing and hybrid neuro-statistical processing developed by the Technische Hochschule Nürnberg team for the TinyML Vision Zero San Jose Competition. The solution proposes a novel neuromorphic edge fusion of spiking neural networks and event-based expectation maximization for the detection and tracking of pedestrians and bicyclists. We provide a deployment-ready evaluation of the detection performance along with robustness, energy footprint, and weatherization while emphasizing the advantages of the neuro-statistical edge solution and its city-level scaling capabilities. |
| format | Article |
| id | doaj-art-e52c89eb52ab4eba99ba152c7c22edbe |
| institution | OA Journals |
| issn | 2634-4386 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Neuromorphic Computing and Engineering |
| spelling | doaj-art-e52c89eb52ab4eba99ba152c7c22edbe2025-08-20T02:24:35ZengIOP PublishingNeuromorphic Computing and Engineering2634-43862025-01-015202400310.1088/2634-4386/adcbcbEdge neuro-statistical learning for event-based visual motion detection and tracking in roadside safety systemsCristian Axenie0https://orcid.org/0000-0001-6184-0546Ertan Halilov1Julian Main2David Weiss3Department of Computer Science and Center for Artificial Intelligence, Technische Hochschule Nürnberg Georg Simon Ohm , Kelerplatz 12, 90489 Nürnberg, GermanyDepartment of Computer Science and Center for Artificial Intelligence, Technische Hochschule Nürnberg Georg Simon Ohm , Kelerplatz 12, 90489 Nürnberg, GermanyDepartment of Computer Science and Center for Artificial Intelligence, Technische Hochschule Nürnberg Georg Simon Ohm , Kelerplatz 12, 90489 Nürnberg, GermanyDepartment of Computer Science and Center for Artificial Intelligence, Technische Hochschule Nürnberg Georg Simon Ohm , Kelerplatz 12, 90489 Nürnberg, GermanyThe Vision Zero Program’s purpose is to reduce traffic-related fatalities and serious injuries while promoting equitable, safe, and healthy mobility for all. Ultimately, the challenge is to detect pedestrians during the day and especially at night to implement safety measures. The current study introduces an award-winning low-power solution employing neuromorphic visual sensing and hybrid neuro-statistical processing developed by the Technische Hochschule Nürnberg team for the TinyML Vision Zero San Jose Competition. The solution proposes a novel neuromorphic edge fusion of spiking neural networks and event-based expectation maximization for the detection and tracking of pedestrians and bicyclists. We provide a deployment-ready evaluation of the detection performance along with robustness, energy footprint, and weatherization while emphasizing the advantages of the neuro-statistical edge solution and its city-level scaling capabilities.https://doi.org/10.1088/2634-4386/adcbcbevent-based visionneuromorphic systemsroadside safetyTinyML |
| spellingShingle | Cristian Axenie Ertan Halilov Julian Main David Weiss Edge neuro-statistical learning for event-based visual motion detection and tracking in roadside safety systems Neuromorphic Computing and Engineering event-based vision neuromorphic systems roadside safety TinyML |
| title | Edge neuro-statistical learning for event-based visual motion detection and tracking in roadside safety systems |
| title_full | Edge neuro-statistical learning for event-based visual motion detection and tracking in roadside safety systems |
| title_fullStr | Edge neuro-statistical learning for event-based visual motion detection and tracking in roadside safety systems |
| title_full_unstemmed | Edge neuro-statistical learning for event-based visual motion detection and tracking in roadside safety systems |
| title_short | Edge neuro-statistical learning for event-based visual motion detection and tracking in roadside safety systems |
| title_sort | edge neuro statistical learning for event based visual motion detection and tracking in roadside safety systems |
| topic | event-based vision neuromorphic systems roadside safety TinyML |
| url | https://doi.org/10.1088/2634-4386/adcbcb |
| work_keys_str_mv | AT cristianaxenie edgeneurostatisticallearningforeventbasedvisualmotiondetectionandtrackinginroadsidesafetysystems AT ertanhalilov edgeneurostatisticallearningforeventbasedvisualmotiondetectionandtrackinginroadsidesafetysystems AT julianmain edgeneurostatisticallearningforeventbasedvisualmotiondetectionandtrackinginroadsidesafetysystems AT davidweiss edgeneurostatisticallearningforeventbasedvisualmotiondetectionandtrackinginroadsidesafetysystems |