An object detection approach for lane change and overtake detection from motion profiles
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913681680367616 |
|---|---|
| author | Benericetti, Andrea Bellaccini, Niccolò Monteagudo, Henrique Piñeiro Simoncini, Matteo Sambo, Francesco |
| author_facet | Benericetti, Andrea Bellaccini, Niccolò Monteagudo, Henrique Piñeiro Simoncini, Matteo Sambo, Francesco |
| contents | In the application domain of fleet management and driver monitoring, it is very challenging to obtain relevant driving events and activities from dashcam footage while minimizing the amount of information stored and analyzed. In this paper, we address the identification of overtake and lane change maneuvers with a novel object detection approach applied to motion profiles, a compact representation of driving video footage into a single image. To train and test our model we created an internal dataset of motion profile images obtained from a heterogeneous set of dashcam videos, manually labeled with overtake and lane change maneuvers by the ego-vehicle. In addition to a standard object-detection approach, we show how the inclusion of CoordConvolution layers further improves the model performance, in terms of mAP and F1 score, yielding state-of-the art performance when compared to other baselines from the literature. The extremely low computational requirements of the proposed solution make it especially suitable to run in device. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_04244 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An object detection approach for lane change and overtake detection from motion profiles Benericetti, Andrea Bellaccini, Niccolò Monteagudo, Henrique Piñeiro Simoncini, Matteo Sambo, Francesco Computer Vision and Pattern Recognition In the application domain of fleet management and driver monitoring, it is very challenging to obtain relevant driving events and activities from dashcam footage while minimizing the amount of information stored and analyzed. In this paper, we address the identification of overtake and lane change maneuvers with a novel object detection approach applied to motion profiles, a compact representation of driving video footage into a single image. To train and test our model we created an internal dataset of motion profile images obtained from a heterogeneous set of dashcam videos, manually labeled with overtake and lane change maneuvers by the ego-vehicle. In addition to a standard object-detection approach, we show how the inclusion of CoordConvolution layers further improves the model performance, in terms of mAP and F1 score, yielding state-of-the art performance when compared to other baselines from the literature. The extremely low computational requirements of the proposed solution make it especially suitable to run in device. |
| title | An object detection approach for lane change and overtake detection from motion profiles |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.04244 |