An object detection approach for lane change and overtake detection from motion profiles
This addresses the problem of efficient driver monitoring and fleet management by enabling compact event detection with low computational requirements, though it is incremental as it builds on existing object detection methods.
The paper tackles the challenge of detecting lane change and overtake maneuvers from dashcam footage by proposing a novel object detection approach applied to motion profiles, achieving state-of-the-art performance with improved mAP and F1 scores through CoordConvolution layers.
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.