An object detection approach for lane change and overtake detection from motion profiles

TL;DR

This paper introduces a novel, low-computation object detection method using motion profiles to accurately identify lane changes and overtakes from dashcam footage, aiding fleet management and driver monitoring.

Contribution

It presents a new approach combining motion profiles and CoordConvolution layers for improved detection accuracy, with state-of-the-art performance and low computational cost.

Findings

Achieved high mAP and F1 scores surpassing existing baselines.

Demonstrated the method's suitability for real-time device deployment.

Created a labeled dataset of dashcam motion profiles for training and testing.

Abstract

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.