FuSSI-Net: Fusion of Spatio-temporal Skeletons for Intention Prediction Network
This work addresses safety in autonomous driving by improving intention recognition, but it appears incremental as it builds on existing methods with new fusion techniques and metrics.
The paper tackles pedestrian intention prediction for autonomous driving by developing an end-to-end framework using skeletal features and fusion mechanisms, achieving an AP of 0.89 and enabling accurate prediction up to half a second ahead of risky maneuvers.
Pedestrian intention recognition is very important to develop robust and safe autonomous driving (AD) and advanced driver assistance systems (ADAS) functionalities for urban driving. In this work, we develop an end-to-end pedestrian intention framework that performs well on day- and night- time scenarios. Our framework relies on objection detection bounding boxes combined with skeletal features of human pose. We study early, late, and combined (early and late) fusion mechanisms to exploit the skeletal features and reduce false positives as well to improve the intention prediction performance. The early fusion mechanism results in AP of 0.89 and precision/recall of 0.79/0.89 for pedestrian intention classification. Furthermore, we propose three new metrics to properly evaluate the pedestrian intention systems. Under these new evaluation metrics for the intention prediction, the proposed end-to-end network offers accurate pedestrian intention up to half a second ahead of the actual risky maneuver.