Open access
Sep 2026
Low-complexity pedestrian intent prediction using contextual stacked ensemble learning
This work proposes CSE, a lightweight contextual stacked ensemble-learning framework to efficiently predict pedestrian crossing intent, and employs a modality-decomposed strategy in which each feature stream is processed independently and integrated via a lightweight meta-classifier.
Chia-Yen Chiang, Yasmin Fathy, G. Slabaugh et al.
· Scientific Reports · 0 citations