RNN-based Pedestrian Crossing Prediction using Activity and Pose-related Features
This work addresses pedestrian safety in autonomous driving, but it appears incremental as it builds on existing methods with variations in features and RNN types.
The paper tackled pedestrian crossing prediction for autonomous driving by proposing deep learning systems with CNN-based feature extractors and RNN modules, achieving results that show feature extraction methods, additional variables like gaze direction, and RNN type significantly impact performance on the JAAD dataset.
Pedestrian crossing prediction is a crucial task for autonomous driving. Numerous studies show that an early estimation of the pedestrian's intention can decrease or even avoid a high percentage of accidents. In this paper, different variations of a deep learning system are proposed to attempt to solve this problem. The proposed models are composed of two parts: a CNN-based feature extractor and an RNN module. All the models were trained and tested on the JAAD dataset. The results obtained indicate that the choice of the features extraction method, the inclusion of additional variables such as pedestrian gaze direction and discrete orientation, and the chosen RNN type have a significant impact on the final performance.