Open Dataset

The pretrained models for CLFT and CLFCN that based on the Waymo Open Dataset.

An open-source dataset for multi-pedestrian crossing classification. Extended from the public synthetic dataset SMIRK. Serving the purpose to retrieve crossing events from real-world datasets.

An open-source training dataset for perception of autonomous vehicles. Collected by iseAuto shuttle (first L4 self-driving shuttle in Estonia). Featured with the challenging wet and dark scenarios