This work aims to address the challenges in domain adaptation of 3D object detection using roadside LiDARs. We design DASE-ProPillars, a model that can detect objects in roadside LiDARs in real-time. Our model uses PointPillars as the baseline model with additional modules to improve the 3D detection performance. To prove the effectiveness of our proposed modules in DASE-ProPillars, we train and evaluate the model on two datasets, the open source A9 dataset and a semi-synthetic roadside A11 dataset created within the Regensburg Next project. We do several sets of experiments for each module in the DASE-ProPillars detector that show that our model outperforms the SE-ProPillars baseline on the real A9 test set and a semi-synthetic A9 test set, while maintaining an inference speed of 45 Hz (22 ms) that allows to detect objects in real-time. We apply domain adaptation from the semi-synthetic A9 dataset to the semi-synthetic A11 dataset from the Regensburg Next project by applying transfer learning and achieve a 3D mAP@0.25 of 93.49% on the Car class of the target test set using 40 recall positions.     «

This work aims to address the challenges in domain adaptation of 3D object detection using roadside LiDARs. We design DASE-ProPillars, a model that can detect objects in roadside LiDARs in real-time. Our model uses PointPillars as the baseline model with additional modules to improve the 3D detection performance. To prove the effectiveness of our proposed modules in DASE-ProPillars, we train and evaluate the model on two datasets, the open source A9 dataset and a semi-synthetic roadside A11 data...     »