Multi-Object Detection in Urban Scenes Utilizing 3D Background Maps and Tracking

In this paper we propose a novel approach for upgrading real time 3D dynamic object detection methods operating on rotating multi-beam (RMB) Lidar measurements using 3D background city maps stored in new generation geographic information systems (GIS) and previously detected dynamic objects propagated by tracking. First, we apply a state-of-the-art object detection method and distinguish the predicted dynamic object candidates and the remaining static regions of the current Lidar measurement. Next we find an optimal transformation between the static part of the RMB Lidar measurements and the background city map using a multimodal point cloud registration algorithm operating in the Hough space. After the accurate alignment, we filter false-positively detected object candidates in the RMB Lidar data based on the map. To find additional objects missed by the object detector on the current measurement, we apply a Kalman-filter based object tracking. Hereby we first predict the current state of the previously detected and tracked objects. Next, we apply a Hungarian matcher based assignment between the tracked and the current objects and update the object list according to the result. For better accuracy, we keep all predictions through a couple of frames. We evaluated our method qualitatively and quantitatively in crowded urban scenes of Budapest, Hungary, and the results showed that with background map based filtering we can achieve a 26,52% improvement detecting vehicles and 9,38% for pedestrians in precision, while via tracking, a 12,84% improvement for vehicles and 14,34% for pedestrians in recall against the state-of-the-art object detection method relying purely on a single Lidar time frame.