| Multiple Vehicle and Person Tracking in Aerial Imagery Using Ensemble of Micro Single-Object-Tracking CNNs |
| Paper ID : 1116-SMPR |
| Authors: |
|
Reza Bahmanyar *, Seyed Majid Azimi, Peter Reinartz Remote Sensing Technology Institute (IMF), German Aerospace Center (DLR), Wessling, Germany |
| Abstract: |
| Geo-referenced real-time vehicle and person tracking in aerial imagery has a variety of applications such as traffic and large-scale event monitoring, disaster management, and also for input into predictive traffic models. However, object tracking in aerial imagery is a challenging task due to the small size of the objects and the limited temporal resolution of geo-referenced datasets. In this work, we propose a new approach based on Convolutional Neural Networks (CNNs) to track multiple vehicles and persons in aerial image sequences. As the large number of objects in aerial images can exponentially increase the processing demands in multiple object tracking scenarios, the proposed approach utilizes the ensemble of micro CNNs, where each micro CNN is responsible for a single-object tracking task. We call our approach ensemble Micro Single-Object-Tracking CNNs (eMSOT-CNNs). More precisely, a set of features are extracted from the input sequence for each object, where the objects are detected based on a CNN method. Then each MSOT-CNN is assigned to the extracted features of each object in order to track it throughout the rest of the image sequence. The proposed method is trained and validated on the KIT AIS dataset. |
| Keywords: |
| Aerial Imagery, Vehicle Tracking, Person Tracking, CNNs, Disaster Management, Traffic Management |
| Status : Conditional Accept (Oral Presentation) |
