Abstract | ||
---|---|---|
Growing cities and increasing traffic densities result in an increased demand for applications such as traffic monitoring, traffic analysis, and support of rescue work. These applications share the need for accurate detection of relevant vehicles, e.g. in aerial imagery. Recently, the application of deep learning based detection frameworks like Faster R-CNN clearly outperformed conventional detection methods for vehicle detection in aerial images. In this paper, we propose a detection framework that fuses Faster R-CNN and semantic labeling to integrate contextual information. We achieve an improved detection performance by decreasing the number of false positive detections while the number of candidate regions to classify is reduced. To demonstrate the generalization of our approach, we evaluate our detection framework for various ground sampling distances on a publicly available dataset. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/AVSS.2017.8078510 | 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) |
Keywords | Field | DocType |
semantic labeling,aerial imagery,traffic monitoring,traffic analysis,vehicle detection,traffic densities,faster R-CNN,deep learning | Computer vision,Traffic analysis,Pattern recognition,Computer science,Vehicle detection,Image segmentation,Sampling (statistics),Artificial intelligence,Deep learning,Fuse (electrical),Aerial imagery,Semantics | Conference |
ISBN | Citations | PageRank |
978-1-5386-2940-6 | 1 | 0.34 |
References | Authors | |
12 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lars Wilko Sommer | 1 | 31 | 9.49 |
Kun Nie | 2 | 1 | 0.68 |
Arne Schumann | 3 | 85 | 14.01 |
Tobias Schuchert | 4 | 93 | 12.21 |
Jürgen Beyerer | 5 | 315 | 75.37 |