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.


    Access

    Download


    Export, share and cite



    Title :

    Semantic labeling for improved vehicle detection in aerial imagery


    Contributors:
    Sommer, L. (author) / Nie, K. (author) / Schumann, A. (author) / Schuchert, Tobias (author) / Beyerer, Jürgen (author)

    Conference:

    2017


    Publication date :

    2017


    Size :

    6 pages



    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    Unknown




    Vehicle detection over DOP20 aerial imagery

    Marple GmbH | Mobilithek

    Free access

    Deep Learning based Vehicle Detection in Aerial Imagery

    Sommer, Lars Wilko | TIBKAT | 2021

    Free access

    Deep Learning based Vehicle Detection in Aerial Imagery

    Sommer, Lars | DataCite | 2018

    Free access

    Deep Learning based Vehicle Detection in Aerial Imagery

    Sommer, Lars Wilko | TIBKAT | 2022

    Free access

    Deep Learning based Vehicle Detection in Aerial Imagery

    Sommer, Lars Wilko | GWLB - Gottfried Wilhelm Leibniz Bibliothek | 2022

    Free access