Object detection in aerial images, particularly of vehicles, is highly important in remote sensing applications including traffic management, urban planning, parking space utilization, surveillance, and search and rescue. In this paper, we investigate the ability of three-dimensional (3D) feature maps to improve the performance of deep neural network (DNN) for vehicle detection. First, we propose a DNN based on YOLOv3 with various base networks, including DarkNet-53, SqueezeNet, MobileNet-v2, and DenseNet-201. We assessed the base networks and their performance in combination with YOLOv3 on efficiency, processing time, and the memory that each architecture required. In the second part, 3D depth maps were generated using pairs of aerial images and their parallax displacement. Next, a fully connected neural network (fcNN) was trained on 3D feature maps of trucks, semi-trailers and trailers. A cascade of these networks was then proposed to detect vehicles in aerial images. Upon the DNN detecting a region, coordinates and confidence levels were used to extract the corresponding 3D features. The fcNN used 3D features as the input to improve the DNN performance. The data set used in this work was acquired from numerous flights of an unmanned aerial vehicle (UAV) across two industrial harbors over two years. The experimental results show that 3D features improved the precision of DNNs from 88.23 % to 96.43 % and from 97.10 % to 100 % when using DNN confidence thresholds of 0.01 and 0.05, respectively. Accordingly, the proposed system was able to successfully remove 72.22 % to 100 % of false positives from the DNN outputs. These results indicate the importance of 3D features utilization to improve object detection in aerial images for future research. CCBY ; open access


    Access

    Download


    Export, share and cite



    Title :

    Vehicle Detection in Aerial Images Based on 3D Depth Maps and Deep Neural Networks


    Contributors:

    Publication date :

    2021-01-01


    Remarks:

    Scopus 2-s2.0-85099218070



    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    629



    Fast deep vehicle detection in aerial images

    Sommer, L.W. / Schuchert, Tobias / Beyerer, Jürgen | Fraunhofer Publica | 2017

    Free access

    Convolutional Neural Networks for Aerial Vehicle Detection and Recognition

    Soleimani, Amir / Nasrabadi, Nasser M. / Griffith, Elias et al. | IEEE | 2018


    Change detection in aerial images using three-dimensional feature maps

    Javadi, Mohammad Saleh / Dahl, Mattias / Pettersson, Mats | BASE | 2020

    Free access

    A real-time object detection framework for aerial imagery using deep neural networks and synthetic training images

    Narayanan, Priya / Borel-Donohue, Christoph / Lee, Hyungtae et al. | SPIE | 2018


    Computing depth maps from descent images

    Xiong, Y. / Olson, C. F. / Matthies, L. H. | British Library Online Contents | 2005