Car detection in images taken from unmanned aerial vehicles

In recent years, unmanned aerial vehicles have become a popular research platform with many application areas such as military, civil, commercial and recreational areas, thanks to their high maneuverability, vertical take-off / landing, and outdoor and indoor use. Today, small, light, and very high powerful embedding systems have been developed. Therefore, many real-time computer vision applications can be run on unmanned aerial vehicle platforms by integrating such embedding systems onto these vehicles. In this work, the problem of car detection (localization) in images taken from unmanned aerial vehicles has been studied. To this end, we collected a new aerial image dataset by using quadcopters and different type of cameras. To solve the car detection problem, the results were compared by using both the Polyhedral Conic Classifier and the You Only Look Once (YOLO) algorithm which is considered one of the fastest deep neural network methods in the literature.

[1]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Matti Pietikäinen,et al.  Face Description with Local Binary Patterns: Application to Face Recognition , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[4]  Hakan Cevikalp,et al.  Polyhedral Conic Classifiers for Visual Object Detection and Classification , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  David A. McAllester,et al.  Object Detection with Discriminatively Trained Part Based Models , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Hakan Cevikalp,et al.  Visual Object Detection Using Cascades of Binary and One-Class Classifiers , 2017, International Journal of Computer Vision.

[8]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[9]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[11]  Rafail N. Gasimov,et al.  Separation via polyhedral conic functions , 2006, Optim. Methods Softw..

[12]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.