Abstract

Vehicle detection with orientation estimation in aerial images has received widespread interest as it is important for intelligent traffic management. This is a challenging task, not only because of the complex background and relatively small size of the target, but also the various orientations of vehicles in aerial images captured from the top view. The existing methods for oriented vehicle detection need several post-processing steps to generate final detection results with orientation, which are not efficient enough. Moreover, they can only get discrete orientation information for each target. In this paper, we present an end-to-end single convolutional neural network to generate arbitrarily-oriented detection results directly. Our approach, named Oriented_SSD (Single Shot MultiBox Detector, SSD), uses a set of default boxes with various scales on each feature map location to produce detection bounding boxes. Meanwhile, offsets are predicted for each default box to better match the object shape, which contain the angle parameter for oriented bounding boxes’ generation. Evaluation results on the public DLR Vehicle Aerial dataset and Vehicle Detection in Aerial Imagery (VEDAI) dataset demonstrate that our method can detect both the location and orientation of the vehicle with high accuracy and fast speed. For test images in the DLR Vehicle Aerial dataset with a size of 5616 × 3744 , our method achieves 76.1% average precision (AP) and 78.7% correct direction classification at 5.17 s on an NVIDIA GTX-1060.

Highlights

  • As a fundamental problem faced by intelligent traffic management, vehicle detection in aerial images plays a very important role for many applications [1,2,3,4,5]

  • We evaluate our method for oriented vehicle detection on two public datasets, namely the DLR Vehicle Aerial dataset and the Vehicle Detection in Aerial Imagery (VEDAI) dataset

  • To evaluate our method’s performance on the DLR Vehicle Aerial dataset, the experiments are divided into two parts: oriented vehicle detection and orientation estimation

Read more

Summary

Introduction

As a fundamental problem faced by intelligent traffic management, vehicle detection in aerial images plays a very important role for many applications [1,2,3,4,5] Both position and orientation are important information for practical use. Over the last few decades, numerous detectors have been developed for vehicle detection in aerial images [6,7,8,9,10,11,12] These methods have shown promising performance, but most of them return the detection results of axis-aligned bounding boxes, which cannot describe the oriented vehicles precisely. The sliding window technique leads to heavy computational costs

Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call