Vehicle Detection in Aerial Images

TL;DR

This paper introduces a novel CNN framework with double focal loss and skip connections for vehicle detection in aerial images, addressing challenges like small object size and complex backgrounds, and provides a new large-scale dataset.

Contribution

The paper proposes a new DFL-CNN framework with double focal loss and skip connections, and introduces the first large-scale vehicle detection dataset for aerial images.

Findings

DFL-CNN outperforms baseline models on benchmark datasets.

The new dataset ITCVD enhances vehicle detection research.

Focal loss improves detection accuracy for small vehicles.

Abstract

The detection of vehicles in aerial images is widely applied in many applications. Comparing with object detection in the ground view images, vehicle detection in aerial images remains a challenging problem because of small vehicle size, monotone appearance and the complex background. In this paper, we propose a novel double focal loss convolutional neural network framework (DFL-CNN). In the proposed framework, the skip connection is used in the CNN structure to enhance the feature learning. Also, the focal loss function is used to substitute for conventional cross entropy loss function in both of the region proposed network and the final classifier. We further introduce the first large-scale vehicle detection dataset ITCVD with ground truth annotations for all the vehicles in the scene. We demonstrate the performance of our model on the existing benchmark DLR 3K dataset as well as the ITCVD dataset. The experimental results show that our DFL-CNN outperforms the baselines on vehicle detection.