@inproceedings{414d61a88c8440d8a68b74e058383fe3,
title = "From simulation to reality: Ground vehicle detection in aerial imagery based on deep learning",
abstract = "Collecting aerial data from physical world is usually time-consuming. Image simulation is a significant data source for various ground target detection systems. Unfortunately, the reality gap between simulated and real data makes the model trained on simulated image not workable on real image. A translation method is proposed for tackling the simulation-toreality problem in this paper. First, image simulation system is employed for data preparation. Then, the simulated data is converted into a more similar one to the real image. The segmentation map is the bridge between simulated and real data. At last, the target detection model is used as the utility evaluation method for the simulated data. The simulated and synthesized data is used to train a vehicle detection model. Experiments show that results trained by synthesized data are really close to the real results. The proposed translation method can assist real image for target detection task, which is an effective data augmentation method for aerial data.",
keywords = "Convolution neural network, GAN, Image simulation, UAV, Vehicle detection",
author = "Yu Yang and Chengpo Mu and Ruiheng Zhang and Xuejian Li and Ruixin Yang",
note = "Publisher Copyright: {\textcopyright} COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.; 11th International Conference on Digital Image Processing, ICDIP 2019 ; Conference date: 10-05-2019 Through 13-05-2019",
year = "2019",
doi = "10.1117/12.2539755",
language = "English",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Jenq-Neng Hwang and Xudong Jiang",
booktitle = "Eleventh International Conference on Digital Image Processing, ICDIP 2019",
address = "United States",
}