VEHICLE OCCLUSION REMOVAL FROM SINGLE AERIAL IMAGES USING GENERATIVE ADVERSARIAL NETWORKS

被引:1
|
作者
Xiang, Meijie [1 ]
Azimi, Seyedmajid [2 ]
Bahmanyar, Reza [2 ]
Soergel, Uwe [1 ]
Reinartz, Peter [2 ]
机构
[1] Univ Stuttgart, Inst Photogrammetry, Stuttgart, Germany
[2] German Aerosp Ctr DLR, Remote Sensing Technol Inst, Oberpfaffenhofen, Germany
关键词
Aerial imagery; Deep learning; Generative Adversarial Network (GAN); HD maps; Vehicle occlusion removal;
D O I
10.5194/isprs-annals-X-1-W1-2023-629-2023
中图分类号
K85 [文物考古];
学科分类号
0601 ;
摘要
Removing occluding objects such as vehicles from drivable areas allows precise extraction of road boundaries and related semantic objects such as lane-markings, which is crucial for several applications such as generating high-definition maps for autonomous driving. Conventionally, multiple images of the same area taken at different times or from various perspectives are used to remove occlusions and to reconstruct the occluded areas. Nevertheless, these approaches require large amounts of data, which are not always available. Furthermore, they do not work for static occlusions caused by, among others, parked vehicles. In this paper, we address occlusion removal based on single aerial images using generative adversarial networks (GANs), which are able to deal with the mentioned challenges. To this end, we adapt several state-of-the-art GAN-based image inpainting algorithms to reconstruct the missing information. Results indicate that the StructureFlow algorithm outperforms the competitors and the restorations obtained are robust, with high visual fidelity in real-world applications. Furthermore, due to the lack of annotated aerial vehicle removal datasets, we generate a new dataset for training and validating the algorithms, the Aerial Vehicle Occlusion Removal (AVOR) dataset. To the best of our knowledge, our work is the first to address vehicle removal using deep learning algorithms to enhance maps.
引用
收藏
页码:629 / 634
页数:6
相关论文
共 50 条
  • [31] Generating Images in Compressed Domain Using Generative Adversarial Networks
    Kang, Byeongkeun
    Tripathi, Subarna
    Nguyen, Truong Q.
    IEEE ACCESS, 2020, 8 : 180977 - 180991
  • [32] STAIN NORMALIZATION OF HISTOPATHOLOGY IMAGES USING GENERATIVE ADVERSARIAL NETWORKS
    Zanjani, Farhad Ghazvinian
    Zinger, Svitlana
    Bejnordi, Babak Ehteshami
    van der Laak, Jeroen A. W. M.
    de With, Peter H. N.
    2018 IEEE 15TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2018), 2018, : 573 - 577
  • [33] Image shadow removal using cycle generative adversarial networks
    Tai, Shen-Chuan
    Chen, Peng-Yu
    Jiang, Xin-An
    JOURNAL OF ELECTRONIC IMAGING, 2019, 28 (01)
  • [34] Automatic Labeling of Industrial Images by using Generative Adversarial Networks
    Wagner, Daniel
    Kalischewski, Kathrin
    Tilgner, Stephan
    Velten, Joerg
    Kummert, Anton
    2019 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS), 2019,
  • [35] Lesion Segmentation in Gastroscopic Images Using Generative Adversarial Networks
    Sun, Yaru
    Li, Yunqi
    Wang, Pengfei
    He, Dongzhi
    Wang, Zhiqiang
    JOURNAL OF DIGITAL IMAGING, 2022, 35 (03) : 459 - 468
  • [36] Lesion Segmentation in Gastroscopic Images Using Generative Adversarial Networks
    Yaru Sun
    Yunqi Li
    Pengfei Wang
    Dongzhi He
    Zhiqiang Wang
    Journal of Digital Imaging, 2022, 35 : 459 - 468
  • [37] Single Image Snow Removal via Composition Generative Adversarial networks
    Li, Zhi
    Zhang, Juan
    Fang, Zhijun
    Huang, Bo
    Jiang, Xiaoyan
    Gao, Yongbin
    Hwang, Jenq-Neng
    IEEE ACCESS, 2019, 7 : 25016 - 25025
  • [38] Generative Adversarial Network for Overcoming Occlusion in Images: A Survey
    Saleh, Kaziwa
    Szenasi, Sandor
    Vamossy, Zoltan
    ALGORITHMS, 2023, 16 (03)
  • [39] Camera Tripod Removal Model in Panoramic Images Based on Generative Adversarial Networks
    Wu, Jian
    Deng, Honghui
    Cheng, Fei
    Wang, Hongjun
    Journal of Computers (Taiwan), 2023, 34 (03) : 19 - 29
  • [40] Generative Adversarial Networks for Noise Removal in Plain Carbon Steel Microstructure Images
    Panda, Aditi
    Naskar, Ruchira
    Pal, Snehanshu
    IEEE SENSORS LETTERS, 2022, 6 (03)