Urban Aquatic Scene Expansion for Semantic Segmentation in Cityscapes

被引:2
|
作者
Yue, Zongcheng [1 ]
Lo, Chun-Yan [1 ]
Wu, Ran [2 ]
Ma, Longyu [1 ]
Sham, Chiu-Wing [1 ]
机构
[1] Univ Auckland, Sch Comp Sci, Auckland 1010, New Zealand
[2] Harbin Inst Technol, Sch Comp Sci, Harbin 150001, Peoples R China
关键词
deep learning; semantic segmentation; Cityscapes; aquatic images;
D O I
10.3390/urbansci8020023
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
In urban environments, semantic segmentation using computer vision plays a pivotal role in understanding and interpreting the diverse elements within urban imagery. The Cityscapes dataset, widely used for semantic segmentation in urban scenes, predominantly features urban elements like buildings and vehicles but lacks aquatic elements. Recognizing this limitation, our study introduces a method to enhance the Cityscapes dataset by incorporating aquatic classes, crucial for a comprehensive understanding of coastal urban environments. To achieve this, we employ a dual-model approach using two advanced neural networks. The first network is trained on the standard Cityscapes dataset, while the second focuses on aquatic scenes. We adeptly integrate aquatic features from the marine-focused model into the Cityscapes imagery. This integration is carefully executed to ensure a seamless blend of urban and aquatic elements, thereby creating an enriched dataset that reflects the realities of coastal cities more accurately. Our method is evaluated by comparing the enhanced Cityscapes model with the original on a set of diverse urban images, including aquatic views. The results demonstrate that our approach effectively maintains the high segmentation accuracy of the original Cityscapes dataset for urban elements while successfully integrating marine features. Importantly, this is achieved without necessitating additional training, which is a significant advantage in terms of resource efficiency.
引用
收藏
页数:17
相关论文
共 50 条
  • [1] The Cityscapes Dataset for Semantic Urban Scene Understanding
    Cordts, Marius
    Omran, Mohamed
    Ramos, Sebastian
    Rehfeld, Timo
    Enzweiler, Markus
    Benenson, Rodrigo
    Franke, Uwe
    Roth, Stefan
    Schiele, Bernt
    2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 3213 - 3223
  • [2] Urban Scene Semantic Segmentation with Insufficient Labeled Data
    Zheng, Qi
    Chen, Jun
    Huang, Peng
    Hu, Ruimin
    CHINA COMMUNICATIONS, 2019, 16 (11) : 212 - 221
  • [3] Urban Scene Semantic Segmentation with Insufficient Labeled Data
    Qi Zheng
    Jun Chen
    Peng Huang
    Ruimin Hu
    中国通信, 2019, 16 (11) : 212 - 221
  • [4] Structured prediction for urban scene semantic segmentation with geographic context
    Volpi, Michele
    Ferrari, Vittorio
    2015 JOINT URBAN REMOTE SENSING EVENT (JURSE), 2015,
  • [5] Effective Use of Synthetic Data for Urban Scene Semantic Segmentation
    Saleh, Fatemeh Sadat
    Aliakbarian, Mohammad Sadegh
    Salzmann, Mathieu
    Petersson, Lars
    Alvarez, Jose M.
    COMPUTER VISION - ECCV 2018, PT II, 2018, 11206 : 86 - 103
  • [6] Urban Scene Semantic Segmentation with Low-Cost Coarse Annotation
    Das, Anurag
    Xian, Yongqin
    He, Yang
    Akata, Zeynep
    Schiele, Bernt
    2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2023, : 5967 - 5976
  • [7] Multi-Feature Aggregation for Semantic Segmentation of an Urban Scene Point Cloud
    Chen, Jiaqing
    Zhao, Yindi
    Meng, Congtang
    Liu, Yang
    REMOTE SENSING, 2022, 14 (20)
  • [8] Semantic segmentation of 3D textured meshes for urban scene analysis
    Rouhani, Mohammad
    Lafarge, Florent
    Alliez, Pierre
    ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2017, 123 : 124 - 139
  • [9] Fast Semantic Segmentation for Scene Perception
    Zhang, Xuetao
    Chen, Zhenxue
    Wu, Q. M. Jonathan
    Cai, Lei
    Lu, Dan
    Li, Xianming
    IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2019, 15 (02) : 1183 - 1192
  • [10] Indoor Scene Segmentation with Semantic Cuboids
    Fang, Zhuoqun
    Wu, Chengdong
    Jia, Tong
    2015 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND BIOMIMETICS (ROBIO), 2015, : 2545 - 2550