Fast Scene Layout Estimation via Deep Hashing

被引:0
|
作者
Zhu, Yi [1 ]
Luo, Wenbing [1 ]
Li, Hanxi [1 ]
Wang, Mingwen [1 ]
机构
[1] Jiangxi Normal Univ, 99 Ziyang Rd, Nanchang, Jiangxi, Peoples R China
来源
THIRD INTERNATIONAL WORKSHOP ON PATTERN RECOGNITION | 2018年 / 10828卷
基金
中国国家自然科学基金;
关键词
deep learning; hashing; scene layout estimation;
D O I
10.1117/12.2501793
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
In this work, we propose an efficient method for accurately estimating the scene layout in both outdoor and indoor scenarios. For outdoor scenes, the horizon line in a road image is estimated while for indoor scenes, the wall-wall, wall-ceiling and wall-floor edges are estimated. A number of image patches are first cropped from the image and then feed into a convolution neural network which is originally trained for object detection. The yielded deep features from three different layers are compared with the features of the training patches, in a spatial-aware hashing fashion. The horizon line is then estimated via a sophisticated voting stage in which different voters are considered differently according to their importances. In particular, for the more complex labels (in indoor scenes), we introduce the structural forest for further enhancing the deep features before learning the hashing function. In practice, the proposed algorithm outperforms the state-of-the-art methods in accuracy for outdoor scenes while achieves the comparable performance to the best indoor scene layout estimators. Further more, the proposed method is real-time speed (up to 25 fps).
引用
收藏
页数:10
相关论文
共 50 条
  • [41] Deep Self-Taught Hashing for Image Retrieval
    Liu, Yu
    Song, Jingkuan
    Zhou, Ke
    Yan, Lingyu
    Liu, Li
    Zou, Fuhao
    Shao, Ling
    IEEE TRANSACTIONS ON CYBERNETICS, 2019, 49 (06) : 2229 - 2241
  • [42] Deep Learning Approaches Assessment for Underwater Scene Understanding and Egomotion Estimation
    Teixeira, Bernardo
    Silva, Hugo
    Matos, Anibal
    Silva, Eduardo
    OCEANS 2019 MTS/IEEE SEATTLE, 2019,
  • [43] Unsupervised semantic deep hashing
    Jin, Sheng
    Yao, Hongxun
    Sun, Xiaoshuai
    Zhou, Shangchen
    NEUROCOMPUTING, 2019, 351 (19-25) : 19 - 25
  • [44] Deep Attention Residual Hashing
    Li, Yang
    Miao, Zhuang
    He, Ming
    Zhang, Yafei
    Li, Hang
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2018, E101A (03) : 654 - 657
  • [45] Deep Discrete Supervised Hashing
    Jiang, Qing-Yuan
    Cui, Xue
    Li, Wu-Jun
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2018, 27 (12) : 5996 - 6009
  • [46] Asymmetric deep online Hashing
    Wu, Nannan
    Yang, Xiaohan
    Liu, Wenhao
    Chang, Xinyi
    Guo, Chengyin
    Wang, Zhen
    Dianzi Keji Daxue Xuebao/Journal of the University of Electronic Science and Technology of China, 2025, 54 (01): : 103 - 115
  • [47] Fast retrieval of similar images of pulmonary nodules based on deep multi-index hashing
    Hao R.
    Qin Y.
    Qiang Y.
    Int. J. Wireless Mobile Comput., 2023, 4 (303-308): : 303 - 308
  • [48] DEEP HASHING WITH MIXED SUPERVISED LOSSES FOR IMAGE SEARCH
    Liang, Dawei
    Yan, Ke
    Zeng, Wei
    Wang, Yaowei
    Yuan, Qingsheng
    Bao, Xiuguo
    Tian, Yonghong
    2017 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW), 2017,
  • [49] Fast Beamforming Design via Deep Learning
    Huang, Hao
    Peng, Yang
    Yang, Jie
    Xia, Wenchao
    Gui, Guan
    IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2020, 69 (01) : 1065 - 1069
  • [50] SPD Hashing Network for Fast Image Set Classification and Retrieval
    Wang, Xiaxin
    Shen, Xiaobo
    Zong, Lixuan
    2024 IEEE CONFERENCE ON ARTIFICIAL INTELLIGENCE, CAI 2024, 2024, : 1324 - 1325