Investigating the Impact of a Low-Rank Tensor-Based Approach on Deforestation Imagery

被引:0
|
作者
Zafeiropoulos, Charalampos [1 ]
Tzortzis, Ioannis N. [1 ]
Protopapadakis, Eftychios [2 ]
Kaselimi, Maria [1 ]
Doulamis, Anastasios [1 ]
Doulamis, Nikolaos [1 ]
机构
[1] Natl & Tech Univ Athens, Athens, Greece
[2] Univ Macedonia, Thessaloniki, Greece
来源
ADVANCES IN VISUAL COMPUTING, ISVC 2023, PT I | 2023年 / 14361卷
关键词
Deforestration; Land Cover; Tensor based model; Deep Learning; Limited Data; DEEP;
D O I
10.1007/978-3-031-47969-4_39
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
In this work we handle deforestation as a semantic segmentation problem using convolution-free methods, specifically tensor-based neural networks. The methodology follows a two-step process: first, we enhance the identification of deforestation areas through the application of low-level filters. Second, we merge the filter outcomes with the original image to create an object-level tensor representation. We introduce a tensor-based model that effectively identifies and analyzes complex patterns even with limited data availability. To evaluate our model, its outcomes are compared with established state-of-the-art models. The experimental results demonstrate the effectiveness and efficiency of the proposed approach in accurately mapping land cover patterns, particularly in deforestation detection and analysis. Based on the results, Squeezed-Net perform better when more data are available, while Tensor neural network model (TNN) outperformed when limited data are available.
引用
收藏
页码:501 / 512
页数:12
相关论文
共 50 条
  • [21] A novel ship trajectory reconstruction approach based on low-rank tensor completion
    Wu, Hao
    Hu, Liyang
    Li, Xueyao
    Wang, Chao
    Ye, Zhirui
    OCEAN ENGINEERING, 2024, 310
  • [22] Adaptive Rank Estimation Based Tensor Factorization Algorithm for Low-Rank Tensor Completion
    Liu, Han
    Liu, Jing
    Su, Liyu
    PROCEEDINGS OF THE 38TH CHINESE CONTROL CONFERENCE (CCC), 2019, : 3444 - 3449
  • [23] Robust Low-Rank Tensor Completion Based on Tensor Ring Rank via,&epsilon
    Li, Xiao Peng
    So, Hing Cheung
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2021, 69 : 3685 - 3698
  • [24] Low-Rank Tensor Completion by Approximating the Tensor Average Rank
    Wang, Zhanliang
    Dong, Junyu
    Liu, Xinguo
    Zeng, Xueying
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 4592 - 4600
  • [25] Tensor Factorization for Low-Rank Tensor Completion
    Zhou, Pan
    Lu, Canyi
    Lin, Zhouchen
    Zhang, Chao
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2018, 27 (03) : 1152 - 1163
  • [26] Low-rank tensor-based motion correction for abdominal cine-MRI data preserves gastric peristalsis
    Sclocco, R.
    Coll-Font, J.
    Napadow, V.
    Nguyen, C.
    Kuo, B.
    NEUROGASTROENTEROLOGY AND MOTILITY, 2023, 35
  • [27] LOW-RANK TENSOR-BASED MOTION CORRECTION FOR ABDOMINAL CINE-MRI DATA PRESERVES GASTRIC PERISTALSIS
    Sclocco, Roberta
    Coll-Font, Jaume
    Napadow, Vitaly
    Nguyen, Christopher
    Kuo, Braden
    GASTROENTEROLOGY, 2023, 164 (06) : S720 - S720
  • [28] Low-Rank tensor completion based on nonconvex regularization
    Su, Xinhua
    Ge, Huanmin
    Liu, Zeting
    Shen, Yanfei
    SIGNAL PROCESSING, 2023, 212
  • [29] Model-Based Tensor Low-Rank Clustering
    Li, Junge
    Mai, Qing
    JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS, 2024, 33 (01) : 208 - 218
  • [30] Low-rank tensor completion: a Riemannian manifold preconditioning approach
    Kasai, Hiroyuki
    Mishra, Bamdev
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 48, 2016, 48