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
  • [31] A Simpler Approach to Low-Rank Tensor Canonical Polyadic Decomposition
    Pimentel-Alarcon, Daniel L.
    2016 54TH ANNUAL ALLERTON CONFERENCE ON COMMUNICATION, CONTROL, AND COMPUTING (ALLERTON), 2016, : 474 - 481
  • [32] Low-Rank Tensor Completion Method for Implicitly Low-Rank Visual Data
    Ji, Teng-Yu
    Zhao, Xi-Le
    Sun, Dong-Lin
    IEEE SIGNAL PROCESSING LETTERS, 2022, 29 : 1162 - 1166
  • [33] Iterative tensor eigen rank minimization for low-rank tensor completion
    Su, Liyu
    Liu, Jing
    Tian, Xiaoqing
    Huang, Kaiyu
    Tan, Shuncheng
    INFORMATION SCIENCES, 2022, 616 : 303 - 329
  • [34] Sparse and Low-Rank Tensor Decomposition
    Shah, Parikshit
    Rao, Nikhil
    Tang, Gongguo
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 28 (NIPS 2015), 2015, 28
  • [35] NONPARAMETRIC LOW-RANK TENSOR IMPUTATION
    Bazerque, Juan Andres
    Mateos, Gonzalo
    Giannakis, Georgios B.
    2012 IEEE STATISTICAL SIGNAL PROCESSING WORKSHOP (SSP), 2012, : 876 - 879
  • [36] A QoS Prediction Approach Based on Truncated Nuclear Norm Low-Rank Tensor Completion
    Xia, Hong
    Dong, Qingyi
    Zheng, Jiahao
    Chen, Yanping
    Gao, Cong
    Wang, Zhongmin
    SENSORS, 2022, 22 (16)
  • [37] Low-Rank Regression with Tensor Responses
    Rabusseau, Guillaume
    Kadri, Hachem
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 29 (NIPS 2016), 2016, 29
  • [38] MULTIRESOLUTION LOW-RANK TENSOR FORMATS
    Mickelin, Oscar
    Karaman, Sertac
    SIAM JOURNAL ON MATRIX ANALYSIS AND APPLICATIONS, 2020, 41 (03) : 1086 - 1114
  • [39] LOW-RANK TENSOR HUBER REGRESSION
    Wei, Yangxin
    Luot, Ziyan
    Chen, Yang
    PACIFIC JOURNAL OF OPTIMIZATION, 2022, 18 (02): : 439 - 458
  • [40] Low-Rank Tensor MMSE Equalization
    Ribeiro, Lucas N.
    de Almeida, Andre L. F.
    Mota, Joao C. M.
    2019 16TH INTERNATIONAL SYMPOSIUM ON WIRELESS COMMUNICATION SYSTEMS (ISWCS), 2019, : 511 - 516