Comprehensive Evaluation of Multispectral Image Registration Strategies in Heterogenous Agriculture Environment

被引:5
|
作者
Rana, Shubham [1 ]
Gerbino, Salvatore [1 ]
Crimaldi, Mariano [2 ]
Cirillo, Valerio [2 ]
Carillo, Petronia [3 ]
Sarghini, Fabrizio [2 ]
Maggio, Albino [2 ]
机构
[1] Univ Campania L Vanvitelli, Dept Engn, Via Roma 29, I-81031 Aversa, Italy
[2] Univ Naples Federico II, Dept Agr Sci, Via Univ 100, I-80055 Naples, Italy
[3] Univ Campania L Vanvitelli, Dept Biol & Pharmaceut Environm Sci & Technol, Via Antonio Vivaldi 43, I-81100 Caserta, Italy
关键词
binary mask; homography matrix; masked pixels; MS (multispectral); SIFT (scale-invariant feature transform); SEGMENTATION; HOMOGRAPHY; ROBUST;
D O I
10.3390/jimaging10030061
中图分类号
TB8 [摄影技术];
学科分类号
0804 ;
摘要
This article is focused on the comprehensive evaluation of alleyways to scale-invariant feature transform (SIFT) and random sample consensus (RANSAC) based multispectral (MS) image registration. In this paper, the idea is to extensively evaluate three such SIFT- and RANSAC-based registration approaches over a heterogenous mix containing Triticum aestivum crop and Raphanus raphanistrum weed. The first method is based on the application of a homography matrix, derived during the registration of MS images on spatial coordinates of individual annotations to achieve spatial realignment. The second method is based on the registration of binary masks derived from the ground truth of individual spectral channels. The third method is based on the registration of only the masked pixels of interest across the respective spectral channels. It was found that the MS image registration technique based on the registration of binary masks derived from the manually segmented images exhibited the highest accuracy, followed by the technique involving registration of masked pixels, and lastly, registration based on the spatial realignment of annotations. Among automatically segmented images, the technique based on the registration of automatically predicted mask instances exhibited higher accuracy than the technique based on the registration of masked pixels. In the ground truth images, the annotations performed through the near-infrared channel were found to have a higher accuracy, followed by green, blue, and red spectral channels. Among the automatically segmented images, the accuracy of the blue channel was observed to exhibit a higher accuracy, followed by the green, near-infrared, and red channels. At the individual instance level, the registration based on binary masks depicted the highest accuracy in the green channel, followed by the method based on the registration of masked pixels in the red channel, and lastly, the method based on the spatial realignment of annotations in the green channel. The instance detection of wild radish with YOLOv8l-seg was observed at a mAP@0.5 of 92.11% and a segmentation accuracy of 98% towards segmenting its binary mask instances.
引用
收藏
页数:25
相关论文
共 50 条
  • [41] AgriSenAI: Automating UAV thermal and multispectral image processing for precision agriculture
    Tulu, Boaz B.
    Teshome, Fitsum
    Ampatzidis, Yiannis
    Hailegnaw, Niguss Solomon
    Bayabil, Haimanote K.
    SOFTWAREX, 2025, 30
  • [42] Simultaneous Multiresolution Strategies for Nonrigid Image Registration
    Sun, Wei
    Niessen, Wiro J.
    van Stralen, Marijn
    Klein, Stefan
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2013, 22 (12) : 4905 - 4917
  • [43] Multispectral breast image grayscale and quality enhancement by repeated pair image registration & accumulation method
    Li, Gang
    Munawar, Adnan
    Win, Nan Su Su
    Fan, Meiling
    Nawaz, Muhammad Zeeshan
    Lin, Ling
    SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY, 2024, 320
  • [44] Distance-Dependent Multimodal Image Registration for Agriculture Tasks
    Berenstein, Ron
    Hocevar, Marko
    Godesa, Tone
    Edan, Yael
    Ben-Shahar, Ohad
    SENSORS, 2015, 15 (08) : 20845 - 20862
  • [45] Automated and Non-destructive Measurement of Plant Growth Characteristics Using a Multispectral Image Based Technique in Controlled Environment Agriculture
    Miller, Alexander
    Adhikari, Ranjeeta
    Nemali, Krishna
    HORTSCIENCE, 2018, 53 (09) : S311 - S311
  • [46] A comprehensive approach for multi-channel image registration
    Rohde, GK
    Pajevic, S
    Pierpaoli, C
    Basser, PJ
    BIOMEDICAL IMAGE REGISTRATION, 2003, 2717 : 214 - 223
  • [47] Quantitative evaluation of deformable image registration
    Zhong, Hualiang
    Siebers, Jeffrey V.
    2007 4TH IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING : MACRO TO NANO, VOLS 1-3, 2007, : 724 - 727
  • [48] Evaluation of two image registration systems
    Zhang, Y
    Hsi, W
    Chu, J
    Khan, A
    Mehta, P
    Bernard, D
    Abrams, R
    MEDICAL PHYSICS, 2005, 32 (06) : 1943 - 1943
  • [49] GF-2 Panchromatic and Multispectral Remote Sensing Image Registration Algorithm
    Wang, Sen
    Wang, Xiaofei
    Li, Jianxiong
    IEEE ACCESS, 2020, 8 : 138067 - 138076
  • [50] A metric for evaluation of deformable image registration
    Takemura, Akihiro
    Kojima, Hironori
    Ueda, Shinichi
    Isomura, Naoki
    Noto, Kimiya
    Ikeda, Tomohiro
    MEDICAL IMAGING 2015: IMAGE-GUIDED PROCEDURES, ROBOTIC INTERVENTIONS, AND MODELING, 2015, 9415