Comparison between Three Registration Methods in the Case of Non-Georeferenced Close Range of Multispectral Images

Abstract

Cucumber powdery mildew, which is caused by Podosphaera xanthii, is a major disease that has a significant economic impact in cucumber greenhouse production. It is necessary to develop a non-invasive fast detection system for that disease. Such a system will use multispectral imagery acquired at a close range with a camera attached to a mobile cart’s mechanic extension. This study evaluated three image registration methods applied to non-georeferenced multispectral images acquired at close range over greenhouse cucumber plants with a MicaSense® RedEdge camera. The detection of matching points was performed using Speeded-Up Robust Features (SURF), and outliers matching points were removed using the M-estimator Sample Consensus (MSAC) algorithm. Three geometric transformations (affine, similarity, and projective) were considered in the registration process. For each transformation, we mapped the matching points of the blue, green, red, and NIR band images into the red-edge band space and computed the root mean square error (RMSE in pixel) to estimate the accuracy of each image registration. Our results achieved an RMSE of less than 1 pixel with the similarity and affine transformations and of less than 2 pixels with the projective transformation, whatever the band image. We determined that the best image registration method corresponded to the affine transformation because the RMSE is less than 1 pixel and the RMSEs have a Gaussian distribution for all of the bands, but the blue band.

Comprehensive Evaluation of Multispectral Image Registration Strategies in Heterogenous Agriculture Environment

“…Another work, found to be partially related to our experiment, was based on the registration of close-range and non-georeferenced MS images acquired in a greenhouse environment. This work compared spectral performances across different types of geometric transformations [ 24 ]. In contrast, our activity was conducted in field conditions.…”

“…This paper provides a certain reference to other scholars to advance their research on weed detection algorithms based on computer vision and achieve intelligent weed control and related areas of research and application [ 23 ]. There has been a similar work based on proximal sensing and feature-based MS image registration following different geometric transformations in plants imaged in a greenhouse environment using the same sensor [ 24 ]. Another experiment based on Parrot Sequoia MS images performed co-registration without assumptions based on scene structure and just required dense matching between two spectrally similar channels [ 7 ].…”

Design and Verification of a Low-Cost Multispectral Camera for Precision Agriculture Application

“…They are primarily based on finding homography for the whole image. Only the approaches for keypoint detection and matching are different [64]- [66].…”

Multispectral Image Matching Using SIFT and SURF Algorithm: A Review

“…SURF detectors performed efficiently in multispectral face recognitions where the combinations of conventional SURF detectors and FREAK descriptions extracted highest number of feature matching compare others algorithms [57]. Micasense RedEdge multispectral images also been tested using SURF techniques and achieve less than one pixel of RMSE when its combined with MSAC matcher algorithm [58].…”