RGB and multispectral UAV image fusion for Gramineae weed detection in rice fields

Barrero, Oscar; Perdomo, Sammy A.

doi:10.1007/s11119-017-9558-x

Cited by 86 publications

(48 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Huang et al (2017) have published an overview about the development and applications of UAVs at low altitudes for precision weed management, and the potential of UAVs for mapping weeds at field scales has been recently evaluated by Lambert et al (2018). UAV images have been successfully used to detect and map broadleaved and grass weeds patches within annual crops for early postemergence SSWM programs (Peña et al 2013;Castaldi et al 2017;Lottes et al 2017;Torres-Sánchez et al 2014, López-Granados et al 2016Barrero and Perdomo 2018). This increasing development and use of UAVs provides a quick, timely and economical source of ancillary information that can be used to enhance the accuracy of estimations, however, so far, the use of kriging with UAV-derived auxiliary variables to improve the spatial mapping of a sparsely sampled variable is rare (Schirrmann et al 2017).…”

Section: Introductionmentioning

confidence: 99%

Papaver rhoeas L. mapping with cokriging using UAV imagery

et al. 2019

View full text Add to dashboard Cite

Accurately mapping the spatial distribution of weeds within a field is a first step towards effective Site-specific Weed Management. The main objective of this study was to investigate if the multivariate geostatistical method of cokriging (COK) can be used to improve the accuracy of Papaver rhoeas L. infestations maps in winter wheat fields using high-resolution UAV imagery as ancillary information. The primary variable was obtained by intensive grid weed density field samplings and the secondary variables were derived from the UAV imagery taken the same day as the weed field samplings (e.g. wavebands and derivative products, such as band ratios and vegetation indexes). Univariate Ordinary Kriging (OK) and multivariate Cokriging (COK) interpolation methods were used and compared for Papaver density mapping. The performances of the different methods were assessed by crossvalidation. The results indicated that COK outperformed OK in the spatial interpolation of Papaver density. COK reduced the prediction errors and enhanced the accuracy of Papaver estimates maps. The best performances were obtained when COK was performed with the UAV-secondary variables that yielded the highest correlation with Papaver density and produced the strongest spatial cross-semivariograms. On average, the COK with UAVderived ancillary variables improved the accuracy of mapping Papaver density by 11 to 21% compared with OK. The results suggest the great potential of high-resolution UAV imagery as a source of ancillary information to improve the accuracy of spatial mapping of sparsely sampled target variables using COK.

show abstract

Section: Introductionmentioning

confidence: 99%

Papaver rhoeas L. mapping with cokriging using UAV imagery

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The textural features, illumination, and resolution in the visible, thermal infrared, and near-infrared crop images differ, and the image contrasts are also not the same [40,41]. The visible or near-infrared farmland crops images have high resolution, and the textural features are distinct.…”

Section: Determination Of the Dynamic Contrast Thresholdmentioning

confidence: 99%

“…Visible and near-infrared UAV images all contain abundant image information, and the image contrast is high [40,57]. The standard SIFT method extracts excess feature points, and the time consumption is extensive, which reduces the efficiency of UAV image mosaicking [58].…”

Section: Applicability Of Algorithm To Images From Different Sourcesmentioning

confidence: 99%

Rapid Mosaicking of Unmanned Aerial Vehicle (UAV) Images for Crop Growth Monitoring Using the SIFT Algorithm

et al. 2019

View full text Add to dashboard Cite

To improve the efficiency and effectiveness of mosaicking unmanned aerial vehicle (UAV) images, we propose in this paper a rapid mosaicking method based on scale-invariant feature transform (SIFT) for mosaicking UAV images used for crop growth monitoring. The proposed method dynamically sets the appropriate contrast threshold in the difference of Gaussian (DOG) scale-space according to the contrast characteristics of UAV images used for crop growth monitoring. Therefore, this method adjusts and optimizes the number of matched feature point pairs in UAV images and increases the mosaicking efficiency. Meanwhile, based on the relative location relationship of UAV images used for crop growth monitoring, the random sample consensus (RANSAC) algorithm is integrated to eliminate the influence of mismatched point pairs in UAV images on mosaicking and to keep the accuracy and quality of mosaicking. Mosaicking experiments were conducted by setting three types of UAV images in crop growth monitoring: visible, near-infrared, and thermal infrared. The results indicate that compared to the standard SIFT algorithm and frequently used commercial mosaicking software, the method proposed here significantly improves the applicability, efficiency, and accuracy of mosaicking UAV images in crop growth monitoring. In comparison with image mosaicking based on the standard SIFT algorithm, the time efficiency of the proposed method is higher by 30%, and its structural similarity index of mosaicking accuracy is about 0.9. Meanwhile, the approach successfully mosaics low-resolution UAV images used for crop growth monitoring and improves the applicability of the SIFT algorithm, providing a technical reference for UAV application used for crop growth and phenotypic monitoring.

show abstract

“…Given the advantages and limitations of the current state of technology for automated or robotic weeding, future research in perception systems will likely focus on either increasing data dimensions or increasing the complexity of algorithms for better weed perception performance. Data dimensions can be increased by fusing sensors from different perspectives or with different sensors that provide complementary information (Barrero and Perdomo, 2018;Gao et al, 2018;Shchez and Marchant, 2000). More complex image processing algorithm can be achieved using deep learning (DL) techniques.…”

Section: Future Trends In Researchmentioning

confidence: 99%

The use of agricultural robots in weed management and control

Steward¹,

Gai²,

Tang³

2019

Burleigh Dodds Series in Agricultural Science

View full text Add to dashboard Cite

Weed management and control are essential for the production of high-yielding and high-quality crops, and advances in weed control technology have had a huge impact on agricultural productivity. Any effective weed control technology needs to be both robust and adaptable. Robust weed control technology will successfully control weeds in spite of variability in the field conditions. Adaptable weed control technology has the capacity to change its strategy in the context of evolving weed populations, genetics, and climatic conditions. This chapter focuses on key work in the development of robotic weeders, including weed perception systems and weed control mechanisms. Following an extensive introduction, the chapter addresses the challenges of robotic weed control focusing on both perception systems, which can detect and classify weed plants from crop plants, and also weed control mechanisms, covering both chemical and mechanical weed control. A case study of an automated weeding system is provided. Disciplines Agricultural Economics | Agriculture | Bioresource and Agricultural Engineering | Robotics Comments This chapter is published as Steward, Brian, Jingyao Gai, and Lie Tang. "The use of agricultural robots in weed management and control. " In Robotics and automation for improving agriculture, edited by

show abstract

RGB and multispectral UAV image fusion for Gramineae weed detection in rice fields

Cited by 86 publications

References 22 publications

Papaver rhoeas L. mapping with cokriging using UAV imagery

Papaver rhoeas L. mapping with cokriging using UAV imagery

Rapid Mosaicking of Unmanned Aerial Vehicle (UAV) Images for Crop Growth Monitoring Using the SIFT Algorithm

The use of agricultural robots in weed management and control

Contact Info

Product

Resources

About