Special Issue "Image Processing in Agriculture and Forestry"
A special issue of Journal of Imaging (ISSN 2313-433X).
Deadline for manuscript submissions: closed (31 December 2016)
Prof. Dr. Gonzalo Pajares Martinsanz
Department Software Engineering and Artificial Intelligence, Faculty of Informatics, University Complutense of Madrid, 28040 Madrid, Spain
Website | E-Mail
Interests: computer vision; image processing; pattern recognition; 3D image reconstruction, spatio-temporal image change detection and track movement; fusion and registering from imaging sensors; superresolution from low-resolution image sensors
Prof. Dr. Francisco Rovira-Más
Agricultural Robotics Laboratory, Polytechnic University of Valencia, 46022 Valencia, Spain
Website | E-Mail
Interests: agricultural robotics and automation; intelligent vehicles; artificial intelligence; machine vision; mechatronics; control systems; autonomous navigation; stereoscopic vision; fluid power; automatic steering; off-road equipment; precision agriculture
Agriculture, forestry and forests are specific areas where imaging-based systems play an important role. They allow a more efficient use of resources while facilitating the realization of different tasks, which are occasionally difficult and dangerous.
Image acquisition, processing and interpretation are oriented toward the efficiency of agricultural activities.
The following is a list of the main topics covered by this Special Issue. The issue will, however, not be limited to these topics:
- Image acquisition devices and systems in outdoor environments.
- Image processing techniques: color, segmentation, texture analysis, image fusion.
- Computing vision-based approaches: pattern recognition, 3D structures and movement.
- Applications: autonomous agricultural vehicles, obstacle avoidance, crop rows detection, yield estimation and quality, plant health, trees monitoring, crown height, bark thickness, communications.
Prof. Dr. Gonzalo Pajares Martinsanz
Prof. Dr. Francisco Rovira-Más
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Journal of Imaging is an international peer-reviewed open access quarterly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) is waived for well-prepared manuscripts submitted to this issue. Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
The below list represents only planned manuscripts. Some of these manuscripts have not been received by the Editorial Office yet. Papers submitted to MDPI journals are subject to peer-review.
Title: Imaging for High-Throughput Phenotyping in Energy Sorghum
Author: Alex Thomasson et al.
Abstract: The paper will report on (1) observations related to challenges in identifying and measuring plant-stalk properties, (2) imaging techniques to meet these challenges, and (3) testing of the imaging solution.
Title: Comparison of Off-the-Shelf Small Unmanned Aerial Systems Using Image Processing
Authors: Bulanon, D.M., Cano, E., Horton, R.
Abstract: Precision agriculture is a farm management technology that involves
sensing and then responding to the observed variability in the field.
Remote sensing is one of the tools of precision agriculture. The
emergence of small unmanned aerial systems (sUAS) have paved the way
to accessible remote sensing tools for farmers. This paper describes
the comparison of two popular off-the-shelf sUASs: 3DR Iris and DJI
Phantom 2. Both units are equipped with a camera gimbal attached with
a GoPro camera. The comparison of the two sUAS involves a hovering
test and a rectilinear motion test. In the hovering test, the sUAS was
allowed to hover over a known object and images were taken every
second for two minutes. The position of the object in the images was
measured and this was used to assess the stability of the sUAV while
hovering. In the rectilinear test, the sUAS was allowed to follow a
straight path and images of a lined track was acquired. The lines on
the images were then measured on how accurate the sUAS followed the
path. Results showed that both sUAV performed well in both the
hovering test and the rectilinear motion test. This demonstrates that
both sUASs can be used for agricultural monitoring.
Title: Combining Satellite, Aerial and Ground Measurements to Assess Forest Carbon Stocks in Democratic Republic of Congo
Author: Jean-François Bastin et al.
Abstract: Monitoring tropical forest carbon stocks changes is a rising topic in the recent years, as a result of REDD+ mechanisms negotiations. Aerial and satellite remote sensing technologies offer cost advantages in implementing large scale forest inventories. Despite the recent progress, no widely operational and cost effective method has yet been delivered for central Africa forest monitoring. In the present study, we assess the potential of use of aireborne stereoscopic images to predict aboveground-biomass (AGB) variations of forests located in the Maï Ndombe region of the Democratic Republic of the Congo. In particular, we built a simple linear model to predict the AGB from airborne sterescopic image pair metrics. The accuracy of the results (R² = 0.7) allow to consider the applications of the method on a much larger scale but will probal by require some adjustments considering the variation of forest structure and allometry among the main forest types of Central Africa.
Title: Analysis of the effect of direct sunlight on the calculation of NDVI for ground-truth multispectral images
Authors: Pilar Barreiro, Pilar Barreiro et al.
Abstract: A new tool, such as unmanned aerial vehicles (UAV), may help to solve the problems derived from data obtained from sensors mounted on satellites. This new tool has advantages and disadvantages in its application regarding the techniques used so far.
In this work, we have studied NDVI under both: direct and diffuse light conditions computed on multispectral images, because it is believed to be one of the parameters, external to the crop that affects mostly the determination of vegetation index. Crop data, taken in conditions of abundant clouds, are data that until now have not been obtained with satellite records. Nowadays multispectral cameras mounted on unmanned aerial vehicles, allow taking the data under these new conditions. Diffuse lighting has the advantage that the incidence of light on the crop is much more homogeneous than in clear-sky conditions, where even making photos in conditions of solar 12h shadows appear. Moreover, the increased spatial resolution derived from the lower flying height allows observing individual plants in the plot, as well as individualized weeds; unavailable from satellite images.
A particularly interesting aspect is to know if the data of concerning both lighting conditions are comparable, in order to assess the usability of both types of data into a historical study. Many authors agree that the use of UAVs allows data collection in diverse conditions compared to satellite, but nobody shows whether the data taken with this new technique are of better or worse quality than those taking so far.
Title: Estimating area of paddy fields in Korean Peninsula around 2001 using vegetation and water indices based on Landsat Thematic Mapper/Enhanced Thematic Mapper Plus data in 2 seasons
Author: Dr. Katsuo Okamoto
Affiliation: NARO Institute for Agro-Environmental Sciences, 1-3 Kannon-dai 3-chome, Tsukuba, 305-8604, Japan
Abstract: Using water and vegetation indices, a method to classify land cover was developed and applied Landsat TM/ETM+ data to estimate the area of paddy field in Korean Peninsula in 2000-2002. NDVI and MNDWI were calculated from TM/ETM+ data in the rice-planting season and the ripening season. Using these indices, the data in each season were classified into 5 categories. Finally, using a decision table from land cover for two seasons, pixels changing from water to vegetation were defined as paddy fields. The estimation accuracy was around 80%. The result shows that this classification method reduced working hours comparing with the usual methods, such as unsupervised classification and supervised classification.