Sensors in Precision Agriculture for the Monitoring of Plant Development and Improvement of Food ProductionView this Special Issue
Sensors in Precision Agriculture for the Monitoring of Plant Development and Improvement of Food Production
The importance of integrating technology into precision agriculture that allows the monitoring of plants and crops in order to obtain higher quality food together with an increase in production is fundamental. This importance is due to various factors such as climate change, food shortages, innocuousness factors, efficiency in food distribution, and the growth of the world population; the impact of these factors can be mitigated or reduced with the use of sensors that can help to generate the conditions for an optimal growth and development of crops and plants. The purpose of this special issue is to provide a scientific link that promotes the exchange of knowledge related to the use of sensors for the integration of technology in precision agriculture.
This special edition contains eight research articles accepted for publication after 2 or 3 review processes.
In the research article “A Preliminary Study of Seeding Absence Detection Method for Drills on the Soil Surface of Cropland Based on Ultrasonic Wave without Soil Disturbance”, C. Lu et al. propose the uses of one transmitting transducer and one receiving sensor to achieve an accurate seeding-absence measurement on the soil surface; the seeding-absence states are defined by a circle energy inside the tilled soil above seed layer or untilled soil layer. The authors used the Zhibolian 5200 ultrasonic detection instrument to obtain the ultrasonic information and the proposed method does not need to remove the soil covered on seeds and does not damage the seedlings. The authors conclude that method has the advantages of nondestructive measurement with the latest position of seeds immediately after seeding considering two states of seeds depth (25mm and 30mm).
In the research article “Detection of Apple Lesions in Orchards Based on Deep Learning Methods of CycleGAN and YOLOV3-Dense”, Y. Tian et al. propose an anthracnose lesions detection method based on YOLO-V3 deep learning and DenseNet. The authors confirmed a dataset of 140 anthracnose apple images and used CycleGAN to learn the features of apple lesions images and transplanted to healthy apple images and 500 healthy apple images. The authors conclude that the classification performance of the proposed method, compared with several state-of-art deep learning methods, presents the highest detection accuracy (95.57%).
In the research article “Fuzzy-Classification of the Maturity of the Tomato Using a Vision System”, M. J. Villaseñor-Aguilar et al. report the behavior of tomato maturity based on color in the RGB model; the tomato images were obtained using a Camera Module Raspberry Pi 2; the average value of the color components of four views of the tomato is the input variables of the Fuzzy System implemented in MATLAB which classified the tomato samples into six categories according to the U.S. Department of Agriculture. The authors concluded that their purposes are a good alternative to evaluate the maturity of tomatoes; this conclusion is based on the average error of 536.995 x 10−6.
In the research article “Nondestructive Quantification of the Ripening Process in Banana (Musa AAB Simmonds) Using Multispectral Imaging”, M. Santoyo-Mora et al. propose a nondestructive technique based on the processing of multispectral images to evaluate the ripening process of a banana (Musa AAB Simmonds) at the seventh stage of the growing process. The results were obtained using a set of multispectral imagery registered in a range of 270-1000 nm; the images were analyzed with three different techniques: Fourier fractal analysis; Hotelling transform; and cooccurrence matrix. The authors found that the analysis based on the cooccurrence matrix gave the best results; this method has the following advantages: it does not require complex calculations; it is rotational invariant; and the homogeneity index has relatively low variations.
In the research article “Peanut Detection Using Droplet Microfluidic Polymerase Chain Reaction Device”, S.-Y. Ma et al. propose the development of a droplet microfluidic PCR device to amplify specific peanut DNA fragments for detection of foodborne allergens. The authors used a cross-junction microchannel to induce emulsion droplets of water in oil for PCR on a chip which presents a 7.24% lower amount of evaporation amount prevented air bubble generation. The developed device was also successfully used to amplify DNA for various species, including sesame, Salmonella spp., and Staphylococcus aureus.
In the research article “Technology Roadmapping Architecture Based on Knowledge Management: Case Study for Improved Indigenous Coffee Production from Guerrero, Mexico”, D. I. Contreras-Medina et al. make a proposal to improve indigenous coffee production from Guerrero, Mexico. Based on knowledge management and technology roadmapping architecture, the authors identify the greenhouses and the knowledge and technology management networks as best strategies to be implemented, selected by the local coffee producers of Paraje Montero and Tierra Colorada from Guerrero, Mexico. From this, the use of emerging technologies for greenhouse in the stages of cultivation and growth according to indigenous coffee producer’s selection is proposed, supported on the design of management networks.
In the research article “A Benchmarking of Learning Strategies for Pest Detection and Identification on Tomato Plants for Autonomous Scouting Robots Using Internal Databases”, A. Gutierrez et al. present the comparison of two different approaches for pest detection on tomato plants based on learning strategies. A solution that combines computer vision and machine learning is compared against a deep learning solution. The authors conclude that deep learning technique is a better solution than the combination between computer vision and machine learning; this conclusion is based on the analysis of 4,331 original pictures converted into 54,743 images of different insect and eggs of Trialeurodes vaporariorum and Bemisia tabaci.
In the research article “An Approach of Beans Plant Development Classification Using Fuzzy Logic”, P. Correa et al. present a method to monitor the growth of bean plants from images taken (with controlled background and lighting) in their vegetative phase with a diffuse system that classifies these stages based on the extracted characteristics: average and standard deviation of the area of the plant in pixels. It was found that the artificial vision system can identify the stages; the vegetative phase: emergence, primary leaves, and first trifoliate leaf.
Conflicts of Interest
The authors declare that they have no conflicts of interest.
José A. Padilla-Medina
Luis M. Contreras-Medina
Miguel U. Gavilán
Jesus R. Millan-Almaraz
Juan E. Alvaro