جستجوی مقالات مرتبط با کلیدواژه « پهپاد » در نشریات گروه « مکانیزاسیون کشاورزی »

Considering that wheat and barley are important and strategic products in Iran, the Sunn pest is one of the most important pests of these products. Every year, the country's plant protection organization monitors this dangerous pest so that an order to fight it can be issued at the right time. Farm monitoring is a very difficult, time-consuming, and destructive task; it also requires a large number of specialized human resources. One of the goals of this research is to create a non-destructive method for such an operation in the identification of Sunn pests. In this research, the counting of Sunn pests in cereal farms was done by two methods using aerial image processing by recording 954 images and framing method and eye counting in the farm by an expert in two farms with different numbers of this pest. The number of pests in each image was obtained after processing the images using the Python programming language in the PyCharm learning library. The statistical study results showed no significant difference at the 1% probability level between the average data of the two methods. This method can be used confidently to monitor the Sunn pest in cereal farms. In this research, by using UAV image processing, a fast, accurate, and non-destructive method was proposed and evaluated for counting the pests and issuing spraying orders in cereal farms.

Maize is one of the most important cereal crops worldwide, providing staple food for people globally. Counting maize tassels provides essential information about yield prediction, growth status, and plant phenotyping, but traditional manual approaches are expensive and time-consuming. Recent developments in technology, including high-resolution RGB imagery acquired by unmanned aerial vehicles (UAVs) and advanced machine-learning techniques such as deep learning (DL), have been used to analyze genotypes, phenotypes, and crops.In this study, we modified the YOLOv5s single-stage object detection technique based on a deep convolutional neural network and named it MYOLOv5s. We incorporated BottleneckCSP structures, Hardswish activation function, and two-dimensional spatial dropout layers to increase tassel detection accuracy and reduce overfitting. Our method's performance was compared with three state-of-the-art algorithms: Tasselnetv2+, RetinaNet, and Faster R-CNN. The results obtained from our proposed method demonstrate the effectiveness of MYOLOv5s in detecting and counting maize tassels. 

The High-Intensity Phenotyping Site (HIPS) dataset was collected from the large field at the Agronomy Center for Research and Education (ACRE) of Purdue University, located in West Lafayette, Indiana, USA during the 2020 growing season. A Sony Alpha 7R-III RGB camera mounted on a UAV at a 20m altitude captured high-resolution orthophotos with a pixel resolution of 0.25 cm. The dataset consisted of two replications of 22 entries each for hybrids and inbreds, planted on May 12 using a two-row segment plot layout with a plant population of 30,000 per acre. The hybrids and inbreds in this dataset had varying flowering dates, ranging from 20 days between the first and last variety.This article uses orthophotos taken on July 20th and 24th to train and test the proposed deep network "MYOLOv5s." These orthophotos were divided into 15 images (3670×2150) and then cropped to obtain 150 images (608 × 2048) for each date. Three modifications were applied to the original YOLOv5s to form MYOLOv5s: BottleneckCSP structures were added to the neck part of the YOLOv5s, replacing some C3 modules; two-dimensional spatial dropout layers were used in the defect layer; and the Hardswish activation function was utilized in the convolution structures. These modifications improved tassel detection accuracy. MYOLOv5s was implemented in the Pytorch framework, and the Adam algorithm was applied to optimize it. Hyper-parameters such as the number of epochs, batch size, and learning rates were also optimized to increase tassel detection accuracy.

In this study, we first compared the original and modified YOLOv5s techniques, and our results show that MYOLOv5s improved tassel detection accuracy by approximately 2.80%. We then compared MYOLOv5s performance to the counting-based approach TasselNetv2+ and two detection-based techniques: Faster R-CNN and RetinaNet. Our results demonstrated the superiority of MYOLOv5s in terms of both accuracy and inference time. The proposed method achieved an AP value of 95.30% and an RMSE of 1.9% at 84 FPS, making it about 1.4 times faster than the other techniques. Additionally, MYOLOv5s correctly detected the highest number of maize tassels and showed at least a 17.64% improvement in AP value compared to Faster R-CNN and RetinaNet, respectively. Furthermore, our technique had the lowest false positive and false negative values. The regression plots show that MYOLOv5s provided slightly higher fidelity counts than other methods.Finally, we investigated the effect of score values on the performance of detection-based models and calculated the optimal values of hyperparameters.

The MYOLOv5s technique outperformed other state-of-the-art models in detecting maize tassels, achieving the highest precision, recall, and average precision (AP) values.The MYOLOv5s method had the lowest root mean square error (RMSE) value in the error counting metric, demonstrating its accuracy in detecting and counting maize tassels.We evaluated the correlation between predicted and ground-truth values of maize tassels using the R2 score, and for the MYOLOv5s method, the R2 score was approximately 99.28%, indicating a strong correlation between predicted and actual values.The MYOLOv5s method performed exceptionally well in detecting tassels, even in highly overlapping areas. It accurately distinguished and detected tassels, regardless of their proximity or overlap with other objects.When compared to the counting-based approach TasselNetv2+, our proposed MYOLOv5s method showed faster inference times. This suggests that the MYOLOv5s method is computationally efficient while maintaining accurate tassel detection capabilities.

In this study, the performance of the drone sprayer and conventional sprayers was evaluated for weed control in wheat fields. This project was conducted in a completely randomized experimental design with three replications. The studied parameters were: effective spraying width, spraying time per hectare and consequently the field capacity and field efficiency of sprayers, amount of herbicide solution per hectare, volume and number median Diameter of herbicide particles, spraying quality coefficient, drift, energy consumption, crushing rate of Wheat, sprayers effectiveness and economic evaluation. The results of analysis of variance showed a significant difference between the experimental treatments at 5% probability level. The results showed that the drone sprayer, boom sprayer and the turboliner sprayer had 11.14, 351.59, 249.14 liters solution per hectare, 16.76, 7.66 and 38.6% rate of drift, and 6.72, 5.92 and 7.66 hectar per hour field capacity, and energy consumption of 418, 2837.8 and 4796.2 kJ respectively. E was 72.6, 5.92 and 7.66 hectares per hour and energy consumption was 418, 2837.8 and 4796.2 Kjoules per hectar. Spray quality coefficient in drone sprayer and turboliner sprayer were 1.78 and 4.24, respectively. In 30 days after spraying, no significant difference was observed between treatments in terms of operation effectiveness. The cost per hectare of using drone sprayer was twice as much as conventional sprayers.

In the present century, the development of information technology (IT) is bringing another revolution to achieve the maximum increase in crop production and efficiency of using agricultural inputs. The greatest role of IT in advanced agriculture (precision, smart and digital) is through the IT-based crop management cycle. So, this paper aims to introduce the components of IT-based crop management cycle and their role in advanced agriculture. IT-based crop management cycle consists of five main components including (1) crop, (2) remote sensing platforms supporting sensors such as satellites, drones and proximal equipment (3) data, (4) decision-making through algorithms such as artificial intelligence and (5) the actuation through variable rate technology. The main purpose of this cycle is to obtain accurate information from every pixels of a farm for smart decision making. This cycle enables the collection of objective data for the implementation of advanced agriculture. In fact, advanced agriculture is based on the principle of monitoring and preparing maps and spatio-temporal information, and this principle arises from the existence of heterogeneity in the field. The role of IT-based crop management cycle components is identifying these heterogeneities (differences in land slope, altitude, soil nutrients, pests and weeds, moisture, salinity (EC), pH, organic matter or even crop yield) for helping to perform precision and smart field management in different parts of the production field

In the present century, the need to provide food security for the growing population of the country, the importance of maintaining human health and the environment, as well as the need to continuously increase the productivity of inputs, has made the use of new technologies in the production of agricultural products more necessary. One of the new technologies is Intelligent agriculture. This paper has tried to present the importance of remote sensing technology as one of the most important parts of intelligent agriculture, namely data collection and recording. Also, the types of platforms and sensors that have been introduced in remote sensing studies and their applications in agriculture, as well as the advantages and limitations of each method are described. In the present century, the need to provide food security for the growing population of the country, the importance of maintaining human health and the environment, as well as the need to continuously increase the productivity of inputs, has made the use of new technologies in the production of agricultural products more necessary. One of the new technologies is Intelligent agriculture. This paper has tried to present the importance of remote sensing technology as one of the most important parts of intelligent agriculture, namely data collection and recording. Also, the types of platforms and sensors that have been introduced in remote sensing studies and their applications in agriculture, as well as the advantages and limitations of each method are described.