A. Azizi; Y. Abbaspour Gilandeh; T. Mesri Gundoshmian; H. Abrishami Moghaddam
Abstract
IntroductionStereo vision is an approach to 3D information from multiple 2D views of a scene. The 3D information can be extracted from a pair image, as known stereo pair by estimating the relative depth of points in the scene.Soil aggregate size distribution is one of the most important issues in the ...
Read More
IntroductionStereo vision is an approach to 3D information from multiple 2D views of a scene. The 3D information can be extracted from a pair image, as known stereo pair by estimating the relative depth of points in the scene.Soil aggregate size distribution is one of the most important issues in the agriculture sector which highly affects energy consumed for preparing the field before planting. Mean weight diameter of clods is a standard metric for determining clod (big aggregates) size. Conventional methods are based on sieving soil samples to calculate the MWD. However, they are faced with several challenges in larger scales and practical applications. Furthermore, due to inherent limitations of soil environment and also being a tedious work, traditional methods would beuse to estimate the metric higher or lower than actual value.As new methods, researchers are using computer vision techniques as virtual sieve so that the size of clods can be determined via processing digital images which have been taken from soil surface. Although, image-based methods have solved many of previous problems, their accuracy is not so high due to the complexity of soil environment and overlapping colds, and needs to be improved. In order to overcome the mentioned challenges, in the current study stereo vision method was developed so that it is possible to extract the third dimension information as height of clods which helps us to categorize clods into their own class.Materials and MethodsIn this study, the W3-Fujifilm stereo camera equipped with two 10-megapixel CCD sensors for both left and right lenses, and baseline spacing of 7.5 cm was used. The distance between the camera lens and the ground was also set to 60 cm.In order to get three components of soil clods including (x, y, z), point cloud was investigated. For this, local features were extracted using a SIFT feature detector. The SIFT algorithm is robust against scale, rotation and illumination changes, so that these specifications have made it as a strong tool in the field of stereo vision. Then, the extracted features (keypoints) were matched between two stereo pair images by means of Brute Force algorithm and the location of all corresponding points were determined and point cloud was obtained.At the final stage, three features including length, width and height of all six classes of soil clods were entered into a linear classifier entitled discriminant analysis. This classifier as a linear separator classified these six classes based on appropriate functions in a 5 dimensional space.Results and DiscussionResults of classification model showed that the height (thickness) of clods have more distinguishing different soil clods. The reason for this refers to the event of overlapping, because most of clods were touched each other after sieving. Consequently, the length and width of clods had not significant effect in soil aggregates classification.In order to analysis the result of soil aggregate classification, confusion matrix was calculated and the overall classification accuracy was achieved 83.7%. The lowest and highest accuracy were obtained for class 1 (the littlest class) and class 6 (the biggest class), respectively due to their low and high height from the soil surface.ConclusionIn this research, the basic geometrical features including length, width and height were extracted from stereo pair digital images via stereo vision techniques to classify six classes of soil clods. This aim was reached by 3-D reconstruction of image data, so that the height of each image as the third component of (x,y,z) was obtained as well as the length and width. The results of classification indicated that the stereo vision technique had the satisfactory performance in determining the aggregate size distribution which is one of the most important indices for tilled soil quality.
F. Keyhani Nasab; T. Mesri Gundoshmian; Sh. Zargar Ershadi
Abstract
Introduction Considering the low cost of the wind power production and its relatively good compatibility with the environment, wind farms have shown extensive growth in the past few years. Considering the importance of using the wind power and its advantages, the careful planning is needed to identify ...
Read More
Introduction Considering the low cost of the wind power production and its relatively good compatibility with the environment, wind farms have shown extensive growth in the past few years. Considering the importance of using the wind power and its advantages, the careful planning is needed to identify the available generation potentials in a region or a country to facilitate its increased use. By the end of 2009, the capacity of wind turbines installed in the wind farms of Iran was 92 MW, which demonstrates the significant potential for additional wind farms in the country and suggests investments in the wind power industry are likely cost effective. The main purpose of this research is to assess the potential of wind power for the city of Pars Abad in northwestern Iran. Materials and Methods In order to measure wind power density and wind energy potential, wind speed data collected every 3 hours at a height of 30 m above the ground for 11 consecutive years are analyzed; the data are provided by the Iranian Meteorological Organization and are used in the assessment of electricity production potential in the area chosen for the wind turbines installation. To determine the wind energy potential at a site and estimate the energy output from this site, statistical functions like probability functions are used. There are many probability functions but the Weibull distribution function is usually considered the most useful function for wind speed data analysis due to its simplicity and good accuracy. The Weibull probability density function is defined with two parameters of k and c as follows: (1) f (v) = k/(c ) 〖( v/c )〗^(k-1) exp (- 〖( v/c )〗^k ) After calculating the Weibull function parameters, status of a location for wind energy potential can be assessed. A good way to assess the available wind resources is by calculation of the wind power density. This parameter indicates how much energy can be converted to electricity at a site and can be calculated as follows: (2) P/A=1/2 ρc^3 Г ( (k+3)/k) Wind energy density expresses the wind power density for a given time period T.The wind energy density for a definite site and in a given time period (one month or one year) (T) can be calculated as: (3) E/A=1/2 ρc^3 Г ((k+3)/k) T Results and Discussion In this study, wind speed data collected in Parsabad, Iran, over a ten-year period (2005-2015) are analyzed, and the Weibull distribution parameters c and k, average wind speed, and average wind power and wind energy densities are determined. According to Table 1, the minimum and maximum standard deviations of the average monthly indicators during 11 years in November and July are 0.63 and 2.51, respectively, and the minimum and maximum wind speeds of the average monthly indicators during 11 years in November and June are 2.09 ms-1 and 4.87 ms-1, respectively. The average annual Weibull scale parameter (c) is 3.84 while the average annual Weibull shape parameter (k) is 2.61. The average annual wind power density (P/A) during 11 years is 45 Wm-2, while the average annual wind energy density (E/A) during 11 years is 389 kWhm-2/year. Pars Abad in terms of generation potential of wind energy and based on quantitative classification for wind resource is located in weak to average region. Conclusion Pars Abad with an average wind power density of 45 Wm-2 and average wind speed of 3.41 ms-1 is not a good candidate for wind power plants and it is just suitable for off-grid electrical and mechanical applications such as charging batteries and pumping water for agricultural and livestock uses.
T. Mesri Gundoshmian; F. Keyhani Nasab; Gh. Shahgholi; E. Abdollahi
Abstract
Introduction Today, most of the agricultural machines for doing agricultural operations and covering the entire farm, must move in the farm, and travel a certain distance without doing anything useful. Common agricultural machines are controlled by human beings using habits, machinery models, and personal ...
Read More
Introduction Today, most of the agricultural machines for doing agricultural operations and covering the entire farm, must move in the farm, and travel a certain distance without doing anything useful. Common agricultural machines are controlled by human beings using habits, machinery models, and personal experiences without using computer-based tools. This trend leads to repetitive patterns and affect farm efficincy. Therefore, applying optimization techniques in determining the optimum pattern and track for on-farm machinery would be very effective. One of the main problems of conventional movement patterns on farms is the time wasted on moving towards the end of the field, which will have a big impact on field efficiency. The purpose of this study is to reduce the useless distance traveled by agricultural machines using genetic algorithm while moving on the farm and going from one track to the next, and, consequently, increase farm efficiency. Materials and Methods In this study, the rectangle farm that was 80 meters wide and had an arbitrary length was selected for simulation, and different types of turning methods were tested. The calculations and simulation were based on genetic algorithm using the MATLAB 2013 software. In this case, the minimum traveled distance was set as solution evaluation criterion. The solutions were applied and simulated according to these assumptions: Each gene was considered a track number, and the algorithm’s chromosomes were produced by connecting all the tracks to each other,. The width of each track was considered equal to the width of the machine, and based on reproduction parameters such as population size and the number of repetitions, a percentage of the children were produced through point intersection and another percentage were produced through mutation. In determining the distance between the tracks, Ω or T or U were used for two adjacent tracks, U was used for two tracks that had a track between them, and a longer U was used for tracks that had more than one track between them. Based on the number of the initial population, the chromosomes that were supposed to be parents at the beginning were selected. The children produced new population was created and the above steps were repeated. During the last repetition, the best child chromosome was introduced as the answer. In order to calculate the effects of different methods of turning on the non-working distance covered during agricultural operations, the non-working distance traveled during 5 orders of movement, including 4 traditional orders (continuous, spiral, all-around, and blocked) and 1 smart order were compared to each other. In the continuous pattern, because movement continues in the next track at the end of each track, all the turnings are inevitably done in the Ω way, and thus a greater distance is travelled compared to the U way. In the spiral pattern, the distance travelled in turnings between different tracks on the farm is equal. In the all-around pattern, movements are done from the sides and the operation is concluded at the center of the farm; therefore, the long U method of movement is used at the end of all the tracks, and Ω turning is used for the last track at the center of the farm. In the blocked pattern, the farm is devided into two or more blocks, and the all-around movement pattern is used in each block as an independent farm. In the smart movement pattern, the beginning and ending of the agricultural operations are considered in the vicinity of the hypothetical road which, in addition to facilitating access to the road, had a significant impact on reducing the useless distance traveled on the farm. Results and Discussion The final optimum pattern was compared to traditional patterns in the form of charts. The optimum pattern of movement which uses smart genetic algorithm and avoids long turning methods (such as, Ω and T) leads to reduced wasted time and distance traveled by agricultural machines and increased field efficiency and also, decreasing the non-working traveled distance and waste time approximately, 45 % and 47 % respectively. This is due to avoiding turning methods of Ω and T (compared to the U method). Also, the fatigue resulting from these approaches and their wasted time is greater than U method used in the genetic algorithm pattern. Conclusion The optimum pattern of movement which uses smart genetic algorithm was compared to conventional patterns that showed significant saving in non- working distance and waste time in farm. This optimum pattern can be implemented in automatic navigation but there is the possibility of its implementation by operators in common navigation.
Modeling
Gh. Shahgholi; H. Ghafouri Chiyaneh; T. Mesri Gundoshmian
Abstract
Introduction Soil compaction is one of the most destructive effects of machine traffic. Compaction increases soil mechanical strength and reduces its porosity, plant rooting and ultimately the yield. Nowadays, agricultural machinery has the maximum share on soil compaction in modern agriculture. The ...
Read More
Introduction Soil compaction is one of the most destructive effects of machine traffic. Compaction increases soil mechanical strength and reduces its porosity, plant rooting and ultimately the yield. Nowadays, agricultural machinery has the maximum share on soil compaction in modern agriculture. The soil destruction may be as surface deformation or as subsurface compaction. Any way machine traffic destructs soil structure and as result has unfavorable effect on the yield. Hence, soil compaction recognition and its management are very important. In general, soil compaction is the most destructive effect of machine traffic. Modeling of ecological systems by conventional modeling methods due to the multitude effective parameters has always been challenging. Artificial intelligence and soft computing methods due to their simplicity, high precision in simulation of complex and nonlinear processes are highly regarded. The purpose of this research was the modeling of soil compaction system affected by soil moisture content, the tractor forward velocity and soil depth by multilayer perceptron neural network. Materials and Methods In order to carry out the field experiments, a tractor MF285 which was equipped with a three-tilt moldboard plough was used. Experiments were conducted at the Agricultural research field of University of Mohaghegh Ardabili in five levels of moisture content of 11, 14, 16, 19 and 22%, forward velocity of 1, 2, 3, 4 and 5 km.h-1, and soil depths of 20, 25, 30, 35 and 40 cm as a randomized complete block design with three replications. In this study, perceptron neural network with five neurons in the hidden layer with sigmoid transfer function and linear transfer function for the output neuron was designed and trained. Results and Discussion Field experiments showed three main factors were significant on the bulk density (P<0.01). The mutual effect of moisture on depth and mutual binary effect of moisture on velocity and depth on velocity were significant (P<0.01). Mutual triplet effect of moisture on velocity on depth was significant (P<0.05). Maximum bulk density of 1362 kg/m3 was obtained at the highest moisture of 22% and the lowest forward velocity of 1 km/h at the depth of 20 cm. Whilst the minimum value of 1234.5 kg/m3 was related to the moisture, forward velocity and depth of 11%, 5 km/h and depth of 40 cm, respectively. Compaction increased as soil moisture content increased up to 22% which was critical moisture. In contrast, soil compaction decreased as the tractor velocity and soil depth increased. A comparison of neural network output and experimental results indicated a high determination coefficient of R2 = 0.99 between them. Also, the mean square error of the model was 0.174, in addition, mean absolute percentage error of the system (MAPE) was equal to %0.29 which showed high accuracy of neural network to model soil compaction.ConclusionIt was concluded that soil compaction increased as soil moisture content increased up to a critical value. Increasing soil moisture act as lubricant and soil layers compacted together. Hence knowledge of soil moisture can help us to manage soil compaction during agricultural operations. Increasing the tractor forward velocity reduced soil compaction. However, agricultural operations should be conducted at certain speeds to carry out the duty properly and increasing speed more that value decreases the efficiency of work.Neural network of MLP with 5 neurons in hidden layer and sigmoid function in middle layer and one neuron with linear transfer function was found the most accurate and precise in prediction of the soil bulk density. A high determination coefficient of R2 = 0.99 was found between measured and predicted values.
T. Mesri Gundoshmian; P. Alighaleh; S. Alighale; B. Najafi
Abstract
Introduction Growth of population, deficiency of resources, environmental hazards, fast spatial science progress and relevant subjects have resulted in significant effects of enhanced accuracy and modern technologies in agricultural technology and management methods. One of the modern technologies’ ...
Read More
Introduction Growth of population, deficiency of resources, environmental hazards, fast spatial science progress and relevant subjects have resulted in significant effects of enhanced accuracy and modern technologies in agricultural technology and management methods. One of the modern technologies’ utilities in production and nondestructive tests is determination of product characteristics (such as product height), using electronic sensors at different stages of plant growth. In recent years, electric sensors improved widely in farm science. Regarding to wide performance of sensors, from simple sensors such as thermo, light and moisture sensors, to complex ones such as GPS and lidar, also the ability of electronic sensors to exact identification and measurement of special farm properties, makes these sensors to an important part of precision agriculture. The subject of this study is to identify and measure the height of the product using ultrasonic technology to automate control of breeding and harvesting operations. Suitable price and noise and dust resistance of ultrasonic sensor, make it an attractive subject in biosystem industries and farm operations. Materials and Methods Plant height measurement Ultrasonic sensor includes an ultrasonic transmitter and receiver with more than 20 kHz frequency. As other waves, ultrasonic waves diffuse constantly from a source by mechanical distracting in a gas, liquid or solid environment. The distance between sensor and object is a function of the wave passing time from generation point to receive point. Plant height calculated by estimating this distance and minus it from sensor height. The sensor used in this research had a diffuse angle of 40 degrees to center axis of source. The sensor ability to height measurement depends on leaves angle, leaves surface, plant aggregation in area and plant height. Leaves angle is the most important factor in recognization ability of ultrasonic sensor. Electronic system design The height measurement electronic system includes: 40 kHz Ultrasonic transmitter with diameter of 10 mm, 67 db ultrasonic receiver, Signal amplifier circuit (op-amp), AVR Microcontroller, (atmega 128) and a 64×128 pi LCD. Electronic part of system produces 40 kHz pulse initially and locates on one of the outlet bases of microcontroller. Then, this pulse is amplified and sent to ultrasonic sensor transmitter for maximum performance of the transmitter. The received pulse has low power so it shoud be amplified by an amplifier to be recognizable by the microcontroller. The received signal transmitted to digital signal by a high-speed 128 AVR atmega microcontroller. The sensor calibrated in the first phase using artificial barriers, the data analyzed by linear regression and paired mean comparison test in SPSS and EXCEL software. Results and Discussion Corn height measured by designed system in a test by 100 plots and 10 blocks. Thus, the blocks had a dimension of 1m length and 10cm width. System output recorded in first block and the block length passed by system with 10cm distances. Actual measurement accuracy comprised as pixels to data from manual measurement. The results didn’t show any significant difference between means. The regression coefficient of model was calculated 99%. The operating phase continued in a lab to measure maize height. The results showed high linear correlation between ultrasonic output voltage and manual measurement. This linear correlation led to present a linear regression model with the regression coefficient of 95%. Correlated mean comparison used for all of data too, i.e. the data obtained by the two measurement methods were compared by t-paired test. So it’s defensible that with 99% confidence, sensor can estimate the real value of height with high accuracy. Conclusion Utilization of measurement technologies and accuracy enhancement in agricultural production systems are unavoidable. In this research, corn height was measured accurately by ultrasonic technology. According to the results, identifying the presence or absence of plant, precision control of the operations (e.g. spraying) and measuring the height of the plants (to set the cutting height at combine harvester). Obviously, the produced device can identify plant height with precision, and can use in different phases of precision agriculture such as seeding row identification, machinery path determination to minimize plant’s loss, poison optimization and harvesting.