Precision Farming
M. Saadikhani; M. Maharlooei; M. A. Rostami; M. Edalat
Abstract
IntroductionRemote sensing is defined as data acquisition about an object or a phenomenon related to a geographic location without physical. The use of remote sensing data is expanding rapidly. Researchers have always been interested in accurately classifying land coverage phenomena using multispectral ...
Read More
IntroductionRemote sensing is defined as data acquisition about an object or a phenomenon related to a geographic location without physical. The use of remote sensing data is expanding rapidly. Researchers have always been interested in accurately classifying land coverage phenomena using multispectral images. One of the factors that reduces the accuracy of the classification map is the existence of uneven surfaces and high-altitude areas. The presence of high-altitude points makes it difficult for the sensors to obtain accurate reflection information from the surface of the phenomena. Radar imagery used with the digital elevation model (DEM) is effective for identifying and determining altitude phenomena. Image fusion is a technique that uses two sensors with completely different specifications and takes advantage of both of the sensors' capabilities. In this study, the feasibility of employing the fusion technique to improve the overall accuracy of classifying land coverage phenomena using time series NDVI images of Sentinel 2 satellite imagery and PALSAR radar imagery of ALOS satellite was investigated. Additionally, the results of predicted and measured areas of fields under cultivation of wheat, barley, and canola were studied.Materials and MethodsThirteen Sentinel-2 multispectral satellite images with 10-meter spatial resolution from the Bajgah region in Fars province, Iran from Nov 2018 to June 2019 were downloaded at the Level-1C processing level to classify the cultivated lands and other phenomena. Ground truth data were collected through several field visits using handheld GPS to pinpoint different phenomena in the region of study. The seven classes of distinguished land coverage and phenomena include (1) Wheat, (2) Barley, (3) Canola, (4) Tree, (5) Residential regions, (6) Soil, and (7) others. After the preprocessing operations such as radiometric and atmospheric corrections using predefined built-in algorithms recommended by other researchers in ENVI 5.3, and cropping the region of interest (ROI) from the original image, the Normalized Difference Vegetation Index (NDVI) was calculated for each image. The DEM was obtained from the PALSAR sensor radar image with the 12.5-meter spatial resolution of the ALOS satellite. After preprocessing and cropping the ROI, a binary mask of radar images was created using threshold values of altitudes between 1764 and 1799 meters above the sea level in ENVI 5.3. The NDVI time series was then composed of all 13 images and integrated with radar images using the pixel-level integration method. The purpose of this process was to remove the high-altitude points in the study area that would reduce the accuracy of the classification map. The image fusion process was also performed using ENVI 5.3. The support Vector Machine (SVM) classification method was employed to train the classifier for both fused and unfused images as suggested by other researchers.To evaluate the effectiveness of image fusion, Commission and Omission errors, and the Overall accuracy were calculated using a Confusion matrix. To study the accuracy of the estimated area under cultivation of main crops in the region versus the actual measured values of the area, regression equation and percentage of difference were calculated.Results and DiscussionVisual inspection of classified output maps shows the difference between the fused and unfused images in classifying similar classes such as buildings and structures versus regions covered with bare soil and lands under cultivation versus natural vegetation in high altitude points. Statistical metrics verified these visual evaluations. The SVM algorithm in fusion mode resulted in 98.06% accuracy and 0.97 kappa coefficient, 7.5% higher accuracy than the unfused images.As stated earlier, the similarities between the soil class (stones and rocks in the mountains) and manmade buildings and infrastructures increase omission error and misclassification in unfused image classification. The same misclassification occurred for the visually similar croplands and shallow vegetation at high altitude points. These results were consistence with previous literature that reported the same misclassification in analogous classes. The predicted area under cultivation of wheat and barley were overestimated by 3 and 1.5 percent, respectively. However, for canola, the area was underestimated by 3.5 percent.ConclusionThe main focus of this study was employing the image fusion technique and improving the classification accuracy of satellite imagery. Integration of PALSAR sensor data from ALOS radar satellite with multi-spectral imagery of Sentinel 2 satellite enhanced the classification accuracy of output maps by eliminating the high-altitude points and biases due to rocks and natural vegetation at hills and mountains. Statistical metrics such as the overall accuracy, Kappa coefficient, and commission and omission errors confirmed the visual findings of the fused vs. unfused classification maps.
R. Karmulla Chaab; S. H. Karparvarfard; M. Edalat; H. Rahmanian- Koushkaki
Abstract
Introduction One of the problems which considered in recent years for grain harvesting is loss of wheat during production until consumption and tenders the offers for prevention of its especially in harvesting times by combine harvesting machine. Grain harvesting combines are good examples of an operation ...
Read More
Introduction One of the problems which considered in recent years for grain harvesting is loss of wheat during production until consumption and tenders the offers for prevention of its especially in harvesting times by combine harvesting machine. Grain harvesting combines are good examples of an operation where a compromise must be made. One would expect increased costs because of natural loss before harvesting, because of cutter bar loss, because of threshing loss, because of greater losses over the sieve and because of the reduced forward speed necessary to permit the through put material to feed passed the cylinder. The ability to recognize and evaluate compromise solutions and be able to predict the loosed grain is a valuable trait of the harvesting machine manager. By understanding the detailed operation of machines, be able to check their performance, and then arrive at adjustments or operating producers which produce the greatest economic return. Voicu et al. (2007) predicted the grain loss in cleaning part of the combine harvester by using the laboratory simulator based on dimensional analysis method. The obtained model was capable to predict the grain loss perfectly. Soleimani and Kasraei (2012) designed and developed a header simulator to optimize the combine header in rapeseed harvesting. Parameters of interest were: forward speed, cutter bar speed and reel index. The results showed that all the factors were significant in 5% probability. Also in the case of forward speed was 2 km h-1, cutter bar speed was 1400 rpm and reel index was 1.5, the grain loss had minimum quantity. The main purpose of this research was to develop an equation for predicting grain loss in combine header simulator. Modeling of the header grain loss was conducted using dimensional analysis approach. Effective factors on grain loss in combine header unit were: forward speed, reel speed and cutter bar height. Materials and Methods For studying the effective parameters on head loss in grain combine harvester, a header simulator with the following components was built in Biosystems Engineering Department of Shiraz University. Reel unit The reel size was 120 cm length and 100 cm diameter. This reel was removed from an old combine header and installed on a fixed bed. For changing the rotational speed of the reel, an electrical inverter (N50-007SF, Korea) was used. Cutter bar unit The cutter bar length was 120 cm. Knifes were installed on this section. Reciprocating motion was transmitted to the cutter bar through a slider crank attached to a variable speed electric motor (1.5kw, 1400 rpm, Poland). The motor was fixed on the bed. Feeder unit This section was consisted of a rail and a virtual ground. This ground was a tray that the wheat stems were staying on it manually. The rail was the path of virtual ground. Treatments consisted of three levels of rotational speed of reel (21, 25 and 30 rpm), three levels of forward speed of virtual ground (2, 3 and 4 km h-1), three levels of cutter bar height (15, 25 and 35 cm) and three replications. In other words, 81 tests were done. The basis of choosing levels of treatments was combine harvester manuals and driver’s experiences. The dependent variable (H.L) was calculated as below: (1) Where L.G is the mass of loss grains and H.G is the mass of harvested grains. Results and Discussion Generally results of ANOVA test showed that the cutter bar height, rotational speed of reel and forward speed had significant effect on head loss. Also interaction of rotational speed and forward speed, cutter bar height and forward speed had significant effect on head loss. These findings were based on Soleimani and Kasraei (2012) research. Therefore, the cutter bar height, rotational speed of reel and forward speed were three independent parameters on head loss as a dependent parameter. By results of laboratory data, the equation for predicting grain loss by header simulator was obtained. Conclusion The statistical results of F- test in 5% probability showed that there were no significant difference between measured and predicted amounts for laboratory data.
