Effect of boom height and operating pressure on spray uniformity and distribution under test bench experiment

카비르사자둘 ( Sazzadul Kabir ),구란다즈아스라푸자만 ( Ashrafuzzaman Gulandaz ),레자나심 ( Nasim Reza ) 한국농업기계학회 2022 한국농업기계학회 학술발표논문집 Vol.27 No.2

The overuse of pesticides has caused increased production costs and environmental pollution. A major focus of precision variable rate technologies has been improving spraying effectiveness. Sprayer performance and quality are significantly impacted by technical performance of the nozzle. The objective of this work was to analyze the impact of boom height and operating pressure on spray distribution and uniformity. The test bench consisted of four nozzles (NN D-35) and a single-cylinder motor with a four-stroke capacity of 0.72 kW. This sprayer was self-propelled and operated with applied speeds of 2 km/h on testing grounds. Experiments were conducted in the lab with conventional spray nozzles and water as the test liquid. Tested liquid outflow pressure ranged from 280 to 520 kPa. Depending on the spraying target surface, 35, 45, and 55 cm of working spray boom height were adjusted. The nozzle spacing was 30 cm, and the spray angles of the nozzles were 110o. Resultant sprayer nozzle width with boom heights of 35, 45, and 55 cm caused overlaps of 22.38%, 23.43%, and 24.15%. The average droplet density levels of 155.38, 159.20, and 168.31 (spots/cm2) were achieved at boom heights 35, 45, and 55 cm with a speed of 2 km/h, resulting in the spray coverage levels of 23.21%, 26.38%, and 28.35%, respectively. This study may assist in designing future sprayers and spray booms. Additionally these spraying devices would also be cost-effective and environmentally friendly to utilize.

Volumetric yield prediction of Chinese cabbage using CCD camera

구란다즈아스라푸자만 ( Ashrafuzzaman Gulandaz ),카비르사자둘 ( Sazzadul Kabir ),래자나심 ( Nasim Reza ),알리모하마드 ( Mohammad Ali ),정선옥 ( Sun-ok Chung ) 한국농업기계학회 2022 한국농업기계학회 학술발표논문집 Vol.27 No.2

Yield monitoring helps farmers make the proper use of their resources and estimate their crop yield precisely. The objective of the study was to measure the volume of Chinese cabbage using CCD (Charged-coupled device) camera. This system captures RGB images of 30 cabbage samples with the help of two 9-W fluorescent LED light sources, a CCD camera, and an HP core i7 laptop. The camera and LED lights were mounted 1.08 m above the harvester conveyor. The speeds of the conveyor were 0.55 m/s, 0.70 m/s, and 0.85 m/s, respectively, for taking RGB images using the CCD camera, which was triggered by two ultrasonic sensors at a frequency of 5 Hz. Archimedes’ law was used to measure the actual volume of the 30 cabbages in a traditional way. A combination of an RGB image processing technique and a point cloud approach was developed. The images were processed by background subtraction and edge detection algorithms using a Python-based programming language. The volume of cabbage with an ellipsoidal shape was estimated using the box method. Height of each cabbage surface point was found by subtracting the value of each cabbage sample point from the value of the background point. These traditional and box estimation methods provided volumes in the range of 0.003m3 to 0.007m3, respectively. The linear regression approach and t-test analyses (equal variances for means α=0.05) were used to compare the estimated and measured volumes of cabbage, and each method was not substantially different. The results showed that the R2 values were 0.82, 0.74, 0.67 and the root mean square error (RMSE) values were 0.00035 m3, 0.00028 m3 and 0.00025 m3, respectively. In real conditions, the estimated volume can be used to calculate the cabbage yield during harvesting.

Recognition and detection of pig posture based on instance segmentation and computer vision in pig farm

레자나심 ( Nasim Reza ),카비르사자둘 ( Sazzadul Kabir ),하케아스라쿨 ( Asrakul Haque ),정선옥 ( Sun-ok Chung ) 한국농업기계학회 2022 한국농업기계학회 학술발표논문집 Vol.27 No.1

Pig posture changes throughout the growing period are most often indicators to illness. Monitoring pigs postural movements enables us to identify morphological changes in pigs early and to detect potential risk factors for pig health. Large-scale pig farming requires extensive manual monitoring by pig farmers, which is time-consuming and laborious. Computer vision-based monitoring of posture activities over time may help to limit the spread of disease infections. The objective of this study was to recognize and detect pig posture using an masked based instance segmentation in the pig farm. Two automatic video acquisition systems were installed from top and side view, respectively. RGB images were extracted from the RGB video files and used for annotation work. Manual annotation of 200 images were prepared as training dataset, including the three postures: standing, lying, and eating from bin. An instance segmentation framework was employed to recognize and detect pig posture. A region proposal network is used in the first stage of the masked R-CNN based instance segmentation procedure. It obtains features from candidate boxes using RoIPool and conducts classification and bounding-box regression in the second step. Proposed method was evaluated using test image dataset and the experimental results showed the proposed framework obtained a F1 score of 0.911. Our work investigated a new way for recognizing and detecting pig posture in pig farm, which enables useful research into vision-based, real-time automated pig monitoring and diseases assessment.

Measurement of pepper plant height and canopy area using 3D LiDAR point cloud

알리모하마드 ( Mohammod Ali ),카림레자울 ( Rejaul Karim ),카비르사자둘 ( Sazzadul Kabir ),구란다즈아스라푸자만 ( Ashrafuzzaman Gulandaz ),레자나심 ( Nasim Reza ),선저스틴 ( Justsung ),정선옥 ( Sun-ok Chung ) 한국농업기계학회 2022 한국농업기계학회 학술발표논문집 Vol.27 No.2

Plant height and canopy area are crucial plant factors for growth and yield monitoring. A significant number of plants at different heights and canopies are required to evaluate the plant phenotyping characteristics, which is labor-intensive and time-consuming. Therefore, the aim of this study was to use 3D LiDAR point clouds to assess the height and canopy area of pepper plants. A LiDAR (VLP-16) was installed in the experimental field to collect the 3D point clouds of pepper plants. The collected data was preprocessed with 3D point cloud data processing software. The automatic segmentation methods were tested on 13 pepper plants to calculate the height and canopy area. The 3D LiDAR point clouds used in the measuring method were compared to the manually gathered ground truth to determine the accuracy of the results. The average plant height and canopy area were found to be 66±4.5 m and 0.48±0.11 m2, respectively, by manual measurement, whereas the 3D point cloud data processing algorithm showed less accuracy. The R2 values were found to be more than 0.89 for the individual phenotypic traits. The results showed that the proposed system could automatically segment and measure plant height and canopy area. The findings of this study would contribute to further research for upland crop growth and yield monitoring.

Potential of impact-based mass estimation of individual radish tubers for real-time yield monitoring

키라가샤피크 ( Shafik Kiraga ),구란다즈아스라푸자만 ( Ashraffuzaman Gulandaz ),카비르사자둘 ( Kabir Sazzadul ),레자나심 ( Nasim Reza ),정선옥 ( Sun-ok Chung ) 한국농업기계학회 2022 한국농업기계학회 학술발표논문집 Vol.27 No.1

Yield monitoring provides information on the spatial variability of yield in the field and it is one of the basic components of precision agriculture. The objective of this study was to investigate the effects of different harvesting conditions on radish mass measurements using a double load cell impact plate. The harvesting conditions included the falling height, conveyor speed, and impact plate angle, which were simulated using an impact plate attached to a laboratory test bench. The relative error (RE), standard error (SE), and the coefficient of determination (R2) were the statistical indicators used to describe the accuracy of the estimates. Analysis of variance (ANOVA) without interaction of factors and the Duncan multiple range tests were performed using the above indicators except R2. The falling height and conveyor speed had no significant effect on radish mass measurement. In contrast, the impact plate angle significantly affected the impact plate precision. Minimum and maximum standard error of 1.68 and 4.39 were obtained at -100, 40 cm, 0.05 m/s and -500, 30 cm, 0.25 m/s, respectively. The results showed the possibility of using impact-based sensors for individual measurement of radish for real-time yield monitoring.