The capture of a target spacecraft by a chaser is an on-orbit docking operation that requires an accurate, reliable, and robust object recognition algorithm. Vision-based guided spacecraft relative motion during close-proximity maneuvers has been consecutively applied using dynamic modeling as a spacecraft on-orbit service system. This research constructs a vision-based pose estimation model that performs image processing via a deep convolutional neural network. The pose estimation model was constructed by repurposing a modified pretrained GoogLeNet model with the available Unreal Engine 4 rendered dataset of the Soyuz spacecraft. In the implementation, the convolutional neural network learns from the data samples to create correlations between the images and the spacecraft’s six degrees-of-freedom parameters. The experiment has compared an exponential-based loss function and a weighted Euclidean-based loss function. Using the weighted Euclidean-based loss function, the implemented pose estimation model achieved moderately high performance with a position accuracy of 92.53 percent and an error of 1.2 m. The in-attitude prediction accuracy can reach 87.93 percent, and the errors in the three Euler angles do not exceed 7.6 degrees. This research can contribute to spacecraft detection and tracking problems. Although the finished vision-based model is specific to the environment of synthetic dataset, the model could be trained further to address actual docking operations in the future.
In one, docking is defined as “when one incoming spacecraft rendezvous with another spacecraft and flies a controlled collision trajectory in such a manner to align and mesh the interface mechanisms”, and defined docking as an on-orbital service to connect two free-flying man-made space objects. The service should be supported by an accurate, reliable, and robust positioning and orientation (pose) estimation system. Therefore, pose estimation is an essential process in an on-orbit spacecraft docking operation. The position estimation can be obtained by the most well-known cooperative measurement, a Global Positioning System (GPS), while the spacecraft attitude can be measured by an installed Inertial Measurement Unit (IMU). However, these methods are not applicable to non-cooperative targets. Many studies and missions have been performed by focusing on mutually cooperative satellites. However, the demand for non-cooperative satellites may increase in the future. Therefore, determining the attitude of non-cooperative spacecrafts is a challenging technological research problem that can improve spacecraft docking operations. One traditional method, which is based on spacecraft control principles, is to estimate the position and attitude of a spacecraft using the equations of motion, which are a function of time. However, the prediction using a spacecraft equation of motion needs support from the sensor fusion to achieve the highest accuracy of the state estimation algorithm. For non-cooperative spacecraft, a vision-based pose estimator is currently developing for space application with a faster and more powerful computational resource.
คณะเทคโนโลยีการเกษตร
The objective of this experiment was to determine the effect of nitrogen and potassium concentration combination with photoperiod on the growth of Viola in a plant factory to increase the quality of the products, reduce the production time and increase the production cycle throughout the year. The experimental plan was 3x3 Factorial in CRD with nine treatments and three replications (six plants per replication). The factor of this study was two factors; the first factor was three different concentrations of nitrogen and potassium in ratios of 1:1, 1:2 and 2:1. The second factor was the application of different photoperiods. There were 1) 24-hours photoperiod, 2) 8-hours light/16-hours dark photoperiod (Induced flowering state: 13-hours light/11-hours dark photoperiod) and 3) 5-hours light/3-hours dark photoperiod. Controlled temperature at 25 °C, the EC=1.5-2.0 mS/cm and the pH=5.8-6.5 in all treatment. The result showed that the concentration of N: K in the ratio of 1:1 combined with 24-hour photoperiod was the most vegetative growth and also maximizes reproductive growth. The overall great sensory evaluation was an acceptable level and suitable for cooking or decorating dishes. Therefore, the concentration of N: K in the ratio of 1:1 combined with 24-hour photoperiod is the best treatment to increase the quality of the product, reduce the production time of viola flowers in each cycle from 90-100 days down to 43-45 days which is good for farmers.
คณะศิลปศาสตร์
"Niyom Thai" represents health-centric footwear adorned with traditional Thai patterns, embodying an innovative approach to sustainable development tailored to the current needs of local communities. These shoes utilize natural materials to mitigate fatigue and integrate safety technologies, including location tracking via a mobile application and heart rate monitoring. This addresses the aspects of convenience and well-being in both daily life and travel
คณะวิทยาศาสตร์
Otitis Media is an infection of the middle ear that can occur in individuals of all ages. Diagnosis typically involves analyzing images taken with an otoscope by specialized physicians, which relies heavily on medical experience to expedite the process. This research introduces computer vision technology to assist in the preliminary diagnosis, aiding expert decision-making. By utilizing deep learning techniques and convolutional neural networks, specifically the YOLOv8 and Inception v3 architectures, the study aims to classify the disease and its five characteristics used by physicians: color, transparency, fluid, retraction, and perforation. Additionally, image segmentation and classification methods were employed to analyze and predict the types of Otitis Media, which are categorized into four types: Otitis Media with Effusion, Acute Otitis Media with Effusion, Perforation, and Normal. Experimental results indicate that the classification model performs moderately well in directly classifying Otitis Media, with an accuracy of 65.7%, a recall of 65.7%, and a precision of 67.6%. Moreover, the model provides the best results for classifying the perforation characteristic, with an accuracy of 91.8%, a recall of 91.8%, and a precision of 92.1%. In contrast, the classification model that incorporates image segmentation techniques achieved the best overall performance, with an mAP50-95 of 79.63%, a recall of 100%, and a precision of 99.8%. However, this model has not yet been tested for classifying the different types of Otitis Media.