KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Author: search.filters.author.Kamsing, PatcharinSubject: search.filters.subject.Deep Learning

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Vision-based attitude estimation for spacecraft docking operation through deep learning algorithm
    (2020-02-01)
    Phisannupawong, Thaweerath
    ;
    Kamsing, Patcharin
    ;
    Tortceka, Peerapong
    ;
    Yooyen, Soemsak
    On-orbital services, especially in docking operation and other space object interaction. The missions need accurate, reliable, and robust detection to be an accurate in joining any interaction concerned. Two spacecrafts with an unknown mathematical model to predict the position and orientation, a computer vision-based attitude estimation system to detect the poses of spacecraft via camera is the key option of the mission. In astronautics control, the position coordinates are normally represented as the cartesian coordinate system and used a quaternions coordinate system for orientation representation because quaternions can represent the orientation of spacecraft better than physical angle and can overcome the problem of singularity. This paper aims to construct a model for both position and orientation estimation with public data. The input images are the dataset of Soyuz in the resolution of 1280x960, which is simulated by Unreal Engine 4. The implementation of this paper use GoogLeNet for a convolutional neural network model with the mathematical model of loss subject to direct regression. The result shows that a position estimation is significantly accurate with having distance error smaller than 1 meter and trand to reduce when setting a proper scaling factor for loss function. The result demonstrates a high error for orientation estimation. However, the experiment expresses that both position and orientation estimation can be improved in case of selecting a suitable scaling factor of loss function.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Deep Convolutional Neural Networks for plane identification on Satellite imagery by exploiting transfer learning with a different optimizer
    (2019-07-01)
    Kamsing, Patcharin
    ;
    Torteeka, Peerapong
    ;
    Yooyen, Soemsak
    Object identification is on an available problem. Automating plane identification on Satellite imagery can be applied for activity and traffic patterns to monitoring airports, and including defense intelligence issues. This paper implements Deep Convolutional Neural Networks(CNN) to classify a plane in the planesnet dataset. Pre-trained model and transfer learning are deployed to overcome a limitation of computation resources by adding new top layer consists of a fully-connected layer and softmax layer to identify the new classes and re-train it. Besides, the experimental designs for testing an implementation of a pretrained model with some kinds of the optimizer to comparing a result. There are four types of optimizer. The first two are well-known optimizer namely Stochastic Gradient Descent optimizer and Adam Optimizer, while others are PowerSign and AddSign optimizer. PowerSign and AddSign optimizer are methods to minimize cost, which discover by using Recurrent neural network(RNN) and Reinforcement Learning. A result demonstrates that a plane identification on Satellite imagery can be achieved by implementing the pre-trained model and obtains an exceptional result with Adam optimizer.