Suksangpanya, Nobphadon
Loading...
Preferred name
Suksangpanya, Nobphadon
Alternative Name
Suksangpanya, N.
Main Affiliation
Email
nobphadon.su@kmitl.ac.th
6 results
Now showing 1 - 6 of 6
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Automatic classification of pararubber trees in Thailand from LANDSAT-8 images using neural networks method(2019-07-01); ; Nakya, SuvalakClassifying features from satellite images has been a time-consuming manual process which requires lots of manpower. This work exploits deep convolutional decoder encoder neural network, to develop an algorithm that can automatically classify the extents of the Pararubber tree growing areas from the LANDSAT-8 images. The classification resulted from this approach was verified. In conclusion, the classification accuracy achieved is at 86.90% with Cohen's kappa at 73.80% which is considered satisfactory. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Automatic para-rubber trees classification in Thailand from LANDSAT-8 imagery using DCED neural network(2021-06-02); Image classification has been one of the main processes performed on satellite imagery where there have been many studies attempt to developing an automatic approach since manual classification is known to be a time-consuming process. Automatic classifying specific types of vegetation in satellite imagery has been a challenging field of study. In this work, a neural network method, specifically deep convolutional encoder-decoder or known as DCED, is applied to the automatic classifying coverage area of Para-rubber trees in Thailand from LANDSAT-8 satellite imagery. The main procedure in this work comprises ground truth preparation, suitable model development with training and validation, and, finally, classification. As a result, the model developed in this work gives average accuracy of 86.9% in training datasets and 70.9% in validation datasets. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Feasibility of exploitation of 3D city model created from LiDAR data and aerial images in applications focusing on Chaophraya river basin and the area of the Eastern economic Corridor (EEC) of Thailand(2020-01-01); 3D city model and their variety applications has been of interests of many users especially the government entities. This is because the applications of 3D city model are tremendous. There are different approaches of creating 3D city model, generally, most of raw datasets used are the point cloud data obtained from the LIDAR (Light Detection and Ranging) technology and the aerial images. In Thailand, it has been of an interest if currently available LIDAR data and aerial images; which were collected over the area of Chaophraya river basin in Thailand, are able to be used for creating 3D city model. These collected datasets had not yet been proved their eligibility to do so. The goals/objectives of this study/project are (1) to study the feasibility of using the available LIDAR datasets and aerial images over the area of the Chaophraya river basin (data of MOST and JICA) to create 3D city model and to determine the possible applications that could make use of the to-be-created products, and (2) to suggest appropriate applications that make use of 3D city model data to be developed for the case of the Eastern Economic Corridor (EEC) of Thailand which covers the Chonburi, Rayong, and Chachoengsao. In this study, vigorous studying and testing were conducted to achieve the objectives of this project. Sets of 3D city model were created over different characteristics of area such as 3D city model in dense urban areas and 3D city model in low dense urban areas. These 3D city models were to be used as examples for estimating tasks in order to answer questions listed in the objectives of this study. Additionally, the aforementioned 3D city models were created by different approaches in order to investigate and study on the pros and cons of each approach considering on different quality of the datasets used. Furthermore, the recommendations are made on the aspects of expected properties and qualities of raw LIDAR data and aerial images to be used for creating 3D city model in the area of the EEC of Thailand as well as the potential usages/applications those 3D city model. Finally, this study also suggests the approach of exploiting a platform that can facilitate variety usages of 3D city model in many applications by developing a mock-up software to demonstrate such idea. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Crack twisting and toughening strategies in Bouligand architectures(2018-10-01); - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Semi-Automatic Classification of Rotating Crops in Northern Thailand by Using Temporal LANDSAT Images(2022-01-01); This work focuses on rotating crops in the forest conservation areas in the northern region of Thailand which always cause false detection for forest encroachment and deforestation. Therefore, this work establishes a database of rotating crop areas in the northern region of Thailand and additionally develops a semi-automatic classification approach to help facilitate the classification process. LANDSAT images ranging from 1987 to 2018 are used as the input data for classifying the rotating crop areas. The semi-automatic classification approach is comprised of the automatic supervised classification and the manual classification by visual interpretation, respectively. The automatic and manual classification procedures are explained, and the results are verified by using ground truth locations distributed over the study region which gives 81.72% accuracy. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Simulation of the scanned point cloud pattern aiding lidar data acquisition planning process for mobile mapping system(2020-01-01); Point cloud data obtained from LIDAR technology is widely used in many sciences and engineering disciplines. Common use-cases of point cloud data are surface models construction or 3D modeling of the interest objects which can then be exploited in a variety of applications that cannot be exhaustively listed, providing solutions to answer specific questions or problems. Many factors in data collection and processing steps dictate the quality of the point cloud which has a direct impact on the quality of the to-be-created object models. Point density is one of the most important properties of the point cloud dataset that influences how the feature extraction process can be efficiently performed to extract points for object model reconstruction. Therefore, data acquisition planning is required to ensure the sufficiency of the point density of the collected dataset. In this work, a prototype of the point cloud simulation platform is developed for aiding data acquisition planning tasks by simulating the expected scanned results from the terrestrial mobile mapping system (MMS). With this platform, MMS devices in the off-the-shelf market can be selected by users to perform the simulation, and the platform will automatically retrieve their associated specifications of the selected MMS. On the other hand, MMS specifications customized by users are also allowed to be adopted. Additionally, the operation parameters such as driving speed of data collection process, the height of the vehicle on which the MMS is mounted, and the nominal distances between the scanner unit and the selected target can be specified. Based on those input parameters the platform simulates the scanned pattern on the scanned scene which is set to be plane in both horizontal and vertical directions which represent ground surface and wall, respectively. With the simulated scanned pattern, the user can select to overlay signalized/reflective targets on the scanned scenes to visual the scan pattern. The platform offers selectable standard designs of reflective targets, such as a cross sign, circle, and chess, the size of them can be altered based on user requirements. With this point cloud simulation platform, users can foresee an expected scanned pattern on their objects and subsequently lead to the capability of estimating point cloud density. Furthermore, users can perform tuning of parameters related to operation scenarios and re-simulate the scan results which can greatly benefit the data acquisition planning process since it can be done in house with less time consuming and in a cost-efficient manner.