KMITL

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

Browse

Search Results

Now showing 1 - 10 of 12

Some of the metrics are blocked by your
consent settings
Transformer-based decoder designs for semantic segmentation on remotely sensed images
(2021-12-01)
Panboonyuen, Teerapong
;
Jitkajornwanich, Kulsawasd
;
Lawawirojwong, Siam
;
Srestasathiern, Panu
;
Vateekul, Peerapon
Transformers have demonstrated remarkable accomplishments in several natural language processing (NLP) tasks as well as image processing tasks. Herein, we present a deep-learning (DL) model that is capable of improving the semantic segmentation network in two ways. First, utilizing the pre-training Swin Transformer (SwinTF) under Vision Transformer (ViT) as a backbone, the model weights downstream tasks by joining task layers upon the pretrained encoder. Secondly, decoder designs are applied to our DL network with three decoder designs, U-Net, pyramid scene parsing (PSP) network, and feature pyramid network (FPN), to perform pixel-level segmentation. The results are compared with other image labeling state of the art (SOTA) methods, such as global convolutional network (GCN) and ViT. Extensive experiments show that our Swin Transformer (SwinTF) with decoder designs reached a new state of the art on the Thailand Isan Landsat-8 corpus (89.8% F1 score), Thailand North Landsat-8 corpus (63.12% F1 score), and competitive results on ISPRS Vaihingen. Moreover, both our best-proposed methods (SwinTF-PSP and SwinTF-FPN) even outperformed SwinTF with supervised pre-training ViT on the ImageNet-1K in the Thailand, Landsat-8, and ISPRS Vaihingen corpora.
Some of the metrics are blocked by your
consent settings
Semantic labeling in remote sensing corpora using feature fusion-based enhanced global convolutional network with high-resolution representations and depthwise atrous convolution
(2020-04-01)
Panboonyuen, Teerapong
;
Jitkajornwanich, Kulsawasd
;
Lawawirojwong, Siam
;
Srestasathiern, Panu
;
Vateekul, Peerapon
One of the fundamental tasks in remote sensing is the semantic segmentation on the aerial and satellite images. It plays a vital role in applications, such as agriculture planning, map updates, route optimization, and navigation. The state-of-the-art model is the Enhanced Global Convolutional Network (GCN152-TL-A) from our previous work. It composes two main components: (i) the backbone network to extract features and (ii) the segmentation network to annotate labels. However, the accuracy can be further improved, since the deep learning network is not designed for recovering low-level features (e.g., river, low vegetation). In this paper, we aim to improve the semantic segmentation network in three aspects, designed explicitly for the remotely sensed domain. First, we propose to employ a modern backbone network called "High-Resolution Representation (HR)" to extract features with higher quality. It repeatedly fuses the representations generated by the high-to-low subnetworks with the restoration of the low-resolution representations to the same depth and level. Second, "Feature Fusion (FF)" is added to our network to capture low-level features (e.g., lines, dots, or gradient orientation). It fuses between the features from the backbone and the segmentation models, which helps to prevent the loss of these low-level features. Finally, "Depthwise Atrous Convolution (DA)" is introduced to refine the extracted features by using four multi-resolution layers in collaboration with a dilated convolution strategy. The experiment was conducted on three data sets: two private corpora from Landsat-8 satellite and one public benchmark from the "ISPRS Vaihingen" challenge. There are two baseline models: the Deep Encoder-Decoder Network (DCED) and our previous model. The results show that the proposed model significantly outperforms all baselines. It is the winner in all data sets and exceeds more than 90% of F1: 0.9114, 0.9362, and 0.9111 in two Landsat-8 and ISPRS Vaihingen data sets, respectively. Furthermore, it achieves an accuracy beyond 90% on almost all classes.
Some of the metrics are blocked by your
consent settings
Combining attentional cnn and gru networks for ocean current prediction based on hf radar observations
(2019-10-23)
Thongniran, Nathachai
;
Jitkajornwanich, Kulsawasd
;
Lawawirojwong, Siam
;
Srestasathiern, Panu
;
Vateekul, Peerapon
Lately, CNN-GRU demonstrates the ability of deep learning techniques on ocean surface current prediction. Improvement of the current prediction model creates positive impact on variety of marine activities, such as search-and-rescue, disaster monitoring and power forecasting. Deep learning techniques was successfully deployed to improve model performance in many areas due to their ability to handle enormous amounts of information in a variety of inputs and their huge growth in recent years. Latest ocean current prediction employed a combination of two mature techniques, which are Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU), to capture spatial and temporal characteristics of its nature. However, there is still room for improvement due to many modern techniques that still have not been employed, and domain knowledge in oceanic, such as lunar illumination, is not taken into account to improve prediction performance. This paper introduces the ocean surface prediction model that employs soft attention mechanism, transfer learning, and incorporation of domain knowledge inputs which are month number, lunar effect, and hour number. An experimental dataset from 2014 to 2016, provided by GISTDA, is collected by using high frequency (HF) radar stations located along the coastal Gulf of Thailand. The experiment compares an existing CNN-GRU and our proposed model. The result shows an improvement of the prediction model in terms of RMSE by 2.57%, and 3.44% on U and V components.
Some of the metrics are blocked by your
consent settings
Spatio-Temporal deep learning for ocean current prediction based on hf radar data
(2019-07-01)
Thongniran, Nathachai
;
Vateekul, Peerapon
;
Jitkajornwanich, Kulsawasd
;
Lawawirojwong, Siam
;
Srestasathiern, Panu
Ocean surface current prediction is necessary to carry a variety of marine activities, such as disaster monitoring, search and rescue operations, etc. There are three traditional forecasting approaches: (i) numerical based approach, (ii) time series based approach and (iii) machine learning based approach. Unfortunately, their prediction accuracy was limited since they did not cooperate with spatial and temporal effects together. In this paper, we present a novel current prediction model, which is a combination between Convolutional Neural Network (CNN) to extract spatial characteristic and Gated Recurrent Unit (GRU) to find a relationship of temporal characteristic. The dataset is collected by high frequency (HF) radar station's located along coastal Thailand's gulf by GISTDA from 2014 to 2016. It was an intensive experiment comparing our method and eight existing methods, e.g., ARIMA, kNN, Perceptron, Multilayer Perceptron (MLP), etc. The results show that our network outperforms almost all baselines in terms of RMSE for 11.21% and 27.01% averaging improvement on U and V components, consecutively.
Some of the metrics are blocked by your
consent settings
Semantic segmentation on remotely sensed images using an enhanced global convolutional network with channel attention and domain specific transfer learning
(2019-01-01)
Panboonyuen, Teerapong
;
Jitkajornwanich, Kulsawasd
;
Lawawirojwong, Siam
;
Srestasathiern, Panu
;
Vateekul, Peerapon
In the remote sensing domain, it is crucial to complete semantic segmentation on the raster images, e.g., river, building, forest, etc., on raster images. A deep convolutional encoder-decoder (DCED) network is the state-of-the-art semantic segmentation method for remotely sensed images. However, the accuracy is still limited, since the network is not designed for remotely sensed images and the training data in this domain is deficient. In this paper, we aim to propose a novel CNN for semantic segmentation particularly for remote sensing corpora with three main contributions. First, we propose applying a recent CNN called a global convolutional network (GCN), since it can capture different resolutions by extracting multi-scale features from different stages of the network. Additionally, we further enhance the network by improving its backbone using larger numbers of layers, which is suitable for medium resolution remotely sensed images. Second, "channel attention" is presented in our network in order to select the most discriminative filters (features). Third, "domain-specific transfer learning" is introduced to alleviate the scarcity issue by utilizing other remotely sensed corpora with different resolutions as pre-trained data. The experiment was then conducted on two given datasets: (i) medium resolution data collected from Landsat-8 satellite and (ii) very high resolution data called the ISPRS Vaihingen Challenge Dataset. The results show that our networks outperformed DCED in terms of F1 for 17.48% and 2.49% on medium and very high resolution corpora, respectively.
Some of the metrics are blocked by your
consent settings
Semantic Segmentation on Medium-Resolution Satellite Images Using Deep Convolutional Networks with Remote Sensing Derived Indices
(2018-09-06)
Chantharaj, Sirinthra
;
Pornratthanapong, Kissada
;
Chitsinpchayakun, Pitchayut
;
Panboonyuen, Teerapong
;
Vateekul, Peerapon
Semantic Segmentation is a fundamental task in computer vision and remote sensing imagery. Many applications, such as urban planning, change detection, and environmental monitoring, require the accurate segmentation; hence, most segmentation tasks are performed by humans. Currently, with the growth of Deep Convolutional Neural Network (DCNN), there are many works aiming to find the best network architecture fitting for this task. However, all of the studies are based on very-high resolution satellite images, and surprisingly; none of them are implemented on medium resolution satellite images. Moreover, no research has applied geoinformatics knowledge. Therefore, we purpose to compare the semantic segmentation models, which are FCN, SegNet, and GSN using medium resolution images from Landsat-8 satellite. In addition, we propose a modified SegNet model that can be used with remote sensing derived indices. The results show that the model that achieves the highest accuracy RGB bands of medium resolution aerial imagery is SegNet. The overall accuracy of the model increases when includes Near Infrared (NIR) and Short-Wave Infrared (SWIR) band. The results showed that our proposed method (our modified SegNet model, named RGB-IR-IDX-MSN method) outperforms all of the baselines in terms of mean F1 scores.
Some of the metrics are blocked by your
consent settings
Utilizing Twitter Data for Early Flood Warning in Thailand
(2018-07-02)
Jitkajornwanich, Kulsawasd
;
Kongthong, Chanwit
;
Khongsoontornjaroen, Nattaya
;
Kaiyasuan, Jeedapa
;
Lawawirojwong, Siam
Natural disasters cause significant damage to the country as well as its citizens as we have seen in the news. Drought, wild fire, earthquake and flooding are some examples of the primary natural disasters occurred in Thailand. In this research, we focus on »flooding» and use data from Twitter, where users' mobile devices are utilized as IoT input channels. The goal of this work is to analyze near real-time data (tweets) for early flood warning. Traditional methods in processing, analyzing and reporting a flooding event take quite some time. In social medias (through cellphones), on the other hand, by harvesting crowdsources, potential flooding can be predicted faster - though with the price of reliability of the retrieved tweets. In our research, several techniques are incorporated in order to maximize the accuracy of results, including, tokenization, geo-encoding and decoding, NLP via string matching (Levenshtein's algorithms), and Google APIs for visualization. Finally, the dynamic yet user-friendly map is produced with respect to the posted relevant tweets along their associated frequencies.
Some of the metrics are blocked by your
consent settings
An enhanced deep convolutional encoder-decoder network for road segmentation on aerial imagery
(2018-01-01)
Panboonyuen, Teerapong
;
Vateekul, Peerapon
;
Jitkajornwanich, Kulsawasd
;
Lawawirojwong, Siam
Object classification from images is among the many practical examples where deep learning algorithms have successfully been applied. In this paper, we present an improved deep convolutional encoder-decoder network (DCED) for segmenting road objects from aerial images. Several aspects of the proposed method are enhanced, incl. incorporation of ELU (exponential linear unit)—as opposed to ReLU (rectified linear unit) that typically outperforms ELU in most object classification cases; amplification of datasets by adding incrementally-rotated images with eight different angles in the training corpus (this eliminates the limitation that the number of training aerial images is usually limited), thus the number of training datasets is increased by eight times; and lastly, adoption of landscape metrics to further improve the overall quality of results by removing false road objects. The most recent DCED approach for object segmentation, namely SegNet, is used as one of the benchmarks in evaluating our method. The experiments were conducted on a well-known aerial imagery, Massachusetts roads dataset (Mass. Roads), which is publicly available. The results showed that our method outperforms all of the baselines in terms of precision, recall, and F1 scores.
Some of the metrics are blocked by your
consent settings
Temporal kNN for short-Term ocean current prediction based on HF radar observations
(2017-09-05)
Jirakittayakorn, Arnon
;
Kormongkolkul, Teeranai
;
Vateekul, Peerapon
;
Jitkajornwanich, Kulsawasd
;
Lawawirojwong, Siam
Ocean surface current prediction is at the core of various marine operational routines, including disaster monitoring, oil-spill backtracking, sea navigation and search-And-rescue operations. More accurate prediction can yield significant improvement to the overall system. Most existing short-Term prediction methods applied numerical models based on physical processes. In this paper, we propose an alternative approach in predicting the surface current by utilizing temporal k-nearest-neighbor technique, which can predict the future surface current up to 24 hours in advance. Our model incorporates several pre-processing methods, e.g. feature extraction and data transformation, in order to capture the seasonal and temporal characteristics of the HF (high frequency) radar observation data. The developed model was implemented, validated and compared with the existing models using the same historical datasets collected from the HF coastal radar stations located along the Gulf of Thailand. Our experimental results indicate that the proposed model can achieve the highest accuracy among all methods, including ARIMA, exponential smoothing, and LSTM; and satisfy the oil-spill backtracking application requirements. In addition, we found that our system requires little to none maintenance and can easily be adapted to other coastal radar locations where the amount of historical HF radar observations is limited.
Some of the metrics are blocked by your
consent settings
Road segmentation of remotely-sensed images using deep convolutional neural networks with landscape metrics and conditional random fields
(2017-07-01)
Panboonyuen, Teerapong
;
Jitkajornwanich, Kulsawasd
;
Lawawirojwong, Siam
;
Srestasathiern, Panu
;
Vateekul, Peerapon
Object segmentation of remotely-sensed aerial (or very-high resolution, VHS) images and satellite (or high-resolution, HR) images, has been applied to many application domains, especially in road extraction in which the segmented objects are served as a mandatory layer in geospatial databases. Several attempts at applying the deep convolutional neural network (DCNN) to extract roads from remote sensing images have been made; however, the accuracy is still limited. In this paper, we present an enhanced DCNN framework specifically tailored for road extraction of remote sensing images by applying landscape metrics (LMs) and conditional random fields (CRFs). To improve the DCNN, a modern activation function called the exponential linear unit (ELU), is employed in our network, resulting in a higher number of, and yet more accurate, extracted roads. To further reduce falsely classified road objects, a solution based on an adoption of LMs is proposed. Finally, to sharpen the extracted roads, a CRF method is added to our framework. The experiments were conducted on Massachusetts road aerial imagery as well as the Thailand Earth Observation System (THEOS) satellite imagery data sets. The results showed that our proposed framework outperformed Segnet, a state-of-the-art object segmentation technique, on any kinds of remote sensing imagery, in most of the cases in terms of precision, recall, and F1.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results