SLSiam Lawawirojwong

Siam Lawawirojwong

*This is an algorithmically generated author record based on publicly available information.

Siam Lawawirojwong has a total of 21 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Coupled responses of carbon storage and habitat quality to land use and land cover change in a tropical watershed of Northern Thailand

    by Sirasit Vongvassana, Sura Pattanakiat, Allan Sriratana Tabucanon, Theerawut Chiyanon, Pisut Nakmuenwai, Siam Lawawirojwong, Warin Boonriam, Pathomphot Chinsawadphan, Thamarat Phutthai

  • Open Access

    Transformer-Based Decoder Designs for Semantic Segmentation on Remotely Sensed Images

    by Teerapong Panboonyuen, Kulsawasd Jitkajornwanich, Siam Lawawirojwong, Panu Srestasathiern, Peerapon Vateekul

    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.


  • Open Access

    Malaria Risk Map Using Spatial Multi-Criteria Decision Analysis along Yunnan Border During the Pre-elimination Period

    by Xiaotao Zhao, Weerapong Thanapongtharm, Siam Lawawirojwong, Chun Wei, Yerong Tang, Yaowu Zhou, Xiaodong Sun, Liwang Cui, Jetsumon Sattabongkot, Jaranit Kaewkungwal

    In moving toward malaria elimination, finer scale malaria risk maps are required to identify hotspots for implementing surveillance–response activities, allocating resources, and preparing health facilities based on the needs and necessities at each specific area. This study aimed to demonstrate the use of multi-criteria decision analysis (MCDA) in conjunction with geographic information systems (GISs) to create a spatial model and risk maps by integrating satellite remote-sensing and malaria surveillance data from 18 counties of Yunnan Province along the China–Myanmar border. The MCDA composite and annual models and risk maps were created from the consensus among the experts who have been working and know situations in the study areas. The experts identified and provided relative factor weights for nine socioeconomic and disease ecology factors as a weighted linear combination model of the following: ([Forest coverage × 0.041] + [Cropland × 0.086] + [Water body × 0.175] + [Elevation × 0.297] + [Human population density × 0.043] + [Imported case × 0.258] + [Distance to road × 0.030] + [Distance to health facility × 0.033] + [Urbanization × 0.036]). The expert-based model had a good prediction capacity with a high area under curve. The study has demonstrated the novel integrated use of spatial MCDA which combines multiple environmental factors in estimating disease risk by using decision rules derived from existing knowledge or hypothesized understanding of the risk factors via diverse quantitative and qualitative criteria using both data-driven and qualitative indicators from the experts. The model and fine MCDA risk map developed in this study could assist in focusing the elimination efforts in the specifically identified locations with high risks.


  • Open Access

    Semantic Labeling in Remote Sensing Corpora Using Feature Fusion-Based Enhanced Global Convolutional Network with High-Resolution Representations and Depthwise Atrous Convolution

    by Teerapong Panboonyuen, Kulsawasd Jitkajornwanich, Siam Lawawirojwong, Panu Srestasathiern, Peerapon Vateekul

    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 ( i i ) 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 F 1 : 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.


  • Open Access

    Semantic Segmentation on Remotely Sensed Images Using an Enhanced Global Convolutional Network with Channel Attention and Domain Specific Transfer Learning

    by Teerapong Panboonyuen, Kulsawasd Jitkajornwanich, Siam Lawawirojwong, Panu Srestasathiern, Peerapon Vateekul

    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 F 1 for 17.48% and 2.49% on medium and very high resolution corpora, respectively.


  • Open Access

    Road Segmentation of Remotely-Sensed Images Using Deep Convolutional Neural Networks with Landscape Metrics and Conditional Random Fields

    by Teerapong Panboonyuen, Kulsawasd Jitkajornwanich, Siam Lawawirojwong, Panu Srestasathiern, Peerapon Vateekul

    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 F 1 .