Due to the various sizes of each object, such as kilometer stones, detection is still a challenge, and it directly impacts the accuracy of these object counts. Transformers have demonstrated impressive results in various natural language processing (NLP) and image processing tasks due to long-range modeling dependencies. This paper aims to propose an exceeding you only look once (YOLO) series with two contributions: (i) We propose to employ a pre-training objective to gain the original visual tokens based on the image patches on road asset images. By utilizing pre-training Vision Transformer (ViT) as a backbone, we immediately fine-tune the model weights on downstream tasks by joining task layers upon the pre-trained encoder. (ii) We apply Feature Pyramid Network (FPN) decoder designs to our deep learning network to learn the importance of different input features instead of simply summing up or concatenating, which may cause feature mismatch and performance degradation. Conclusively, our proposed method (Transformer-Based YOLOX with FPN) learns very general representations of objects. It significantly outperforms other state-of-the-art (SOTA) detectors, including YOLOv5S, YOLOv5M, and YOLOv5L. We boosted it to 61.5% AP on the Thailand highway corpus, surpassing the current best practice (YOLOv5L) by 2.56% AP for the test-dev data set.
Semantic segmentation is a fundamental task in remote sensing image analysis that aims to classify each pixel in an image into different land use and land cover (LULC) segmentation tasks. In this paper, we propose MeViT (Medium-Resolution Vision Transformer) on Landsat satellite imagery for the main economic crops in Thailand as follows: (i) para rubber, (ii) corn, and (iii) pineapple. Therefore, our proposed MeViT enhances vision transformers (ViTs), one of the modern deep learning on computer vision tasks, to learn semantically rich and spatially precise multi-scale representations by integrating medium-resolution multi-branch architectures with ViTs. We revised mixed-scale convolutional feedforward networks (MixCFN) by incorporating multiple depth-wise convolution paths to extract multi-scale local information to balance the model’s performance and efficiency. To evaluate the effectiveness of our proposed method, we conduct extensive experiments on the publicly available dataset of Thailand scenes and compare the results with several state-of-the-art deep learning methods. The experimental results demonstrate that our proposed MeViT outperforms existing methods and performs better in the semantic segmentation of Thailand scenes. The evaluation metrics used are precision, recall, F1 score, and mean intersection over union (IoU). Among the models compared, MeViT, our proposed model, achieves the best performance in all evaluation metrics. MeViT achieves a precision of 92.22%, a recall of 94.69%, an F1 score of 93.44%, and a mean IoU of 83.63%. These results demonstrate the effectiveness of our proposed approach in accurately segmenting Thai Landsat-8 data. The achieved F1 score overall, using our proposed MeViT, is 93.44%, which is a major significance of this work.
This study investigates optimal processing parameters for near real-time Zenith Total Delay (ZTD) estimation using Ultra-Rapid products and a sliding window approach. GNSS data from 20 CORS stations in Thailand were processed with GipsyX over 90 days representing three seasons. Window sizes from 30 to 540 minutes were evaluated using 15-minute steps, and overlapping estimates were combined by weighted least squares averaging. Results show that RMSE decreases rapidly for short windows (30–100 minutes) and stabilizes at approximately 4-8 mm for window sizes exceeding 250 minutes, remaining below the 13 mm accuracy threshold for NWP nowcasting. Most stations achieve operational accuracy with window sizes of about 120 minutes, while the network-wide average optimal window size is 79 ± 20 minutes after excluding outliers. Observation data quality, particularly data gaps and cycle slips, significantly influences ZTD stability and required window length. Seasonal analysis indicates that increased atmospheric variability leads to higher ZTD variability and longer optimal windows. Overall, Ultra-Rapid products enable reliable near real-time ZTD estimation within 1–3 hours, offering a practical balance between timeliness, accuracy, and computational efficiency for GNSS meteorology in tropical regions.