KMITL

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

Browse

Search Results

Now showing 1 - 10 of 10

Some of the metrics are blocked by your
consent settings
Deep Learning-Based Heritage Building Assessment with Spatial Context
(2025-01-01)
Rattanapitak, Wirat
;
Khwansuwan, Poon
;
Wangsiripitak, Somkiat
;
Sirikitsathian, Phatthanan
Rapid urbanization threatens architectural heritage in developing regions, where limited conservation experts cannot assess thousands of potentially valuable buildings before irreversible modifications occur. This paper presents an automated screening system for heritage building identification using deep learning and spatial analysis. The proposed framework employs a dual-stream architecture combining YOLOv8 object detectionwith SegFormer semantic segmentation to extract architectural features from building facade photographs. These visual features are integrated with Geographic Information System (GIS) data to incorporate spatial context, recognizing that heritage buildings often cluster in historically significant areas. A hybrid weighting mechanism balances data-driven feature importance (80%) with expert architectural knowledge (20%) to ensure cultural sensitivity. Experimental evaluation on 1,500 buildings in Roi Et Province, northeastern Thailand, demonstrates the system's effectiveness, achieving 87.6% classification accuracy while processing each building in approximately one second. In corporating spatial context improved performance by 6.4% over visual features alone. The transformer-based architecture proved particularly effective at identifying characteristic features such as paired windows and traditional wall patterns that distinguish heritage structures. This work provides a practical tool for large scale preliminary heritage assessment, enabling conservation authorities to efficiently allocate limited expert resources to high priority buildings while maintaining classification reliability suitable for initial screening purposes.
Some of the metrics are blocked by your
consent settings
GIS and Street View Integration: Analyzing Spatial Factors of Motorcycle Taxi Stands in Bangkok
(2024-01-01)
Rattanapitak, Wirat
;
Sirikitsathian, Phatthanan
Motorcycle taxis play a vital role in addressing lastmile connectivity challenges in Bangkok's complex urban transportation system. However, the factors influencing the spatial distribution of these informal transport services remain poorly understood. Kernel Density Estimation (KDE) was employed to examine the spatial distribution patterns, revealing two primary high-density clusters of stands in southern Chatuchak. Proximity analysis quantified relationships between the 208 stand locations and urban infrastructure factors, finding strategic positioning near mass transit stations (avg. 1.79 km), on sidewalks (70.5%), and in mixed-use areas with predominantly residential (33.19%) and commercial (29.32%) land use within a 100m radius. A decision tree model identified residential area proportion (importance 0.3423) and distance from metro stations (0.2935) as key predictors of stand presence, but achieved moderate accuracy (52.38%). The results highlight the close integration of motorcycle taxi stands within the urban fabric and their role in enhancing accessibility.
Some of the metrics are blocked by your
consent settings
Human height estimation using visual geometry and feature learning
(2021-01-01)
Dokthurian, Siriporn
;
Rattanapitak, Wirat
;
Wangsiripitak, Somkiat
Many existing video surveillance systems use human characteristics like face, height, and gait to identify a person. This paper proposes a human height estimation approach using visual geometry and feature learning that makes an estimate from a video clip of a person. An experiment was conducted to evaluate the performance of the approach. The approach achieved an average percentage final height estimate of 100.59 % (actual height = 100%), better than a previously reported estimate of 98.8% in the literature achieved by another approach. A successful further development of this approach would directly benefit forensic science investigators.
Some of the metrics are blocked by your
consent settings
Pixel-based foreground detection in repetitive time-series region
(2019-01-01)
Rattanapitak, Wirat
;
Wangsiripitak, Somkiat
Currently, many state-of-the-art background subtraction techniques cannot deal properly with the area of periodic changing background, while some continue classifying them as foreground at intervals, others simply mask that area as a non-region of interest. To cope with this issue, a novel method of detecting repetitive temporal patterns based on the image sequences was proposed in this paper. The main emphasis of the proposed approach is on classifying those pixels as a background and identifying foreground objects in their relevant areas. As for the foreground detection, a model of time series pattern found in each pixel is individually built first; and then, any changes beyond the allowance of model periodicity are then determined as foreground objects. The proposed method could be used and run in parallel with any state-of-the-art background subtraction technique, allowing more accurate foreground-background segmentation. Experimental results showed that using Y channel, the proposed method of detecting time-series background area could achieve 92.9% of recall rate with less than 1% false positives. The recall of foreground detection in an area of repetitive time-series pattern was about 87%; while F-measure was about 0.73 on average. The false positives of foreground detection were also less than 1%. Accordingly, the proposed time-delay detection technique could significantly help to suppress the foreground error on time series background area, especially during the change from one sub-pattern to another which causes a camera sensor to capture both sub-pattern values in one frame. Performance comparison with state-of-the-art methods showed that our proposed method was able to reduce 80% of the average false alarm and improve F-measure to 28% while the computational efficiency was reduced by only 1%.
Some of the metrics are blocked by your
consent settings
CDoTS: Change detection on time series background for video foreground segmentation
(2017-11-03)
Wangsiripitak, Somkiat
;
Rattanapitak, Wirat
Although many adaptive background subtraction methods have been proposed for image-based foreground detection, dynamic background in the scene, such as an electronic billboard, still causes a serious problem of false alarm. Exclusion of such area from region of interest may prevent the problem, however an issue of security hole on that area becomes another concern. A method of change detection on repetitive time series background is proposed in this paper. Our method extends an adaptive multiresolution background subtraction to allow detection of time series, which is in turn used for foreground extraction on such area. The accuracy of segmentation on static background is barely changed, while that on the area of periodic change is significantly improved.
Some of the metrics are blocked by your
consent settings
Vision-based system for automatic detection of suspicious objects on ATM
(2015-01-01)
Rattanapitak, Wirat
;
Wangsiripitak, Somkiat
Most skimming devices attached to an automatic teller machine (ATM) are similar in color and shape to the host machine, vision-based detection of such things is therefore difficult. A background subtraction method may be used to detect changes in a normal situation. However, without human detection, its background model is sometimes polluted by the ATM user, and the method cannot detect suspicious objects left in the scene. This paper proposes a real-time system which integrates (i) a simple image subtraction for detection of user arrival and departure, and (ii) an automatic detection of suspicious objects left on the ATM. The background model is updated only when no user is found, and used to detect suspicious objects based on a guided adaptive threshold. To avoid a detection miss, nonlinear enhancement is applied to amplify the intensity differences between foreign objects and host machine. Experimental results show that the proposed system increases correctly detected area by 13.21% compared with the fixed threshold method. It has no detection miss and false alarm either.
Some of the metrics are blocked by your
consent settings
Tracking-based human entry/exit detection on various video resolutions (A study on parameter effects)
(2015-01-01)
Saelao, Wongsatorn
;
Rattanapitak, Wirat
;
Wangsiripitak, Somkiat
A real-time tracking-based change detection using FAST features and a background feature model are proposed as a base system for detection of human entrance and exit. A speedy FAST feature extraction and tracking has to trade-off its accuracy, which sometimes causes a failure in human entrance/exit detection. Many video sizes are therefore tested in the system to examine the trade-off effects on the accuracy of feature extraction, tracking, and entry/exit detection. Tracking parameters are also investigated to determine the optimal values for each video resolution, such that stable tracking and detection are achieved. Experimental results show that the higher the video resolution is the more the error is likely to happen. Instability of feature extraction and position which increases in higher resolution is proved to be the main reason of failure. Increasing the number of previous images used in the update of background feature model, proportional to the resolution of video, takes into account the feature uncertainty. As the result, the proposed method is robust to changes in video resolution and runs at 30 fps without a miss of human entrance/exit detection and false alarm.
Some of the metrics are blocked by your
consent settings
Comparative efficiency of color models for multi-focus color image fusion
(2010-12-01)
Rattanapitak, Wirat
;
Udomhunsakul, Somkait
The comparative efficiency of color models for multi-focus color image fusion is presented in this paper. The objective of these experiments is to finding the proper color model for using in multi-focus color image fusion. In our research study, firstly we transform RGB color model of source images into four color models that are YIQ, YCbCr, HSV and HSI color models. Next, the intensity or luminance component is only used in fusion process using Spatial Frequency Measurement based fusion method compared with Stationary Wavelet Transform with Extended Spatial Frequency Measurement. Finally, the fused image results are transformed back to RGB model to get the final results. The experiments show that the YCbCr color model outperforms other color models in term of objective quality assessment.
Some of the metrics are blocked by your
consent settings
Comparative efficiency of Wavelet filters for multi-focus color image fusion
(2010-09-02)
Toontham, Jaruwan
;
Rattanapitak, Wirat
;
Udomhunsakul, Somkait
The comparative efficiency of Wavelet filters for multi-focus color image fusion is presented in this paper. Our experiment purposes are study and examine the suitable mother wavelets for using in multi-focus color image fusion. In fusion process, we use HSI color model and the fusing technique based on Stationary Wavelet Transform with Extended Spatial Frequency Measurement method. In our experiments, we investigate the effect of applying different types of wavelet filters belonging to orthogonal and biorthogonal wavelets with different orders. The wavelet filter used are Daubichies4, 8, 10, 12, 14, 16, 18 and Biorthogonal2.2, 2.4, 2.6, 2.8, 3.1, 3.3, 3.5, 3.7, 3.9, 4.4, 5.5, and 6.8. The fused image quality assessment is measured using Peak Signal to Noise Ratio. The result indicated that Biorthogonal 3.3 and 3.5 are proper choices for multi-focus color image fusion. © 2010 IEEE.
Some of the metrics are blocked by your
consent settings
Multi-focus image fusion based on Stationary Wavelet Transform and extended Spatial Frequency Measurement
(2009-04-20)
Borwonwatanadelok, Pusit
;
Rattanapitak, Wirat
;
Udomhunsakul, Somkait
In this paper, we propose a multi-focus image fusion approach based on Stationary Wavelet Transform (SWT) and extended the Spatial Frequency Measurements (SFM). Our proposed approach, two fused images are firstly decomposed into four subbands, which are one approximation subband (LL) and three details subbands (HL, LH and HH). Next, each subband is partitioned into blocks and each block is identified the clearer regions by computing the focus measure using the extended Spatial Frequency Measurement (SFM). Finally, the recovered fused image is reconstructed by performing the Inverse Stationary Wavelet Transform. From the experimental results, we found that the proposed method outperforms the traditional Wavelet Transform and SFM based methods in terms of objective and subjective assessments. © 2009 IEEE.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results