Position: 黃怡碩 > ePortfolio > Publication
Work Experience
Professional Certification
1. Yishuo Huang, "Detecting the changes in rural communities in Taiwan by applyingmultiphase segmentation on FORMOSA-2 satellite imagery," International Journal of Applied Earth Observation and Geoinformation, pp.56-75, Sep, 2015.
Agricultural activities mainly occur in rural areas; recently, ecological conservation and biologicaldiversity are being emphasized in rural communities to promote sustainable development for rural com-munities, especially for rural communities in Taiwan. Therefore, since 2005, many rural communities inTaiwan have compiled their own development strategies in order to create their own unique character-istics to attract people to visit and stay in rural communities. By implementing these strategies, youngpeople can stay in their own rural communities and the rural communities are rejuvenated. However,some rural communities introduce artificial construction into the community such that the ecologicaland biological environments are significantly degraded. The strategies need to be efficiently monitoredbecause up to 67 rural communities have proposed rejuvenation projects. In 2015, up to 440 rural com-munities were estimated to be involved in rural community rejuvenations. How to monitor the changesoccurring in those rural communities participating in rural community rejuvenation such that ecologicalconservation and ecological diversity can be satisfied is an important issue in rural community manage-ment. Remote sensing provides an efficient and rapid method to achieve this issue. Segmentation playsa fundamental role in human perception. In this respect, segmentation can be used as the process oftransforming the collection of pixels of an image into a group of regions or objects with meaning. Thispaper proposed an algorithm based on the multiphase approach to segment the normalized differencevegetation index, NDVI, of the rural communities into several sub-regions, and to have the NDVI distri-bution in each sub-region be homogeneous. Those regions whose values of NDVI are close will be mergedinto the same class. In doing so, a complex NDVI map can be simplified into two groups: the high andlow values of NDVI. The class with low NDVI values corresponds to those regions containing roads, build-ings, and other manmade construction works and the class with high values of NDVI indicates that thoseregions contain vegetation in good health. In order to verify the processed results, the regional boundarieswere extracted and laid down on the given images to check whether the extracted boundaries were laiddown on buildings, roads, or other artificial constructions. In addition to the proposed approach, anotherapproach called statistical region merging was employed by grouping sets of pixels with homogeneousproperties such that those sets are iteratively grown by combining smaller regions or pixels. In doing so,the segmented NDVI map can be generated. By comparing the areas of the merged classes in differentyears, the changes occurring in the rural communities of Taiwan can be detected. The satellite imageryof FORMOSA-2 with 2-m ground resolution is employed to evaluate the performance of the proposedapproach. The satellite imagery of two rural communities (Jhumen and Taomi communities) is chosento evaluate environmental changes between 2005 and 2010. The change maps of 2005–2010 show thata high density of green on a patch of land is increased by 19.62 ha in Jhumen community and converselya similar patch of land is significantly decreased by 236.59 ha in Taomi community. Furthermore, thechange maps created by another image segmentation method called statistical region merging generatesimilar processed results to multiphase segmentation.
2. Yishuo Huang, "Depressing the Interferogram Phase Noise Using a Total Variation Approach," Journal of Photogrammetry and Remote Sensing, Jan, 2015.
3. Ming-Gin Lee; Mang Tia; Shun-Hsing Chuang; Yishuo Huang; and Chia-Liang Chiang, "Pollution and Purification Study of the Pervious Concrete Pavement Material," Journal of Materials in Civil Engineering, Aug, 2014.
4. Y. Huang, CT. Chiu, MG. Lee and SY. Lin, "Applying the Multilayer Level Set Approach to Explore the Thermal Surface Characteristics of Hot Mix Asphalt," Construction and Building Materials, Vol.53 pp.621-634., Feb, 2014.
The surface temperature of hot mix asphalt (HMA) in the field is an important indicator of whether it is
under the appropriate conditions for installation and satisfies the installation specifications. Traditionally,
field engineers examine the temperature of HMA by employing a metal thermometer, penetrating the
HMA at random locations to measure the temperature. However, a non-contact thermal infrared camera
effectively provides a reasonable correlation between the surface temperature readings and the internal
mat temperature. In this paper, an image segmentation method is proposed and employed to analyze collected
thermal images of HMA in order to extract the surface temperature information without contacting
the HMA. Based on the minimization of energy, the multilayer level set approach implicitly presents
the regional boundaries as several nested level lines. The segmented results can be used to extract the
temperature information in order to establish the relationships between the recorded temperature and
time. These relationships can be utilized to monitor the cool-down phenomena of HMA to control the
quality of HMA installation.
5. Ming-Ju Lee, Ming-Gin Lee, Yung-Chih Wang, Yishuo Huang, and Wei-Chien Wang, "Study of Steam and Microwave Curing of Concretes Containing Slag, Fly Ash, or Silica Fume," Journal of Testing and Evaluation, Feb, 2014.
6. Yishuo Huang and Yu-Chen Huang, "Segmenting SAR Satellite Images With the Multilayer Level Set Approach," IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol4, No. 3,pp. 632-642,SCI, Sep, 2011.
Synthetic aperture radar (SAR) provides a remote sensing method to explore the ground truth in all types of weather conditions. However, interpretation of SAR images is difficult because of the effects of speckle signals in the images. One method, the multilayer level set approach, segments an entire given SAR image into several sub-regions such that the segmented regions are homogeneous. This method employs two implicit functions with pre-selected level values. Based on the fact that the segmented regions are homogeneous and presented as regional constants, the energy defined by the segmented regions and their corresponding regional boundaries is minimized such that the relationships between the defined energy and the implicit functions can be transformed into the relationships between the implicit functions and time. By implementing the algorithm in terms of finite difference, this method offers an efficient and stable approach to a numerical solution. By increasing iterations and preselected level values, the implicit functions evolve close to the regional boundaries based on the energy minimization. From the processed results, the multilayer level set approach can efficiently segment the given SAR images, allowing further image interpretation to reveal the ground truth in the imaged areas.
7. Yishuo Huang and Jer-Wei Wu, "Infrared Thermal Image Segmentations Employing the Multilayer Level Set Method for Non-Destructive Evaluation of Layered Structures," NDT&E International, vol 43, pp 34-44,(SCI), Jan, 2010.
This paper describes the multilayer level set method for identification of surface defects within a material. This method relies upon the examination of temperature variations within the material. Even though several image processing techniques have used thermal images for detection of surface defects. Detecting and locating surface defects from thermal images is difficult. Mumford and Shah proposed to divide an image in a set of homogeneous sub-regions such that the energy contained in the image can be minimized. Based on this minimization of the energy, the multilayer level set method implicitly presents the regional boundaries as several nested level lines. By increasing iterations and preselected level values, these lines evolve close to the level boundaries based on the energy minimization. In this paper, two kinds of tests are employed to evaluate the performance of the algorithm: the first is that the artificial defects are buried behind the tiles; the second that the artificial defectors are buried behind and near the surface of a structure covered with Carbon Fiber Reinforced Plastic (CFRP). With a set of halogen lights used to heat the structure, a thermal camera with temperature resolution 0.1 degrees Celsius is employed to record the temperature changes. The experimental results show that, according to the predefined level values, the multilayer level set method can successfully detect regional boundaries of the buried defects by identifying temperature changes within their neighborhoods using infrared thermal images.