In this study, an area-based matching strategy is proposed for conjugate point searching between multiple spherical panorama images (SPIs). With the concept of collinearity and epipolar constraint, object space images are produced for matching to prevent the problem caused by different viewing perspective and scale variation. Two matching index, Average Normalized Cross Correlation(ANCC) and Yet Another Reconstruction Dataprogram (YARD) index are used to check the similarity between images within the searching range, the position which has the highest similarity is regard as the conjugate point position. An indoor text field with five SPIs is set for image matching text, the exterior orientation parameters (EOPs) of SPIs are obtained by the multi-station network adjustment in advance. The mean difference and the root mean square difference (RMSD) of positioning results are compared, and the result shows better matching accuracy can be performed by object space matching.

Public Bicycle-Sharing System (PBS) has been developed for a decade in Taipei City. As the construction of the rental station has gradually become complete, it has become one of the public transport systems in Taipei City. Since the usage of PBS in outdoor environments, not only that, Taiwan has a high concentration of particulate matter in winter and spring. The particulate matter in the air easily enter the respiratory tract and blood vessels of the human body, which may cause physical discomfort or increase the risk of cardiovascular disease. Does air quality and weather profile have an impact on the use of public bicycles? The study used Pearson Correlation Coefficient and Regression Analysis method to analyze the relationship between PBS rental behavior and weather and air quality from November, 2016 to October, 2017 in Taipei City. The results show that rainfall in the weather-related variables is significantly negatively correlated with the rental rate of PBS; temperature, wind speed and concentration of PM2.5 have no significant effect.

Reacting to the era of autonomous vehicle, various domestic and foreign experts and companies have been actively involved in related studies and development. The technique which uses the pre-build three-dimensional high definition map (HD Maps) to aid the ability of positioning and orientation efficiently is indispensable. The ultimate goal is to provide autonomous vehicles with assistant information and ensure that they can drive safely and accurately during the whole process without human intervention. Currently, there is still no universal standard workflow for HD Maps and related regulations in our country. The existing mapping regulations and specifications are no longer meet the requirements for the construction, maintenance and inspection of HD Maps. Hence, this research proposes the concept of definition of mapping specifications, accuracy requirements, operation method, standard procedure and other related works for HD Maps based on literature reviews. To sum up, we will conduct preliminary feasible assessment and offer the contents to experts and scholars for further researches and development.

Whereas the paddy rice has played an important role on the life of human being, however, the estimation of its production is a difficult task. In tradition, the difference image classification on image data combine with levees is a major solution for their location and distribution. It includes the variation of each indicators of vegetation. On the other hand, the amounts of the relative error on the production of the paddy rice are quite large based on the developed regression equation. This study cooperated with Chun Hsing Survey applying the hyperspectral imagery data. The orthophotos are first used to perform the ROC (Regional Object-based Classification) and the entropy-based classification (EBC) for classifying each rice levee of field. The Monte Carlo method to analyze the image content, calculate the production density of each block, estimate the reasonable yield of rice fields, and make an absolute contribution to the accuracy of agricultural yield estimation. The ROC+ Monte Carlo method is used to estimate the error of about 14.5% and the standard deviation is 1.24 ton/ha.

Vehicle-to-vehicle anti-collision warning can be achieved by using real-time high-precision positioning and instant communication among vehicles when there is no way to see, and the article combines the RTK technology and the DSRC technology to meet the requirements. When doing the GNSS RTK positioning, the GNSS receiver on the vehicle receives the observation data and the station information from the reference station when collecting the satellite data. Then, the instantly relative positioning is performed on the two sets of data to achieve high-precision positioning. The DSRC technology enables vehicles to directly transmit two-way messages within tens of meters, and provides high-speed data transmission to ensure real-time information transmission while the vehicle is moving at high speed. With the two technologies, the vehicle-to-vehicle anti-collision warning system makes the driver have sufficient reaction time, preventing the traffic accident.