Browsing by Author "Ik, Tsi-Ui"

Now showing 1 - 3 of 3

Microscopic Traffic Monitoring and Data Collection Cloud Platform Based on Aerial Video
(2020-01-01)
Chen, Guan-Wen
;
Yeh, Tzu-Chuan
;
Liu, Ching-Yu
;
Ik, Tsi-Ui
;
資訊工程學系
Real-time traffic video streaming, such as roadside surveillance and aerial video, has been widely used in traffic monitoring nowadays. However, most of the traditional traffic data collection methods lack mobility that can only collect macroscopic data. In this paper, an intelligent traffic monitoring system based on an open source cooperative platform called SAGE2 was developed. Based on the integrated big screen TV wall of SAGE2, a map-based aerial traffic video streaming management interface was designed. In the image pre-processing section, it provides functions such as lens distortion removal, top view projection transforms, and video stabilization; simulate video streaming to provide instant and long-term micro-flow data collection. Micro-traffic flow data provides high-resolution information both in time and space which can be used to analyze the driving behavior of individuals and the public. Combined with the lane level map, it can provide a variety of visual vehicle flow presentations, such as intersection traffic distribution that can also be used to develop an innovative application in the future.
Smart Shopping Carts Based on Mobile Computing and Deep Learning Cloud Services
(2020-01-01)
Sarwart, Muhammad Atif
;
Daraghmi, Yousef-Awwad
;
Liu, Kuan-Wen
;
Chi, Hong-Chuan
;
Ik, Tsi-Ui
Self-checkout systems enable retailers to reduce costs and customers to process their purchases quickly without waiting in queues. However, existing self-checkout systems suffer from design problems as they require large hardware consisting of a camera, sensors, RFID and other IoT technologies which increases the cost of such systems. Therefore, we propose a smart shopping cart with self-checkout, called iCart, to improve customer's experience at retail stores by enabling just walk out checkout and overcome the aforementioned problems. iCart is based on mobile cloud computing and deep learning cloud services. In iCart, a checkout event video is captured and sent to the cloud server for classification and segmentation where an item is identified and added to the shopping list. The Linux based cloud server contained the yolov2 deep learning network. iCart is a lightweight system of low cost solution which is suitable for the small-scale retail stores. The system is evaluated using real-world checkout video, and the accuracy of the shopping event detection and item recognition is about 97%.
Stitching Aerial Images for Vehicle Positioning and Tracking
(2018-01-01)
Tsao, Paul
;
Ik, Tsi-Ui
;
Chen, Guan-Wen
;
Peng, Wen-Chih
;
資訊工程學系
In recent years, applications such as reproduction of traffic accident scene, calculation of traffic flow, etc. use UAVs to collect data by aerial images. If a UAV does not move, the coordinates of objects in images can be considered as reference for predicting parameters such as distance and direction. However, this does not apply if the UAV is moving. In this research, methods of image processing are used to obtain the pinhole model which is similar to perpendicularly taken images, which should be distance-preserving. Then, the method of image stitching is used to find out the correlation of relative position between each image in order to construct a global coordinates system over every images. The common used methods of image stitching are not considered about distance-preserving, and cause the cumulative error usually. In this case, GPS information is used to estimate the starting position of images, then stitching those images to a panorama through applying SIFT feature pair and fine-tuning by the gradient method. At last, this paper integrates methods as mentioned into implementation and presents visualized data, then both the trajectory of UAV and the relative position of objects between images and the panorama can be observed by user in order to verify feasibility and precision of methods. Also the results of this paper can be applied with traffic flows detection in the future.