Vision-Based Navigation in Indoor Environments Without Using Image Database
PROCEEDINGS OF THE 27TH INTERNATIONAL TECHNICAL MEETING OF THE SATELLITE DIVISION OF THE INSTITUTE OF NAVIGATION (ION GNSS 2014)(2014)
摘要
Recently, an indoor navigation has attracted great attention in industries and research institutes. Also, a wearable device such as smart glasses has been emerging as the next-generation device to substitute the smartphone. We have a plan to develop an indoor navigation system based on smart glasses as soon as it is released in Republic of Korea. One of the most critical problems in vision-based indoor navigation is difficulty in the database construction when estimating the locations of users.Here, we propose a vision-based navigation system in indoor environments which uses an indoor map and does not require an image database. In each image, features are extracted to recognize the indoor objects without using image database. We define the metric about the four features which are pillar detection metric (PDM), hallway entrance detection metric (HEDM), hallway detection metric (HDM), and absence. Since the four metrics are normalized in the range of 0 or 1, we can classify them using the decision tree. After the classification, we estimate the position of the user through the angle-based matching between the recognized objects and the objects in an indoor map. We already know the angular information of each image using magnetometer and gyroscope built in smartphone. So, we can know the angle between the current position and recognized object. The current position of user is represented as a linear equation and we can solve it using pseudo inverse.To verify the performance of the proposed system, we conducted the positioning experiments in indoor environment. The indoor map is comprised of hall and hallway and we captured the image in six positions which were four halls and two hallways. In each position, we captured 18 images around the user with its angular information. The experimental results show an average recognition rate with 71.3% and the positioning performance with 7 meters.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要