The concept of Autonomous Vehicles (AV) or self-driving cars has been increasingly popular these past few years. As such, research and development of AVs have also escalated around the world. One of those researches is about High-Definition (HD) maps. HD Maps are basically very detailed maps that provide all the geometric and semantic information on the road, which helps the AV in positioning itself on the lanes as well as mapping objects and markings on the road. This research will focus on the early stages of updating said HD maps. The methodology mainly consists of (1) running YOLOv3, a real-time object detection system, on a photo taken from a stereo camera to detect the object of interest, in this case a traffic cone, (2) applying the theories of stereo-photogrammetry to determine the 3D coordinates of the traffic cone, and (3) executing all of it at the same time on a Python-based platform. Results have shown centimeter-level accuracy in terms of obtained distance and height of the detected traffic cone from the camera setup. In future works, observed coordinates can be uploaded to a database and then connected to an application for real-time data storage/management and interactive visualization.
|頁（從 - 到）||271-274|
|期刊||International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives|
|出版狀態||Published - 2019 12月 23|
|事件||2019 Geomatics and Data Science: Towards Adaptive Management in a Changing World, PhilGEOS x GeoAdvances 2019 - Manila, Philippines|
持續時間: 2019 11月 14 → 2019 11月 15
All Science Journal Classification (ASJC) codes