Traffic Sign Detection and Extraction with GIS, GPS, and Machine Learning

Authors: ZIHAO WU*, GS
Topics: Geographic Information Science and Systems, Transportation Geography, UAS / UAV
Keywords: GIS, Traffic Signs Detection, Machine Learning, TensorFlow, Google Street View, Go Pro, YOLO
Session Type: Poster
Day: 4/4/2019
Start / End Time: 9:55 AM / 11:35 AM
Room: Lincoln 2, Marriott, Exhibition Level
Presentation File: Download



Road traffic signs management is a process that searches, maintains, and builds traffic signs inventory to ensure normal functioning of traffic systems. Automatic road traffic signs detection is an important feature in smart cities. Existing road assets management systems usually rely on labor-intensive site inventory. Some approaches use computer vision techniques to recognize traffic signs. Recent approaches combine GPS data and vehicle-based image recognition system to detect traffic signs along with geographic information. This research provides an innovative way to detect traffic signs based on geotagged photos from Google Street View and geotagged videos from Go Pro. We used the Single Shot Multi-Box Detector based on a TensorFlow framework to train the recognition model to deal with the Google Street images. Besides, this research also utilized YOLO to extract traffic signs form Go Pro videos, which can provide a fresh street view. The whole process is implemented on a graphic card with CUDA acceleration to speed up the training and detecting process. Results showed that stop signs and traffic signs can be accurately detected and extracted with presenting them on the digital map. This research helps to reduce workload for traditional traffic asset inventory. Our workflow can be used to detect other traffic signs and applied to other cities.

Abstract Information

This abstract is already part of a session. View the session here.

To access contact information login