Mobilenet based traffic sign detection system for mobile mapping: Crowdsourced geographical data collection system

Abstract

Mobile mapping systems (MMS) have gained increasing interest as a cost-effective means of collecting geospatial data, catering to the digital mapping needs of various domains such as advanced driver assistance systems (ADAS) and intelligent transportation systems (ITS). In the generated maps, the location and class information of traffic signs are particularly crucial for the aforementioned applications. However, the extensive and complex nature of data collected by MMS makes it challenging to infer the location and class of traffic signs. Consequently, researchers have developed artificial intelligence -based methods for processing traffic sign data. In this study, a Crowdsourced Geographical Data Collection System (CGDCS) which is designed for the inference of traffic sign location and class information using artificial intelligence is introduced. CGDCS is a lightweight system that operates on mobile devices, leveraging the MobileNet architecture to detect and classify traffic signs present in real-time camera images, thereby transferring the location and class information of the signs to a database. The study demonstrates that CGDCS is more practical and efficient than traditional methods involving manual processing, semi -traditional methods based on the extraction of shape and color features of traffic signs, and AIbased methods that process field data in high-performance computers using high computer vision and machine learning techniques.