Accelerating Road Sign Ground Truth Construction with Knowledge Graph and Machine Learning
This work provides a tool to accelerate and improve the accuracy of road sign annotation, which is a critical bottleneck for developing robust AI-based Road Sign Recognition (RSR) systems for developers and researchers.
This paper addresses the challenge of creating high-quality road sign datasets for AI-based recognition systems, which is often hampered by annotators' unfamiliarity with diverse road sign systems. The authors propose a system that combines a knowledge graph with a variational prototyping-encoder (VPE) to assist human annotators, reducing the sign search space by 98.9% and proposing the correct single candidate for 75% of signs.
Having a comprehensive, high-quality dataset of road sign annotation is critical to the success of AI-based Road Sign Recognition (RSR) systems. In practice, annotators often face difficulties in learning road sign systems of different countries; hence, the tasks are often time-consuming and produce poor results. We propose a novel approach using knowledge graphs and a machine learning algorithm - variational prototyping-encoder (VPE) - to assist human annotators in classifying road signs effectively. Annotators can query the Road Sign Knowledge Graph using visual attributes and receive closest matching candidates suggested by the VPE model. The VPE model uses the candidates from the knowledge graph and a real sign image patch as inputs. We show that our knowledge graph approach can reduce sign search space by 98.9%. Furthermore, with VPE, our system can propose the correct single candidate for 75% of signs in the tested datasets, eliminating the human search effort entirely in those cases.