This paper describes the tracking stage of a road sign identification system with the use of a Kalman filter estimator. Although traditionally traffic sign recognition systems work in a single-frame way, tracking using inter-frame information is crucial in order to reduce false alarms. In applications that involve maintenance systems, the purpose of tracking is to give a single stroke of each road sign although it is presented in several frames of a sequence. The tracking module uses the output of the recognition stage, which processes each frame independently. Each traffic sign is followed for a specific distance which is computed in each case based on the system parameters. This setup has permitted improve the accuracy of the performance with respect to the obtained at the output of the recognition system. Additionally most false alarms are eliminated because their characteristic are temporally incoherent.
No takes yet. Share an insight, caveat, or question.
Lafuente-Arroyo et al. (2007) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: