IQ-STAN: Image Quality Guided Spatio-Temporal Attention Network for License Plate Recognition

Author(s):  
Cong Zhang ◽  
Qi Wang ◽  
Xuelong Li
Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 1005
Author(s):  
Pau Climent-Pérez ◽  
Francisco Florez-Revuelta

The potential benefits of recognising activities of daily living from video for active and assisted living have yet to be fully untapped. These technologies can be used for behaviour understanding, and lifelogging for caregivers and end users alike. The recent publication of realistic datasets for this purpose, such as the Toyota Smarthomes dataset, calls for pushing forward the efforts to improve action recognition. Using the separable spatio-temporal attention network proposed in the literature, this paper introduces a view-invariant normalisation of skeletal pose data and full activity crops for RGB data, which improve the baseline results by 9.5% (on the cross-subject experiments), outperforming state-of-the-art techniques in this field when using the original unmodified skeletal data in dataset. Our code and data are available online.


The license plate recognition (LPR) system in Saudi Arabia is a system used to identify vehicle license plates automatically. It is used in many places such as airports, highways, and parking lots. The efficiency of the system depends on the image quality, weather conditions, location of plates, and the variations of license plates. The license plates in the Kingdom of Saudi Arabia are different from other license plates in other countries because they are written in both Arabic and English languages. This could be exploited to integrate the recognition results from both languages in a way to increase the efficiency of the system and reduce the errors that could affect the recognition of license plates. Instead of one LPR system, we have two independent LPR systems, and the results of both systems could be fused to increase the system's ability of reading cars’ plates


Sign in / Sign up

Export Citation Format

Share Document