Deep Learning Process and Application for the Detection of Dangerous Goods Passing through Motorway Tunnels

Automated deep learning and data mining algorithms can provide accurate detection, frequency patterns, predictions of dangerous goods passing through motorways tunnels. This paper presents a post-processing image detection application three-stage algorithm that identifies records goods’ passage tool receives low-resolution input from toll camera images offers timely information on vehicles carrying goods. According to the authors’ experimentation, mean accuracy achieved by stage 2 proposed in identifying ADR plates is close 96% 92% both stages 1 algorithm. In addition, for successful optical character recognition numbers, algorithm’s 3 between 90 97%, overall Optical Character Recognition are 94%. Regarding execution time, achieve real-time capabilities processing one less than 2.69 s.