Research of Automobile Fault Lamp Recognition Algorithm Based on Mobile Platform

In order to identify dashboard fault indicators timely and help drivers take countermeasures, we design and implement a mobile platform-based dashboard fault indicator recognition algorithm. First we collect dashboard fault indicator images through mobile phone shooting and network download, and then use image augmentation to expand our dataset. This paper improves the SSD algorithm by increasing the number of feature maps in the feature pyramid and changing the specifications of the default box. These changes made the algorithm better detect fault indicators. Aiming at the excessive volume in model compression and transplantation, we select a better compression algorithm by comparing three different compression methods. Finally, the compressed model is transplanted to the mobile terminal.