Robust speed estimation for the video car recorder system

Recently, some of applications (APP) about car recorder systems have been proposed for iPhone. The car recorder system is built on iOS smart mobile devices, and the objective-c programming language is employed to code applications in the Xcode. The iOS mobile devices are usually equipped with GPS and camera. Thus, it only needs to design software on the integration and links so as to replace the traditional tachograph. The smart mobile device supports three types of positioning methods: built-in GPS positioning, telecommunications base station triangulation positioning, and Wi-Fi base station positioning. Using those methods, the car speed data of the car recorder system can be more accurate. But, the car speed that provided by iOS is not accurate in the actual operation. In this study, the corrected speed method for the video car recorder is proposed. In the corrected speed method, the robust linear regression is applied to correct the car speed in iPhone. In our experience, the proposed method can improve the accuracy of the car speed estimation in iPhone.