Fast speedometer identification in dynamic scene based on phase correlation

Speedometer identification has been researched for many years. The common approaches to that problem are usually based on image subtraction, which does not adapt to image offsets caused by camera vibration. To cope with the rapidity, robust and accurate requirements of this kind of work in dynamic scene, a fast speedometer identification algorithm is proposed, it utilizes phase correlation method based on regional entire template translation to estimate the offset between images. In order to effectively reduce unnecessary computation and false detection rate, an improved linear Hough transform method with two optimization strategies is presented for pointer line detection. Based on VC++ 6.0 software platform with OpenCV library, the algorithm performance under experiments has shown that it celerity and precision.