Main idea
•TSR customer experience is marred by false identification and misclassification
•
•First step of successful TSR require traffic sign been segregated from back ground
•
•Potential signs meet the color and shape criteria also need to be identified as a traffic sign instead a roadside ads board.
•
•Current TSR algorithms relied on geometry shape and color hue to do segregation and identification.
•Color matching is also important criteria to positively classify traffic signs into a specific sign.
•
•Due to environment constraint included lighting, shadow. motion burl, vehicle vibration and sign warp, geometry of sign in images tends to be broken and the intensity and chromaticity property vary widely. powerful hardware computation needed to deal with the complex. Since by nature, these variables are random and unpredictable, some classification still cross the threshold causing error.
•Optical apparatus integrate car head lamp properties with special TSR sensor .
•The output images from this optical apparatus is basically get targets segregated and indentified by optical mean.
•Clean target images of day and night scene with much accurate color are provided for TSR algorithm.
•After the segregation and identification, TSR algorithm deals variables that have less unpredictable and have stricter mathematic rules to follow.
•TSR algorithm based on this optical apparatus can expect higher classification rate due to less uncertainty.
