Notice of RetractionTraffic lights recognition based on morphology filtering and statistical classification

Notice of Retraction

After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE´s Publication Principles.

We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.

The presenting author of this paper has the option to appeal this decision by contacting TPII@ieee.org.

Detection and recognition of the traffic lights are key processes for path planning of the intelligent vehicle. In this research, a novel method is introduced to recognize the traffic lights in urban environment. Firstly, an original image is converted to a binary image by the top-hat transform and threshold segmentation to obtain the brighter regions. Then the candidate regions without satisfying condition are removed by methods of the morphology and geometry feature filtering. Furthermore, a novel recognition method is carried out based on statistical analysis with amount of traffic lights image samples. It utilizes the color feature extracted by the Hue component in the HSV color space for classifying the types of traffic lights. Amount of experiments indicate that the novel algorithm is better adapted to the complex weather conditions, and the rate of recognition is higher than 97%, as well as the time performance could achieve the requirement of real-time processing.