Method and device for road sign recognition
View Patent ↗A method and a device are provided for recognizing road signs in image data. The method includes, but is not limited to segmenting an object in the image data that is a road sign for a predefined probability. A text mapped in the segmented image data is identified using a text recognition method, where this text comprises numbers and/or words and/or abbreviations and/or combinations thereof. A probability value is determined for the text being depicted on a road sign and, in case the probability value is smaller than or equal to a predefined threshold value, is selected as a potential road sign. In case the probability value is greater than the predefined threshold value, a classifier is applied to the segmented image data for recognizing the object as an actual road sign.
1. A method for recognizing road signs in image data, comprising:
segmenting a road sign for a predefined first probability in the image data in a processor;
identifying a text mapped in the image data after the segmenting using a text recognition method in the processor;
determining a probability value for the text depicted on the road sign in the processor;
selecting, in the processor, the road sign as a potential road sign in a first case that the probability value is smaller than or equal to a predefined threshold value; and
applying, in the processor, a classifier to the image data for recognizing the road sign as an actual road sign in a second case that the probability value is greater than the predefined threshold value;
wherein the probability value is based on a predefined desired match of an outer contour of the road sign that is mapped in the image data with a shape of a known road sign.
2. The method according to claim 1 , wherein the probability value is based on a predefined match of colors of the road sign that is mapped in the image data with colors of a known road sign.
3. The method according to claim 1 , wherein the segmenting is performed using an edge based segmenting process.
4. The method according to claim 1 , wherein the text recognition method is an OCR method.
5. The method according to claim 1 , wherein the classifier is configured for a classification of pictograms.
6. A device for recognizing road signs in image data comprising:
a segmenting device that is configured to segment a road sign for a predefined first probability in the image data;
text mapping device that is configured to map text in the image data produced by the segmenting device with a text recognition method;
a determining device with which a probability value is determined for the text depicted on the road sign;
a selecting device that is configured to select the road sign as a potential traffic sign if the probability value is smaller than or equal to a predefined threshold value; and
a classifying device that is applied to the image data produced by the segmenting device for recognizing the road sign as an actual road sign if the probability value is greater than the predefined threshold value;
wherein the probability value is based on a predefined desired match of an outer contour of the road sign that is mapped in the image data with a shape of a known road sign.
7. The device according to claim 6 , wherein the text recognition method is an OCR recognition method.
8. The device according to claim 6 , wherein the text comprises a number.
9. The device according to claim 6 , wherein the text comprises a word.
10. The device according to claim 6 , wherein the text comprises an abbreviation.
11. The device according to claim 7 , wherein the text recognition method is an ICR method.
12. The device according to claim 7 , wherein the text recognition method is an IWR method.