A method of recognizing seat-belt wear based on gray scale integral projection

作者：Ge Ruhai^*; Hu Manjiang; Fu Kai

来源：Qiche Gongcheng/automotive Engineering, 2012, 34(9): 787-790.

• Geometric feature
• Global threshold
• Gray scale
• Integral projections
• Position coordinates
• Priori knowledge
• Recognition methods
• Seat belt
• Seat-belt recognition
• Threshold segmentation
• Wear state
• Wearing rate

To further increase the seat belt wearing rate, and in view of the inadequacy of existing prompt system for seat belt wear, a new recognition method of seat belt wear is proposed based on gray scale integral projection. With the method, by preprocessing the collected occupant pictures, an image with a relatively uniform gray scale distribution is obtained, which is converted into binary images by global threshold segmentation. Then both vertical and horizontal gray scale integral projections are conducted on binary images, combined with a priori knowledge on the geometric features of seat-belt, to get the position coordinates of the feature points of seat-belt. Finally, the recognition on seat belt wear is realized. The results of tests show that the method proposed can effectively recognize the seat-belt wear state of occupants with relatively high applicability and accuracy.

• 出版日期2012