In the field of intelligence video surveillance

pedestrian detection is paid great attention to the security of daily life. In order to raise the detection rate

we combine partial features based on Adaboost with model matching. First

a new way of selecting proper partial feature is shown through analysis and comparison. Then

partial body is used in modeling which shows that model matching is combined in pedestrian detection. At last

experiments indicate that our method achieves a good result in pedestrian detection.