For the multi-target tracking problems with complex background

a method combing background subtraction with Guassian pyramid on objects detection is presented.The method detects the whole object with taking sample on the objects with Guassian pyramid

building background model

extracting foreground areas with background subtraction

and eliminating the shadow on the foreground.The detection that integrates Gauss model concerning background renewal of calculation

overcomes the error resulted from the sudden change of background.A dynamic threshold concept is proposed to enhance detection effect and thus increase the possibility of implementation.Color model and motion feature is leaded in the method

so the veracity and security is enhanced.The experiment results have showed that the proposed algorithm is robust to the problems of the appearance and disappearance of targets

the cross movement of targets and occlusion.