Aiming at the problem of low efficiency and poor real-time performance of pedestrian detection algorithm in embedded platform

a fast pedestrian detection system based on digital signal processor（DSP） is designed in this work.Firstly

the compatibility problem of Open CV on the DSP platform is solved by modification.Then

the pedestrian detection algorithm by combining a background model based on vibe and histogram of oriented gradient（HOG） plus support vector machine（SVM） is transplanted to the embedded DSP platform.Finally

various optimization techniques are used to optimize the program.The experimental results show that the detection system can effectively detect pedestrians on the embedded TMS320 C6657 DSP platform

and improve the detection speed through optimization.