This paper proposes a pedestrian detection algorithm to which ROI was applied to implement pedestrian detection that is suitable for the embedded environment. Pedestrian detection has computations for unnecessary areas because the entire input images are computed to find pedestrians in the given images. In this paper, a pedestrian detection algorithm that is ideal for the embedded environment is proposed which reduced computations for unnecessary areas by applying ROI. The CENTIRST descriptor method was used for the pedestrian detection algorithm, which was implemented using 512×360 pixel images on an ALDEBARAN board. The proposed pedestrian detection with ROI showed a 16% improved performance of 3.6 frames per second compared to the conventional method.