Adaptive superpixel-based multi-object pedestrian recognition

This paper proposed an adaptive multi-object pedestrian recognition algorithm based on SLIC. First, we used SLIC to superpixel the pre-segmentation processing on the image. Then, the hash distance is added as the superpixel point aggregation parameter based on the traditional superpixel measurement unit of LAB color space distance and position distance. Finally, we identified the clustering subject by using the extreme learning machine neural network. The proposed method can adaptively determine the number of superpixels to achieve high recognition performance. This method simply needs to preset the number of pre-segments, which can reduce the number of detection targets, improve the segmentation efficiency, and shorten the image identification time.