Need for Human Detection
People counting techniques have been applied in many public places with entrances, such as supermarkets, subways and libraries. The people flow data of these scenes can supply useful information for public security, marketing decision and resource allocation. With the increasing requirements for automatic people counting systems based on digital image processing and computer vision, effective people counting methods become remarkable and meaningful.
ModelsMany studies on people counting have been done. Charoenpong introduced a head detection method by using partial head contour, and they used the eclipse model to fit the contour. Zhao et al. utilized the hair-color and head contour features to detect human heads. It is known that human heads have an approximate circular shape, so the contour template is commonly used in head detection. But the contour template based method is often influenced by other objects similar to human heads in scenes. Mukherjee et al. proposed an effective passenger counting method, which first uses Hough circle transform to detect human heads, and then performs head tracking using the optical flow method. However, the tracking method based on the optical flow requires a large amount of calculation.
|