Auto-Zooming CNN-Based Framework for Real-Time Pedestrian Detection in Outdoor Surveillance Videos

One of the challenges faced by surveillance video analysis is to detect objects from the frames. For outdoor surveillance, detection of small object like pedestrian is of particular interest. This paper proposes a fast, lightweight, and auto-zooming-based framework for small pedestrian detection. An attentive virtual auto-zooming scheme is proposed to adaptively zoom-in the input frame by splitting it into non-overlapped tiles and pay attention to the only important tiles. Without sacrificing detection performance, we have obtained a fully convolutional pedestrian detection model which can be run on low computational resources. It has been trained on an outdoor surveillance dataset and evaluated on two specially prepared testing sets of small (far) pedestrians in outdoor surveillance. We have compared our framework performance with different single-step customized pedestrian detectors as well as the two-step detector faster R-CNN. The results validate the efficiency of our framework.