Crowd Counting in Low-Resolution Crowded Scenes Using Region-Based Deep Convolutional Neural Networks

IEEE Access

Muhammad Saqib¹  Michael Blumenstein¹  Sultan Daud Khan²  Nabin Sharma³ 

[1] Centre for Artificial Intelligence, Faculty of Engineering and Information Technology, School of Software, University of Technology Sydney, Ultimo, NSW, Australia;University of Hail, Ha&x2019;il, Saudi Arabia;

关键词: Deep convolutional neural networks;    crowd counting and density estimation;    Motion Guided Filter;    faster R-CNN;   

DOI  :  10.1109/ACCESS.2019.2904712

来源: DOAJ

【 摘 要 】

Crowd counting and density estimation is an important and challenging problem in the visual analysis of the crowd. Most of the existing approaches use regression on density maps for the crowd count from a single image. However, these methods cannot localize individual pedestrian and therefore cannot estimate the actual distribution of pedestrians in the environment. On the other hand, detection-based methods detect and localize pedestrians in the scene, but the performance of these methods degrades when applied in high-density situations. To overcome the limitations of pedestrian detectors, we proposed a motion-guided filter (MGF) that exploits spatial and temporal information between consecutive frames of the video to recover missed detections. Our framework is based on the deep convolution neural network (DCNN) for crowd counting in the low-to-medium density videos. We employ various state-of-the-art network architectures, namely, Visual Geometry Group (VGG16), Zeiler and Fergus (ZF), and VGGM in the framework of a region-based DCNN for detecting pedestrians. After pedestrian detection, the proposed motion guided filter is employed. We evaluate the performance of our approach on three publicly available datasets. The experimental results demonstrate the effectiveness of our approach, which significantly improves the performance of the state-of-the-art detectors.

【 授权许可】

Unknown