GhostCount: A lightweight convolution network based on high‐altitude video for vehicle instantaneous counting in dense traffic scenes

• Published in: IET intelligent transport systems 2023-05, Vol.17 (5), p.943-959
• Main Authors: Cao, Qianxia, Shan, Zhenyu, Long, Kejun, Wang, Zhengwu
• Format: Article
• Language: English
• Subjects: computer vision; convolutional neural nets; edge detection; intelligent transportation systems; road traffic
• ISSN: 1751-956X; 1751-9578
• DOI: 10.1049/itr2.12318

Instantaneous vehicle counting of traffic scenes based on high‐altitude video is an important way for real‐time traffic information collection in intelligent transportation systems (ITS). However, vehicle counts based on high‐altitude video are susceptible to problems such as denseness, occlusion and small size. The mainstream method is to use a Convolutional Neural Network (CNN) to output density maps and obtain vehicle count results. However, most CNNs are computationally expensive and have poor real‐time performance. Therefore, we propose a lightweight CNN named GhostCount, specially designed for high‐accuracy vehicle counts on edge devices. First, we combine ResNet‐18 and Lightweight RefineNet to build an encoder–decoder network architecture to effectively extract vehicle features in complex traffic scenes. Next, we replace the ordinary convolutional layers in ResNet‐18 with Ghost modules to lighten the network. Finally, a binary cross‐entropy loss function is introduced to suppress background noise. We demonstrate GhostCount on public datasets (TRANCOS, CARPK, PUCPR+) and our self‐built dataset (CSCAR). Results show that GhostCount can perform instantaneous vehicle counting with higher accuracy and faster inference speed than other representative lightweight CNNs. The method we propose would provide new solutions and ideas for ITS applications such as traffic information collection and smart parking management. To implement instantaneous vehicle counting based on high‐altitude video, we propose a lightweight convolutional neural network model and build an ultra‐small target vehicle dataset. Experimental results show that our model has excellent accuracy and can be run on edge devices.