A Deeply-Recursive Convolutional Network for Crowd Counting
This addresses the issue of high storage and computing resource requirements in CNN-based crowd counting methods, which is important for real-world applications like video surveillance and public safety, but it is incremental as it builds on existing ResNet architectures.
The authors tackled the problem of crowd counting in images by proposing a deeply-recursive network (DR-ResNet) based on ResNet blocks, which reduces parameters and storage while maintaining performance, achieving state-of-the-art results with far fewer parameters.
The estimation of crowd count in images has a wide range of applications such as video surveillance, traffic monitoring, public safety and urban planning. Recently, the convolutional neural network (CNN) based approaches have been shown to be more effective in crowd counting than traditional methods that use handcrafted features. However, the existing CNN-based methods still suffer from large number of parameters and large storage space, which require high storage and computing resources and thus limit the real-world application. Consequently, we propose a deeply-recursive network (DR-ResNet) based on ResNet blocks for crowd counting. The recursive structure makes the network deeper while keeping the number of parameters unchanged, which enhances network capability to capture statistical regularities in the context of the crowd. Besides, we generate a new dataset from the video-monitoring data of Beijing bus station. Experimental results have demonstrated that proposed method outperforms most state-of-the-art methods with far less number of parameters.