A Real-Time Deep Network for Crowd Counting
This work addresses the need for fast and efficient crowd counting in real-world scenarios, though it appears incremental as it builds on prior methods to improve speed.
The paper tackles the problem of real-time crowd counting by proposing a compact convolutional neural network that achieves nearly real-time speed while maintaining accuracy, with experiments showing it balances performance and efficiency better than existing light-weight models.
Automatic analysis of highly crowded people has attracted extensive attention from computer vision research. Previous approaches for crowd counting have already achieved promising performance across various benchmarks. However, to deal with the real situation, we hope the model run as fast as possible while keeping accuracy. In this paper, we propose a compact convolutional neural network for crowd counting which learns a more efficient model with a small number of parameters. With three parallel filters executing the convolutional operation on the input image simultaneously at the front of the network, our model could achieve nearly real-time speed and save more computing resources. Experiments on two benchmarks show that our proposed method not only takes a balance between performance and efficiency which is more suitable for actual scenes but also is superior to existing light-weight models in speed.