Plug-and-Play Rescaling Based Crowd Counting in Static Images
This addresses crowd counting for surveillance and public safety, but it is incremental as it builds on existing methods with a new module.
The paper tackles the problem of inaccurate crowd counting in static images due to diverse crowds and cluttered backgrounds by proposing a plug-and-play image patch rescaling module, which improves state-of-the-art models by up to 10.4% in RMSE on benchmarks and shows better generalization.
Crowd counting is a challenging problem especially in the presence of huge crowd diversity across images and complex cluttered crowd-like background regions, where most previous approaches do not generalize well and consequently produce either huge crowd underestimation or overestimation. To address these challenges, we propose a new image patch rescaling module (PRM) and three independent PRM employed crowd counting methods. The proposed frameworks use the PRM module to rescale the image regions (patches) that require special treatment, whereas the classification process helps in recognizing and discarding any cluttered crowd-like background regions which may result in overestimation. Experiments on three standard benchmarks and cross-dataset evaluation show that our approach outperforms the state-of-the-art models in the RMSE evaluation metric with an improvement up to 10.4%, and possesses superior generalization ability to new datasets.