Pushing the Frontiers of Unconstrained Crowd Counting: New Dataset and Benchmark Method

TL;DR

This paper introduces a new crowd counting network that progressively refines density maps using residual error estimation guided by uncertainty, and presents a large, diverse new dataset for benchmarking.

Contribution

The paper proposes the CG-DRCN network with residual error refinement and uncertainty guidance, and introduces the large-scale JHU-CROWD dataset for unconstrained crowd counting.

Findings

CG-DRCN achieves significant error reduction on complex datasets.

JHU-CROWD dataset is 2.8 times larger and more diverse than existing datasets.

Recent methods evaluated on the new dataset demonstrate its challenging nature.

Abstract

In this work, we propose a novel crowd counting network that progressively generates crowd density maps via residual error estimation. The proposed method uses VGG16 as the backbone network and employs density map generated by the final layer as a coarse prediction to refine and generate finer density maps in a progressive fashion using residual learning. Additionally, the residual learning is guided by an uncertainty-based confidence weighting mechanism that permits the flow of only high-confidence residuals in the refinement path. The proposed Confidence Guided Deep Residual Counting Network (CG-DRCN) is evaluated on recent complex datasets, and it achieves significant improvements in errors. Furthermore, we introduce a new large scale unconstrained crowd counting dataset (JHU-CROWD) that is ~2.8 larger than the most recent crowd counting datasets in terms of the number of images. It contains 4,250 images with 1.11 million annotations. In comparison to existing datasets, the proposed dataset is collected under a variety of diverse scenarios and environmental conditions. Specifically, the dataset includes several images with weather-based degradations and illumination variations in addition to many distractor images, making it a very challenging dataset. Additionally, the dataset consists of rich annotations at both image-level and head-level. Several recent methods are evaluated and compared on this dataset.