Multi-source Multi-scale Counting in Extremely Dense Crowd Images

We propose to leverage multiple sources of information to compute an estimate of the number of individuals present in an extremely dense crowd visible in a single image. Due to problems including perspective, occlusion, clutter, and few pixels per person, counting by human detection in such images is almost impossible. Instead, our approach relies on multiple sources such as low confidence head detections, repetition of texture elements (using SIFT), and frequency-domain analysis to estimate counts, along with confidence associated with observing individuals, in an image region. Secondly, we employ a global consistency constraint on counts using Markov Random Field. This caters for disparity in counts in local neighborhoods and across scales. We tested our approach on a new dataset of fifty crowd images containing 64K annotated humans, with the head counts ranging from 94 to 4543. This is in stark contrast to datasets used for existing methods which contain not more than tens of individuals. We experimentally demonstrate the efficacy and reliability of the proposed approach by quantifying the counting performance.

PDF Abstract

Datasets


Introduced in the Paper:

UCF-CC-50

Used in the Paper:

UCF-QNRF

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Crowd Counting UCF CC 50 Idrees et al. MAE 419.5 # 21

Results from Other Papers


Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Crowd Counting UCF-QNRF Idrees et al. MAE 315 # 22

Methods


No methods listed for this paper. Add relevant methods here