Accurate Gigapixel Crowd Counting by Iterative Zooming and Refinement

by   Arian Bakhtiarnia, et al.

The increasing prevalence of gigapixel resolutions has presented new challenges for crowd counting. Such resolutions are far beyond the memory and computation limits of current GPUs, and available deep neural network architectures and training procedures are not designed for such massive inputs. Although several methods have been proposed to address these challenges, they are either limited to downsampling the input image to a small size, or borrowing from other gigapixel tasks, which are not tailored for crowd counting. In this paper, we propose a novel method called GigaZoom, which iteratively zooms into the densest areas of the image and refines coarser density maps with finer details. Through experiments, we show that GigaZoom obtains the state-of-the-art for gigapixel crowd counting and improves the accuracy of the next best method by 42


page 3

page 4


Leveraging Unlabeled Data for Crowd Counting by Learning to Rank

We propose a novel crowd counting approach that leverages abundantly ava...

Plug-and-Play Rescaling Based Crowd Counting in Static Images

Crowd counting is a challenging problem especially in the presence of hu...

CCCNet: An Attention Based Deep Learning Framework for Categorized Crowd Counting

Crowd counting problem that counts the number of people in an image has ...

Backdoor Attacks on Crowd Counting

Crowd counting is a regression task that estimates the number of people ...

Crowd Counting using Deep Recurrent Spatial-Aware Network

Crowd counting from unconstrained scene images is a crucial task in many...

Revisiting Crowd Counting: State-of-the-art, Trends, and Future Perspectives

Crowd counting is an effective tool for situational awareness in public ...

Please sign up or login with your details

Forgot password? Click here to reset