Skip to main navigation Skip to search Skip to main content

Crowd Counting by Adaptively Fusing Predictions from an Image Pyramid

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

Abstract

Because of the powerful learning capability of deep neural networks, counting performance via density map estimation has improved significantly during the past several years. However, it is still very challenging due to severe occlusion, large scale variations, and perspective distortion. Scale variations (from image to image) coupled with perspective distortion (within one image) result in huge scale changes of the object size. Earlier methods based on convolutional neural networks (CNN) typically did not handle this scale variation explicitly, until Hydra-CNN and MCNN. MCNN uses three columns, each with different filter sizes, to extract features at different scales. In this paper, in contrast to using filters of different sizes, we utilize an image pyramid to deal with scale variations. It is more effective and efficient to resize the input fed into the network, as compared to using larger filter sizes. Secondly, we adaptively fuse the predictions from different scales (using adaptively changing per-pixel weights), which makes our method adapt to scale changes within an image. The adaptive fusing is achieved by generating an across-scale attention map, which softly selects a suitable scale for each pixel, followed by a 1x1 convolution. Extensive experiments on three popular datasets show very compelling results.
Original languageEnglish
Title of host publicationBritish Machine Vision Conference 2018, BMVC 2018
PublisherBMVA Press
Publication statusPublished - Sept 2018
Event29th British Machine Vision Conference (BMVC 2018) - Northumbria University, Newcastle, United Kingdom
Duration: 3 Sept 20186 Sept 2018
http://bmvc2018.org/index.html
http://www.bmvc2018.org/programmedetail.html
http://bmvc2018.org/programme/BMVC2018Booklet.pdf

Publication series

NameBritish Machine Vision Conference, BMVC

Conference

Conference29th British Machine Vision Conference (BMVC 2018)
PlaceUnited Kingdom
CityNewcastle
Period3/09/186/09/18
Internet address

Fingerprint

Dive into the research topics of 'Crowd Counting by Adaptively Fusing Predictions from an Image Pyramid'. Together they form a unique fingerprint.

Cite this