English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

In this paper, we propose two modified neural networks based on dual pathmulti-scale fusion networks (SFANet) and SegNet for accurate and efficientcrowd counting. Inspired by SFANet, the first model, which is named M-SFANet,is attached with atrous spatial pyramid pooling (ASPP) and context-aware module(CAN). The encoder of M-SFANet is enhanced with ASPP containing parallel atrousconvolutional layers with different sampling rates and hence able to extractmulti-scale features of the target object and incorporate larger context. Tofurther deal with scale variation throughout an input image, we leverage theCAN module which adaptively encodes the scales of the contextual information.The combination yields an effective model for counting in both dense and sparsecrowd scenes. Based on the SFANet decoder structure, M-SFANet's decoder hasdual paths, for density map and attention map generation. The second model iscalled M-SegNet, which is produced by replacing the bilinear upsampling inSFANet with max unpooling that is used in SegNet. This change provides a fastermodel while providing competitive counting performance. Designed for high-speedsurveillance applications, M-SegNet has no additional multi-scale-aware modulein order to not increase the complexity. Both models are encoder-decoder basedarchitectures and are end-to-end trainable. We conduct extensive experiments onfive crowd counting datasets and one vehicle counting dataset to show thatthese modifications yield algorithms that could improve state-of-the-art crowdcounting methods. Codes are available athttps://github.com/Pongpisit-Thanasutives/Variations-of-SFANet-for-Crowd-Counting.

Encoder-Decoder Based Convolutional Neural Networks with Multi-Scale-Aware Modules for Crowd Counting