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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Pedestrian detection methods have been significantly improved with thedevelopment of deep convolutional neural networks. Nevertheless, detectingsmall-scaled pedestrians and occluded pedestrians remains a challengingproblem. In this paper, we propose a pedestrian detection method with acouple-network to simultaneously address these two issues. One of thesub-networks, the gated multi-layer feature extraction sub-network, aims toadaptively generate discriminative features for pedestrian candidates in orderto robustly detect pedestrians with large variations on scales. The secondsub-network targets in handling the occlusion problem of pedestrian detectionby using deformable regional RoI-pooling. We investigate two different gateunits for the gated sub-network, namely, the channel-wise gate unit and thespatio-wise gate unit, which can enhance the representation ability of theregional convolutional features among the channel dimensions or across thespatial domain, repetitively. Ablation studies have validated the effectivenessof both the proposed gated multi-layer feature extraction sub-network and thedeformable occlusion handling sub-network. With the coupled framework, ourproposed pedestrian detector achieves state-of-the-art results on the Caltechand the CityPersons pedestrian detection benchmarks.

Coupled Network for Robust Pedestrian Detection with Gated Multi-Layer Feature Extraction and Deformable Occlusion Handling