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

Effective fusion of complementary information captured by multi-modal sensors(visible and infrared cameras) enables robust pedestrian detection undervarious surveillance situations (e.g. daytime and nighttime). In this paper, wepresent a novel box-level segmentation supervised learning framework foraccurate and real-time multispectral pedestrian detection by incorporatingfeatures extracted in visible and infrared channels. Specifically, our methodtakes pairs of aligned visible and infrared images with easily obtainedbounding box annotations as input and estimates accurate prediction maps tohighlight the existence of pedestrians. It offers two major advantages over theexisting anchor box based multispectral detection methods. Firstly, itovercomes the hyperparameter setting problem occurred during the training phaseof anchor box based detectors and can obtain more accurate detection results,especially for small and occluded pedestrian instances. Secondly, it is capableof generating accurate detection results using small-size input images, leadingto improvement of computational efficiency for real-time autonomous drivingapplications. Experimental results on KAIST multispectral dataset show that ourproposed method outperforms state-of-the-art approaches in terms of bothaccuracy and speed.

Box-level Segmentation Supervised Deep Neural Networks for Accurate and Real-time Multispectral Pedestrian Detection