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

Due to the deteriorated conditions of \mbox{illumination} lack and unevenlighting, nighttime images have lower contrast and higher noise than theirdaytime counterparts of the same scene, which limits seriously the performancesof conventional background modeling methods. For such a challenging problem ofbackground modeling under nighttime scene, an innovative and reasonablesolution is proposed in this paper, which paves a new way completely differentfrom the existing ones. To make background modeling under nighttime sceneperforms as well as in daytime condition, we put forward a promisinggeneration-based background modeling framework for foreground surveillance.With a pre-specified daytime reference image as background frame, the{\bfseries GAN} based generation model, called {\bfseries N2DGAN}, is trainedto transfer each frame of {\bfseries n}ighttime video {\bfseries to} a virtual{\bfseries d}aytime image with the same scene to the reference image except forthe foreground region. Specifically, to balance the preservation of backgroundscene and the foreground object(s) in generating the virtual daytime image, wepresent a two-pathway generation model, in which the global and localsub-networks are well combined with spatial and temporal consistencyconstraints. For the sequence of generated virtual daytime images, amulti-scale Bayes model is further proposed to characterize pertinently thetemporal variation of background. We evaluate on collected datasets withmanually labeled ground truth, which provides a valuable resource for relatedresearch community. The impressive results illustrated in both the main paperand supplementary show efficacy of our proposed approach.

To See in the Dark: N2DGAN for Background Modeling in Nighttime Scene