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

Video object segmentation is a fundamental step in many advanced visionapplications. Most existing algorithms are based on handcrafted features suchas HOG, super-pixel segmentation or texture-based techniques, while recentlydeep features have been found to be more efficient. Existing algorithms observeperformance degradation in the presence of challenges such as illuminationvariations, shadows, and color camouflage. To handle these challenges wepropose a fusion based moving object segmentation algorithm which exploitscolor as well as depth information using GAN to achieve more accuracy. Our goalis to segment moving objects in the presence of challenging background scenes,in real environments. To address this problem, GAN is trained in anunsupervised manner on color and depth information independently withchallenging video sequences. During testing, the trained GAN generatesbackgrounds similar to that in the test sample. The generated backgroundsamples are then compared with the test sample to segment moving objects. Thefinal result is computed by fusion of object boundaries in both modalities, RGBand the depth. The comparison of our proposed algorithm with fivestate-of-the-art methods on publicly available dataset has shown the strengthof our algorithm for moving object segmentation in videos in the presence ofchallenging real scenarios.

Unsupervised RGBD Video Object Segmentation Using GANs