Spatiotemporal saliency detection and salient region determination for H.264 videos

Hu, Kang-Ting; Leou, Jin-Jang; Hsiao, Han-Hui

doi:10.1016/j.jvcir.2013.05.001

Cited by 12 publications

(7 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The visual Attention is based on Information Maximization (AIM) [15]. In Figure 3 visual attention region has shown which we achieved by employing the AIM-based method to the frame of "Container" video.…”

Section: Visual Attention Regionmentioning

confidence: 99%

A Hybrid Video Watermarking Technique based on DWT, SVD and SCHUR Decomposition

Adhikari¹,

Sing²

2018

IJCA

View full text Add to dashboard Cite

Video watermarking is a technique that used to protect the multimedia data, video in reference to authentication, proof of ownership, copy control etc. In this paper a robust video watermarking scheme is proposed that will protect videos from being unauthorized manipulation by the intruder. A hybrid transform technique consists of Discrete Wavelet Transform (DWT), Schur decomposition, Singular Value Decomposition (SVD) and a visual attention region determination scheme is used to determine the region of interest and region of non interest blocks of video frames. To make the scheme robust, watermark is embedded in the region of non interest blocks of HL band of the frame. The robustness against various attacks has been compared with high Normalized Cross Correlation (NCC) values and the imperceptibility of the watermarked image with the original cover image has been compared with indicated high achievable Peak Signal to Noise Ratio (PSNR) values. The experimental results show that the proposed method has achieved a satisfactory performance against various notable attacks. General TermsVideo watermarking

show abstract

Section: Visual Attention Regionmentioning

confidence: 99%

A Hybrid Video Watermarking Technique based on DWT, SVD and SCHUR Decomposition

Adhikari¹,

Sing²

2018

IJCA

View full text Add to dashboard Cite

show abstract

“…Based on the binary salient object mask SP and the corresponding binary ground truth,GT three objective evaluation metrics, namely, precision, recall and F-measure are employed [34], respectively, as:…”

Section: Tablementioning

confidence: 99%

Saliency detection using mutual consistency-guided spatial cues combination

Wang

Chen

2015

Infrared Physics & Technology

View full text Add to dashboard Cite

“…Additionally, spatial and temporal features are not restricted to the pixel domain, for instance, the phase spectrum of Fourier transform is used to detect spatial saliency. Similarly, phase spectrum of Fourier transform can be used to obtain the temporal saliency map of each video frame using motion vector information [5]. Likewise, local centersurround differences and global contrast can also be computed using wavelet-domain features [6].…”

Section: Introductionmentioning

confidence: 99%