Automatic Detection of 3D Quality Defects in Stereoscopic Videos Using Binocular Disparity

ABSTRACT:

3D video quality issues that may disturb the human visual system and negatively impact the 3D viewing experience are well known and become more relevant as the availability of 3D video content increases, primarily through 3D cinema, but also through 3D television. In this paper, we propose four algorithms that exploit available stereo disparity information, in order to detect disturbing stereoscopic effects, namely stereoscopic window violations (SWV), bent window effects, UFO objects and depth jump cuts on stereo videos. After detecting such issues, the proposed algorithms characterize them, based on the stress they cause to the viewer’s visual system. Qualitative representative examples, quantitative experimental results on a custom-made video dataset, a parameter sensitivity study and comments on the computational complexity of the algorithms are provided, in order to assess the accuracy and performance of stereoscopic quality defect detection.

EXISTING SYSTEM:

• In 3DTV and 3D cinema, the stereo-pairs are typically processed in post-production, to allow a perceived placement of imaged objects, during video display, both in front of and behind the screen plane. Therefore, the disparity maps estimated from post-processed 3DTV content typically contain both positive and negative disparity values. Pixels associated with negative left disparity are to be displayed in front of the screen, pixels with positive left disparity are to be displayed behind the screen and pixels with zero disparity will be displayed on the screen plane itself.

• The disparity estimation algorithms can be classified into two main groups, namely local and global methods.

• Local algorithms use local neighbourhood information for matching windows, one in each stereo image channel. They generally give less accurate results than global ones, but are significantly faster, due to their reduced computational complexity.

• Global methods are iterative algorithms, which typically try to minimize a global energy function. They often produce quite good disparity maps, though at high computational complexity.

• Several assistance systems have been proposed for stereo video shooting and 3DTV production. The stereoscopic analyzer (STAN) developed by HHI detects stereoscopic window violation and gives a framing alert, by keeping track of several features present in both the left and right stereo image.

DISADVANTAGES OF EXISTING SYSTEM:

• In the existing system though it works in real-time, is of limited accuracy, as it involves sparse disparity maps and needs special hardware.

• Detection of stereoscopic window violations (referred to as framing violations) was proposed as a possible extension of the computational stereo camera system. However, such an algorithm was neither implemented, nor tested.

• The existing processes are manual and, thus, need the presence of an operator.

PROPOSED SYSTEM:

• In this paper, we propose algorithms that exploit the available stereo disparity information, in order to detect stereoscopic quality issues in videos, so that they can be fixed in a post-processing stage. Particularly, we deal with the detection of the stereoscopic window violations (SWV), bent window effects, UFO objects and depth jump cuts. Moreover, the proposed algorithms try to characterize the detected effects, according to the visual stress they cause to the viewer.

• In this paper, we propose four algorithms that exploit available stereo disparity information, in order to detect disturbing stereoscopic effects, namely stereoscopic window violations (SWV), bent window effects, UFO objects and depth jump cuts on stereo videos.

ADVANTAGES OF PROPOSED SYSTEM:

• The algorithms also try to characterize these stereoscopic effects according to the stress they cause to the viewer.

• Representative qualitative examples, quantitative experimental results on a custom-made video dataset, a parameter sensitivity study and comments on the computational complexity of the algorithms are provided, proving effectiveness of the proposed methods in detecting the four above mentioned stereo quality defects.

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

• System           : Pentium Dual Core.

• Hard Disk      : 120 GB.

• Monitor          : 15’’ LED

• Input Devices : Keyboard, Mouse

• Ram                : 1GB.

SOFTWARE REQUIREMENTS:

• Operating system : Windows 7.

• Coding Language : MATLAB

• Tool                       : MATLAB R2013A

REFERENCE:

Sotirios Delis, Ioannis Mademlis, Nikos Nikolaidis, Ioannis Pitas, “Automatic Detection of 3D Quality Defects in Stereoscopic Videos Using Binocular Disparity”, IEEE Transactions on Circuits and Systems for Video Technology, 2017