No-reference hybrid video quality assessment based on partial least squares regression

Abstract

Constructing objective assessment model on visual quality is challenging, since it associates closely with many factors in human visual perception, as well as both source coding and transmission. In this paper, a no reference hybrid model for video quality assessment is proposed by employing Partial Least Squares Regression (PLSR). The hybrid model combines both bitstream-based features and network-based features, taking into video quality dependence on visual content and network conditions account. We have conducted subjective tests to validate its quality assessment accuracy. Simulation results in Network Simulator version 2 (NS-2) verify the performance advantage of the hybrid model for SD (standard definition) and HD (high definition) video sequences. Proposed model could be used as a quality monitoring tool for assessing the real-time video quality during wireless transmission. Simulation results show that the devised model can improve the quality prediction against a full-reference metric, and achieves a high correlation (0.955) between quality prediction and the actual perceived quality judged by subjective assessment.

Impact of video content and transmission impairments on quality of experience

“…The selection and consideration of the key quality influencing artifacts is an important step towards the robust video/image quality metric/QoE model design [40][41][42]. In this context, the resource scheduling algorithm may be adapted based on the impact of transmission impairments on the perceived quality.…”

Energy Efficient and QoS Aware Framework for Video Transmission over Wireless Sensor Networks

“…There is a continuous feedback messages sent from Sink node to source nodes, to propagate back both recommended video encoding parameters and calculated path cost. Received video will be analyzed at sink node [13] and could be analyzed using PLSR (Partial Least Squares Regression) [29] or other video quality assessment techniques (such as VQM, MS-SSIM, …) [30] [31], so that, the optimum MPEG-4 encoding parameters optimized for current wireless channel state is communicated back to source nodes. Source node will configure MPEG-4 encoder using new video encoding parameters sent from sink, in addition, source node will select suitable path at time of sending new video packet according to current packet type and communicated path cost from sink node.…”

Image quality assessment using edge based features

“…According to either availability or no-availability of an original image, objective IQA techniques can be divided into three groups, full-reference, non-reference, and reduced-reference [22,33,36,40,41].…”

“…For example, in digital photography, a non-reference assessment algorithm is used in order to inform the user that a low or high quality photo has been taken. It is easy for HVS to determine the visual quality of an image without any reference, but it is far more difficult to design a system that performs the same [15,32,36,[42][43][44].…”