The influence of camera shakes, harmful occlusions and camera misalignment on the perceived quality in user generated video

Abstract

Video sharing sites such as Youtube are prominent examples for the increasing demand of private camera owners to record, save and share their real life experiences as videos. Whereas professional video productions use advanced camera equipment in a controlled environment with skilled cameramen, User-Generated Video (UGV) differs significantly in regard of equipment, skill and thus in video quality. In this work we focus on a detailed analysis of the effects of camera shakes, harmful occlusions as well as a possible misalignment between the recording camera and the scene, on the resulting video quality. In contrast, most of the video quality discussion in the literature has focused on encoding artifacts and other compression problems. Our data was systematically gathered using large crowdsourcing experiments over three genres of video, and it was validated in a controlled lab setting. Our results show that even minimal camera shaking as well as occlusions lead to a significant reduction in the perceived video quality.

Monitoring of User Generated Video Broadcasting Services

“…Based on this data, the detection of user behavior that leads to degraded video quality, such as camera shaking or wrong orientation of the phone, can also be observed directly on the users' device without analyzing (or transmitting) the video data itself [5]. In previous work [10], we found that degradations such as camera shakes have a huge impact on the QoE.…”

Mobile Video Broadcasting Services

“…The resulting quality of a video stream should not only integrate the effects of video compression artifacts and map their impact to a Mean Opinion Score (M OS V ideo ) but adds the impact of recording degradations. First results illustrate that recording degradations have a significant impact on the perceived quality and that the impact differs for different video genres [10]. Identified degradations include camera shakes, occlusions or camera misalignments.…”

EnvDASH

“…The MOS represents the subjective video quality ranging from 1 (bad quality) to 5 (excellent quality). Based on our previous work [18] we define the MOS function as M OS = a 0 + a ampl * x 1 + a dur * x 2 + a speed * x 3 . In this model x 1 is the amplitude of a measured device shaking, x 2 represents the duration of the current shaking and x 3 the velocity of the shaking.…”