Subjective video quality assessment methods for recognition tasks

Video transmission and analysis is often utilized in applications outside of the entertainment sector, and generally speaking this class of video is used to perform specific tasks. Examples of these applications include security and public safety. The Quality of Experience (QoE) concept for video content used for entertainment differs significantly from the QoE of surveillance video used for recognition tasks. This is because, in the latter case, the subjective satisfaction of the user depends on achieving a given functionality. Recognizing the growing importance of video in delivering a range of public safety services, we focused on developing critical quality thresholds in license plate recognition tasks based on videos streamed in constrained networking conditions. Since the number of surveillance cameras is still growing it is obvious that automatic systems will be used to do the tasks. Therefore, the presented research includes also analysis of automatic recognition algorithms.

show abstract

“…Usually, classical quality models, like the PSNR [10] or SSIM [26], were applied. Other approaches are just emerging [12,13,25].…”

Section: Introductionmentioning

confidence: 99%

Quality assessment for a visual and automatic license plate recognition

Janowski

Kozłowski

Baran

et al. 2012

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…For instance, people working in the public safety sector (e.g., law enforcement, fire control, and emergency services) use natural imaging systems in real-time scenarios to make immediate decisions about how best to respond to an incident [2,3]. In another example, investigators not only examine recordings obtained with video surveillance systems, but also introduce such recordings as evidence for criminal investigations [4][5][6].…”

Section: Introductionmentioning

confidence: 99%

Estimating the usefulness of distorted natural images using an image contour degradation measure

et al. 2011

View full text Add to dashboard Cite

Quality estimators aspire to quantify the perceptual resemblance, but not the usefulness, of a distorted image when compared to a reference natural image. However, humans can successfully accomplish tasks (e.g., object identification) using visibly distorted images that are not necessarily of high quality. A suite of novel subjective experiments reveals that quality does not accurately predict utility (i.e., usefulness). Thus, even accurate quality estimators cannot accurately estimate utility. In the absence of utility estimators, leading quality estimators are assessed as both quality and utility estimators and dismantled to understand those image characteristics that distinguish utility from quality. A newly proposed utility estimator demonstrates that a measure of contour degradation is sufficient to accurately estimate utility and is argued to be compatible with shape-based theories of object perception.

show abstract