A saliency weighted no-reference perceptual blur metric for the automotive environment

Winterlich, Anthony; Zlokolica, Vladimir; Denny, Patrick; Kilmartin, Liam; Glavin, Martin; Jones, Edward

doi:10.1109/qomex.2013.6603238

Cited by 10 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural network metrics such as precision, recall, false positive per image and multiple object tracking accuracy were used. Winterlich et al has proposed a weighted metric based on perception saliency to evaluate the linearisation of automotive fisheye camera images [28].…”

Section: Iqa For Automotivementioning

confidence: 99%

Correlating traditional image quality metrics and DNN-based object detection: a case study with compressed camera data

Gummadi,

Chan,

Wang

et al. 2023

Preprint

View full text Add to dashboard Cite

<p> Assisted and automated driving (AAD) systems heavily rely on data collected from perception sensors, such as cameras. While prior research has explored the quality of camera data via traditional and well-established image quality assessment (IQA) metrics (e.g. PSNR, SSIM, BRISQUE) or have considered when noisy/degraded data affects perception algorithms (e.g. deep neural network (DNN) based object detection), there are no works that approach the holistic relationship between IQA and DNN performance. This work proposes that traditional IQA metrics, designed to evaluate digital image quality according to human visual perception, can help to predict the sensor data degradation level that perception algorithms can tolerate before performance deterioration occurs. Consequently, a correlation analysis was conducted between 17 selected IQA metrics (with and without reference) and DNN average precision. The evaluated data was increasingly compressed to generate degradation and artefacts. Notably, the experimental results show that several IQA metrics had a strong positive correlation (exceeding correlation scores of 0.7) with average precision, with IW-SSIM and DSS having very high correlation (> 0.9). Interestingly, the results show that re-training BRISQUE on compressed data causes an exceptionally high positive correlation (> 0.97), making it very suitable for predicting the performance of DNN object detectors. By effectively relating traditional image quality metrics to DNN performance, this research offers a series of significant tools to understand and predict perception degradation based on the quality of data, thus resulting in a significant impact on the development of automated driving systems. </p>

show abstract

Section: Iqa For Automotivementioning

confidence: 99%

Correlating traditional image quality metrics and DNN-based object detection: a case study with compressed camera data

Gummadi,

Chan,

Wang

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Development of compression algorithms for multimedia content has driven many of the developments in defining and measuring perceptual image and video quality. In the automotive space, what “good quality” means is not so straightforward, with no single clear definition available [ 4 , 5 ]. This is compounded by the fact that video is necessary for two distinct applications: display to the driver (e.g., rear view and multi-camera surround view monitoring) and computer vision for advanced driver assistance systems.…”

Section: Introductionmentioning

confidence: 99%

“…These borrowed from traditional feature detection or work on image compression metrics [ 15 , 16 ]. These included Universal Quality Index [ 17 ] and Structured Similarity (SSIM) [ 18 ], MS-SSIM [ 19 ], IFC [ 20 ], VIF [ 21 ], VSNR [ 22 ], FSIM [ 23 ] and salience weighted quality metrics [ 5 ]. “No-reference” techniques, which exclude the need for non-aberrant reference images when assessing the images are more desirable in real-time systems, but suffer from many of the same issues as reference techniques, which frustrate generalization of the interpretation of a metric’s measurement.…”

Section: Introductionmentioning

confidence: 99%

“…In order to reduce or eliminate contributions from potentially confounding variables, classical visual psychophysical tests are deliberately set up to provide very constrained test environments [ 26 , 27 ] and attempts at more general automated visual psychophysical measurements are similarly highly artificially constrained and even then correlate poorly [ 28 ]. This, however, is the opposite of the general expectations of automotive imaging systems, which experience the greatest diversity of scene content of any imaging application, and automatic methods which leverage anticipated salience of objects to an observer in an automotive scene must be considered [ 5 , 29 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Overview and Empirical Analysis of ISP Parameter Tuning for Visual Perception in Autonomous Driving

et al. 2019

Self Cite

View full text Add to dashboard Cite

Image quality is a well understood concept for human viewing applications, particularly in the multimedia space, but increasingly in an automotive context as well. The rise in prominence of autonomous driving and computer vision brings to the fore research in the area of the impact of image quality in camera perception for tasks such as recognition, localization and reconstruction. While the definition of “image quality” for computer vision may be ill-defined, what is clear is that the configuration of the image signal processing pipeline is the key factor in controlling the image quality for computer vision. This paper is partly review and partly positional with demonstration of several preliminary results promising for future research. As such, we give an overview of what is an

show abstract

Imaging for the Automotive Environment

Denny¹,

Jones²,

Glavin³

et al. 2016

Handbook of Visual Display Technology

View full text Add to dashboard Cite

A saliency weighted no-reference perceptual blur metric for the automotive environment

Cited by 10 publications

References 20 publications

Correlating traditional image quality metrics and DNN-based object detection: a case study with compressed camera data

Correlating traditional image quality metrics and DNN-based object detection: a case study with compressed camera data

Overview and Empirical Analysis of ISP Parameter Tuning for Visual Perception in Autonomous Driving

Imaging for the Automotive Environment

Contact Info

Product

Resources

About