Cornelia Denk

BRDF Representation and Acquisition

Photorealistic rendering of real world environments is important in a range of different areas; including Visual Special effects, Interior/Exterior Modelling, Architectural Modelling, Cultural Heritage, Computer Games and Automotive Design.

Driver Drowsiness Detection Based on Novel Eye Openness Recognition Method and Unsupervised Feature Learning

In this paper, we proposed a driver drowsiness detection method for which only eyelid movement information was required. The proposed method consists of two major parts. 1) In order to obtain accurate eye openness estimation, a vision based eye openness recognition method was proposed to obtain an regression model that directly gave degree of eye openness from a low-resolution eye image without complex geometry modeling, which is efficient and robust to degraded image quality. 2) A novel feature extraction method based on unsupervised learning was also proposed to reveal hidden pattern from eyelid movements as well as reduce the feature dimension. The proposed method was evaluated and shown good performance.

Cluster Regularized Extreme Learning Machine for Detecting Mixed-Type Distraction in Driving

Distraction was previously studied within each dimension separately, i.e., physical, cognitive and visual. However real-world activities usually involve multiple distraction dimensions in terms of brain resources that might conflict with the driving task. This brings difficulties for classifying dimension/type of distraction even for human experts. On the other hand, many subsequent functional blocks do not utilize distraction type information. For example, a pre-collision system usually makes decision based on distraction level rather than distraction type. Therefore this study aims to detect distraction in general regardless of its type, and proposes an effective machine learning algorithm, i.e., Cluster Regularized Extreme Learning Machine (CR-ELM), to detect mixed-type distraction in driving. Compared to traditional machine learning techniques, CR-ELM is designed to handle problems with multiple clusters per class, and provides more accurate detection performance, which could be used for advanced driver assistance systems.

Grand challenges: material models in automotive

Material reflectance definitions are core to high fidelity visual simulation of objects within a compelling 3D scene. In the automotive industry these are used across the entire business process: from conceptualisation of a new product range, through to the final sale. However, current state-of-the-art of material representations leave much to be desired for fast and practical deployment in the industry. Even after decades of research and development, there are no interoperable standards for material models to facilitate exchange between applications. A large discrepancy also exists between the quality of material models used (and indeed the quality at which they can be displayed) across the spectrum of use-cases within the industry. Focussing on the needs of the Automotive Industry, in this position paper, we summarise the main issues that limit the effective use of material models. Furthermore, we outline specific solutions we believe could be investigated in order to address this problem. This paper is the result of a review conducted in conjunction with several key players in the automotive field.

Machine Learning Reveals Different Brain Activities in Visual Pathway during TOVA Test

This paper explores the changes in EEG when subjects performed a modified Test of Variables of Attention (TOVA), compared to open eye resting (baseline) state. To recognize these two different brain states, two machine learning algorithms, i.e. extreme learning machine (ELM) and support vector machine (SVM), were applied and compared, using 3 statistical features and 4 power spectral density per channel. The results showed that using all 14 channels, ELM and SVM achieved similar test accuracy of 94.6% and 95.1% respectively (McNemar’s test p = 0.8 > 0.05). Using recursive channel selection, 9 channels (ELM) and 8 channels (SVM) were selected from 14 channels. After channel selection, ELM outperformed SVM significantly (McNemar’s test p = 0.0005 < 0.01) with average test accuracy of 95.0% and 92.5% respectively. The channel rank of each subject was weighted and merged using analytic hierarchical process to obtain a cross-subject ranking, which revealed the close correlation between TOVA and the visual pathway in brain.

Towards a Consistent, Tool Independent Virtual Material Appearance

Current materials appearance is mainly tool dependent and requires time, labour and computational cost to deliver consistent visual result. Within the industry, the development of a project is often based on a virtual model, which is usually developed by means of a collaboration among several departments, which exchange data. Unfortunately, a virtual material in most cases does not appear the same as the original once imported in a different renderer due to different algorithms and settings. The aim of this research is to provide artists with a general solution, applicable regardless the file format and the software used, thus allowing them to uniform the output of the renderer they use with a reference application, arbitrarily selected within an industry, to which all the renderings obtained with other software will be made visually uniform. We propose to characterize the appearance of several classes of materials rendered using the arbitrary reference software by extracting relevant visual characteristics. By repeating the same process for any other renderer we are able to derive ad-hoc mapping functions between the two renderers. Our approach allows us to hallucinate the appearance of a scene, depicting mainly the selected classes of materials, under the reference software.