Deike Albers
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Deike Albers has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Andreas Keinath
BMW Group
2 shared publications - Felix Wilhelm Siebert
Department of Technology, Management and Economics, Technical University of Denmark (DTU), Denmark
2 shared publications - Frederik Naujoks
BMW Group
2 shared publications - Klaus Bengler
Chair of Ergonomics, Technical University of Munich, Munich, Germany
2 shared publications - Sebastian Hergeth
BMW Group, 80937 Munich, Germany
2 shared publications - Alexandra Loew
BMW Group, Knorrstrasse 147, 80937 Munich, Germany
1 shared publication
Latest Publications
- 18 May 2021
- Published by Springer Nature
- p. 541-551
Human-Machine Interfaces for Automated Driving: Development of an Experimental Design for Evaluating Usability
- 18 May 2021
- Published by Springer Nature
- p. 541-551
Human-Machine Interfaces for Automated Driving: Development of an Experimental Design for Evaluating Usability
- Open Access
- 2 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 162073-162084
Helmet Use Detection of Tracked Motorcycles Using CNN-Based Multi-Task Learning
Automated detection of motorcycle helmet use through video surveillance can facilitate efficient education and enforcement campaigns that increase road safety. However, existing detection approaches have a number of shortcomings, such as the inabilities to track individual motorcycles through multiple frames, or to distinguish drivers from passengers in helmet use. Furthermore, datasets used to develop approaches are limited in terms of traffic environments and traffic density variations. In this paper, we propose a CNN-based multi-task learning (MTL) method for identifying and tracking individual motorcycles, and register rider specific helmet use.We further release the HELMET dataset, which includes 91,000 annotated frames of 10,006 individual motorcycles from 12 observation sites in Myanmar. Along with the dataset, we introduce an evaluation metric for helmet use and rider detection accuracy, which can be used as a benchmark for evaluating future detection approaches.We show that the use of MTL for concurrent visual similarity learning and helmet use classification improves the efficiency of our approach compared to earlier studies, allowing a processing speed of more than 8 FPS on consumer hardware, and a weighted average F-measure of 67.3% for detecting the number of riders and helmet use of tracked motorcycles. Our work demonstrates the capability of deep learning as a highly accurate and resource efficient approach to collect critical road safety related data.
- 2 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 162073-162084
Open AccessHelmet Use Detection of Tracked Motorcycles Using CNN-Based Multi-Task Learning
Automated detection of motorcycle helmet use through video surveillance can facilitate efficient education and enforcement campaigns that increase road safety. However, existing detection approaches have a number of shortcomings, such as the inabilities to track individual motorcycles through multiple frames, or to distinguish drivers from passengers in helmet use. Furthermore, datasets used to develop approaches are limited in terms of traffic environments and traffic density variations. In this paper, we propose a CNN-based multi-task learning (MTL) method for identifying and tracking individual motorcycles, and register rider specific helmet use.We further release the HELMET dataset, which includes 91,000 annotated frames of 10,006 individual motorcycles from 12 observation sites in Myanmar. Along with the dataset, we introduce an evaluation metric for helmet use and rider detection accuracy, which can be used as a benchmark for evaluating future detection approaches.We show that the use of MTL for concurrent visual similarity learning and helmet use classification improves the efficiency of our approach compared to earlier studies, allowing a processing speed of more than 8 FPS on consumer hardware, and a weighted average F-measure of 67.3% for detecting the number of riders and helmet use of tracked motorcycles. Our work demonstrates the capability of deep learning as a highly accurate and resource efficient approach to collect critical road safety related data.
- Open Access
- 28 April 2020
- Published by MDPI AG in Information
- Vol. 11 (5) , 240
Usability Evaluation—Advances in Experimental Design in the Context of Automated Driving Human–Machine Interfaces
The projected introduction of conditional automated driving systems to the market has sparked multifaceted research on human–machine interfaces (HMIs) for such systems. By moderating the roles of the human driver and the driving automation system, the HMI is indispensable in avoiding side effects of automation such as mode confusion, misuse, and disuse. In addition to safety aspects, the usability of HMIs plays a vital role in improving the trust and acceptance of the automated driving system. This paper aggregates common research methods and findings based on an extensive literature review. Empirical studies, frameworks, and review articles are included. Findings and conclusions are presented with a focus on study characteristics such as test cases, dependent variables, testing environments, or participant samples. These methods and findings are discussed critically, taking into consideration requirements for usability assessments of HMIs in the context of conditional automated driving. The paper concludes with a derivation of recommended study characteristics framing best practice advice for the design of experiments. The advised selection of scenarios and metrics will be applied in a future validation study series comprising a driving simulator experiment and three real driving experiments on test tracks in Germany, the USA, and Japan.
- 28 April 2020
- Published by MDPI AG in Information
- Vol. 11 (5) , 240
Open AccessUsability Evaluation—Advances in Experimental Design in the Context of Automated Driving Human–Machine Interfaces
The projected introduction of conditional automated driving systems to the market has sparked multifaceted research on human–machine interfaces (HMIs) for such systems. By moderating the roles of the human driver and the driving automation system, the HMI is indispensable in avoiding side effects of automation such as mode confusion, misuse, and disuse. In addition to safety aspects, the usability of HMIs plays a vital role in improving the trust and acceptance of the automated driving system. This paper aggregates common research methods and findings based on an extensive literature review. Empirical studies, frameworks, and review articles are included. Findings and conclusions are presented with a focus on study characteristics such as test cases, dependent variables, testing environments, or participant samples. These methods and findings are discussed critically, taking into consideration requirements for usability assessments of HMIs in the context of conditional automated driving. The paper concludes with a derivation of recommended study characteristics framing best practice advice for the design of experiments. The advised selection of scenarios and metrics will be applied in a future validation study series comprising a driving simulator experiment and three real driving experiments on test tracks in Germany, the USA, and Japan.
- 7 October 2019
- Published by SAGE Publications in Human Factors: The Journal of the Human Factors and Ergonomics Society
- Vol. 62 (7) , 1212-1229
How Do Drivers Respond to Silent Automation Failures? Driving Simulator Study and Comparison of Computational Driver Braking Models
This paper aims to describe and test novel computational driver models, predicting drivers’ brake reaction times (BRTs) to different levels of lead vehicle braking, during driving with cruise control (CC) and during silent failures of adaptive cruise control (ACC). Validated computational models predicting BRTs to silent failures of automation are lacking but are important for assessing the safety benefits of automated driving. Two alternative models of driver response to silent ACC failures are proposed: a looming prediction model, assuming that drivers embody a generative model of ACC, and a lower gain model, assuming that drivers’ arousal decreases due to monitoring of the automated system. Predictions of BRTs issued by the models were tested using a driving simulator study. The driving simulator study confirmed the predictions of the models: (a) BRTs were significantly shorter with an increase in kinematic criticality, both during driving with CC and during driving with ACC; (b) BRTs were significantly delayed when driving with ACC compared with driving with CC. However, the predicted BRTs were longer than the ones observed, entailing a fitting of the models to the data from the study. Both the looming prediction model and the lower gain model predict well the BRTs for the ACC driving condition. However, the looming prediction model has the advantage of being able to predict average BRTs using the exact same parameters as the model fitted to the CC driving data. Knowledge resulting from this research can be helpful for assessing the safety benefits of automated driving.
- 7 October 2019
- Published by SAGE Publications in Human Factors: The Journal of the Human Factors and Ergonomics Society
- Vol. 62 (7) , 1212-1229
How Do Drivers Respond to Silent Automation Failures? Driving Simulator Study and Comparison of Computational Driver Braking Models
This paper aims to describe and test novel computational driver models, predicting drivers’ brake reaction times (BRTs) to different levels of lead vehicle braking, during driving with cruise control (CC) and during silent failures of adaptive cruise control (ACC). Validated computational models predicting BRTs to silent failures of automation are lacking but are important for assessing the safety benefits of automated driving. Two alternative models of driver response to silent ACC failures are proposed: a looming prediction model, assuming that drivers embody a generative model of ACC, and a lower gain model, assuming that drivers’ arousal decreases due to monitoring of the automated system. Predictions of BRTs issued by the models were tested using a driving simulator study. The driving simulator study confirmed the predictions of the models: (a) BRTs were significantly shorter with an increase in kinematic criticality, both during driving with CC and during driving with ACC; (b) BRTs were significantly delayed when driving with ACC compared with driving with CC. However, the predicted BRTs were longer than the ones observed, entailing a fitting of the models to the data from the study. Both the looming prediction model and the lower gain model predict well the BRTs for the ACC driving condition. However, the looming prediction model has the advantage of being able to predict average BRTs using the exact same parameters as the model fitted to the CC driving data. Knowledge resulting from this research can be helpful for assessing the safety benefits of automated driving.
- Open Access
- 1 March 2019
- Published by Elsevier in Accident Analysis & Prevention
- Vol. 124, 146-150
Patterns of motorcycle helmet use – A naturalistic observation study in Myanmar
- 1 March 2019
- Published by Elsevier in Accident Analysis & Prevention
- Vol. 124, 146-150
Open AccessPatterns of motorcycle helmet use – A naturalistic observation study in Myanmar