This page contains automatically translated content.

M. Eng. Florian Heidecker

AI for Motion (AIM)

Telephone: +49 561 804-6018
Fax: +49 561 804-6022
Email: florian.heidecker[at]uni-kassel[dot]de

Site: Wilhelmshöher Allee 67
34121 Kassel

Room: 4106

Publications

[ 2024 ]
[ 2023 ]
[ 2022 ]
[ 2021 ]
[ 2020 ]
[ 2019 ]

2024[ to top ]

Criteria for Uncertainty-based Corner Cases Detection in Instance Segmentation. Heidecker, Florian; El-Khateeb, Ahmad; Bieshaar, Maarten; Sick, Bernhard. In arXiv e-prints, bl arXiv:2404.11266. 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
The operating environment of a highly automated vehicle is subject to change, e.g., weather, illumination, or the scenario containing different objects and other participants in which the highly automated vehicle has to navigate its passengers safely. These situations must be considered when developing and validating highly automated driving functions. This already poses a problem for training and evaluating deep learning models because without the costly labeling of thousands of recordings, not knowing whether the data contains relevant, interesting data for further model training, it is a guess under which conditions and situations the model performs poorly. For this purpose, we present corner case criteria based on the predictive uncertainty. With our corner case criteria, we are able to detect uncertainty-based corner cases of an object instance segmentation model without relying on ground truth (GT) data. We evaluated each corner case criterion using the COCO and the NuImages dataset to analyze the potential of our approach. We also provide a corner case decision function that allows us to distinguish each object into True Positive (TP), localization and/or classification corner case, or False Positive (FP). We also present our first results of an iterative training cycle that outperforms the baseline and where the data added to the training dataset is selected based on the corner case decision function.
@article{heidecker2024criteria, abstract = {The operating environment of a highly automated vehicle is subject to change, e.g., weather, illumination, or the scenario containing different objects and other participants in which the highly automated vehicle has to navigate its passengers safely. These situations must be considered when developing and validating highly automated driving functions. This already poses a problem for training and evaluating deep learning models because without the costly labeling of thousands of recordings, not knowing whether the data contains relevant, interesting data for further model training, it is a guess under which conditions and situations the model performs poorly. For this purpose, we present corner case criteria based on the predictive uncertainty. With our corner case criteria, we are able to detect uncertainty-based corner cases of an object instance segmentation model without relying on ground truth (GT) data. We evaluated each corner case criterion using the COCO and the NuImages dataset to analyze the potential of our approach. We also provide a corner case decision function that allows us to distinguish each object into True Positive (TP), localization and/or classification corner case, or False Positive (FP). We also present our first results of an iterative training cycle that outperforms the baseline and where the data added to the training dataset is selected based on the corner case decision function.}, author = {Heidecker, Florian and El-Khateeb, Ahmad and Bieshaar, Maarten and Sick, Bernhard}, journal = {arXiv e-prints}, keywords = {itegpub}, pages = {arXiv:2404.11266}, title = {Criteria for Uncertainty-based Corner Cases Detection in Instance Segmentation}, year = 2024 }
%0 Journal Article %1 heidecker2024criteria %A Heidecker, Florian %A El-Khateeb, Ahmad %A Bieshaar, Maarten %A Sick, Bernhard %D 2024 %J arXiv e-prints %P arXiv:2404.11266 %T Criteria for Uncertainty-based Corner Cases Detection in Instance Segmentation %U https://arxiv.org/abs/2404.11266 %X The operating environment of a highly automated vehicle is subject to change, e.g., weather, illumination, or the scenario containing different objects and other participants in which the highly automated vehicle has to navigate its passengers safely. These situations must be considered when developing and validating highly automated driving functions. This already poses a problem for training and evaluating deep learning models because without the costly labeling of thousands of recordings, not knowing whether the data contains relevant, interesting data for further model training, it is a guess under which conditions and situations the model performs poorly. For this purpose, we present corner case criteria based on the predictive uncertainty. With our corner case criteria, we are able to detect uncertainty-based corner cases of an object instance segmentation model without relying on ground truth (GT) data. We evaluated each corner case criterion using the COCO and the NuImages dataset to analyze the potential of our approach. We also provide a corner case decision function that allows us to distinguish each object into True Positive (TP), localization and/or classification corner case, or False Positive (FP). We also present our first results of an iterative training cycle that outperforms the baseline and where the data added to the training dataset is selected based on the corner case decision function.

2023[ to top ]

What Does Really Count? Estimating Relevance of Corner Cases for Semantic Segmentation in Automated Driving. Breitenstein, Jasmin; Heidecker, Florian; Lyssenko, Maria; Bogdoll, Daniel; Bieshaar, Maarten; Zöllner, J. Marius; Sick, Bernhard; Fingscheidt, Tim. In Workshop on roBustness and Reliability of Autonomous Vehicles in the Open-world (BRAVO), ICCV, bll 3991–4000. 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
In safety-critical applications such as automated driving, perception errors may create an imminent risk to vulnerable road users (VRU). To mitigate the occurrence of unexpected and potentially dangerous situations, so-called corner cases, perception models are trained on a huge amount of data. However, the models are typically evaluated using task-agnostic metrics, which do not reflect the severity of safety-critical misdetections. Consequently, misdetections with particular relevance for the safe driving task should entail a more severe penalty during evaluation to pinpoint corner cases in large-scale datasets. In this work, we propose a novel metric IoUw that exploits relevance on the pixel level of the semantic segmentation output to extend the notion of the intersection over union (IoU) by emphasizing small areas of an image affected by corner cases. We (i) employ IoUw to measure the effect of pre-defined relevance criteria on the segmentation evaluation, and (ii) use the relevance-adapted IoUw to refine the identification of corner cases. In our experiments, we investigate vision-based relevance criteria and physical attributes as per-pixel criticality to factor in the imminent risk, showing that IoUw precisely accentuates the relevance of corner cases.
@inproceedings{breitenstein2023what, abstract = {In safety-critical applications such as automated driving, perception errors may create an imminent risk to vulnerable road users (VRU). To mitigate the occurrence of unexpected and potentially dangerous situations, so-called corner cases, perception models are trained on a huge amount of data. However, the models are typically evaluated using task-agnostic metrics, which do not reflect the severity of safety-critical misdetections. Consequently, misdetections with particular relevance for the safe driving task should entail a more severe penalty during evaluation to pinpoint corner cases in large-scale datasets. In this work, we propose a novel metric IoUw that exploits relevance on the pixel level of the semantic segmentation output to extend the notion of the intersection over union (IoU) by emphasizing small areas of an image affected by corner cases. We (i) employ IoUw to measure the effect of pre-defined relevance criteria on the segmentation evaluation, and (ii) use the relevance-adapted IoUw to refine the identification of corner cases. In our experiments, we investigate vision-based relevance criteria and physical attributes as per-pixel criticality to factor in the imminent risk, showing that IoUw precisely accentuates the relevance of corner cases.}, author = {Breitenstein, Jasmin and Heidecker, Florian and Lyssenko, Maria and Bogdoll, Daniel and Bieshaar, Maarten and Zöllner, J. Marius and Sick, Bernhard and Fingscheidt, Tim}, booktitle = {Workshop on roBustness and Reliability of Autonomous Vehicles in the Open-world (BRAVO), ICCV}, keywords = {itegpub}, pages = {3991–4000}, title = {What Does Really Count? Estimating Relevance of Corner Cases for Semantic Segmentation in Automated Driving}, year = 2023 }
%0 Conference Paper %1 breitenstein2023what %A Breitenstein, Jasmin %A Heidecker, Florian %A Lyssenko, Maria %A Bogdoll, Daniel %A Bieshaar, Maarten %A Zöllner, J. Marius %A Sick, Bernhard %A Fingscheidt, Tim %B Workshop on roBustness and Reliability of Autonomous Vehicles in the Open-world (BRAVO), ICCV %D 2023 %P 3991--4000 %T What Does Really Count? Estimating Relevance of Corner Cases for Semantic Segmentation in Automated Driving %U https://openaccess.thecvf.com/content/ICCV2023W/BRAVO/html/Breitenstein_What_Does_Really_Count_Estimating_Relevance_of_Corner_Cases_for_ICCVW_2023_paper.html %X In safety-critical applications such as automated driving, perception errors may create an imminent risk to vulnerable road users (VRU). To mitigate the occurrence of unexpected and potentially dangerous situations, so-called corner cases, perception models are trained on a huge amount of data. However, the models are typically evaluated using task-agnostic metrics, which do not reflect the severity of safety-critical misdetections. Consequently, misdetections with particular relevance for the safe driving task should entail a more severe penalty during evaluation to pinpoint corner cases in large-scale datasets. In this work, we propose a novel metric IoUw that exploits relevance on the pixel level of the semantic segmentation output to extend the notion of the intersection over union (IoU) by emphasizing small areas of an image affected by corner cases. We (i) employ IoUw to measure the effect of pre-defined relevance criteria on the segmentation evaluation, and (ii) use the relevance-adapted IoUw to refine the identification of corner cases. In our experiments, we investigate vision-based relevance criteria and physical attributes as per-pixel criticality to factor in the imminent risk, showing that IoUw precisely accentuates the relevance of corner cases.
Sampling-based Uncertainty Estimation for an Instance Segmentation Network. Heidecker, Florian; El-Khateeb, Ahmad; Sick, Bernhard. In arXiv e-prints, bl arXiv:2305.14977. 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
The examination of uncertainty in the predictions of machine learning (ML) models is receiving increasing attention. One uncertainty modeling technique used for this purpose is Monte-Carlo (MC)-Dropout, where repeated predictions are generated for a single input. Therefore, clustering is required to describe the resulting uncertainty, but only through efficient clustering is it possible to describe the uncertainty from the model attached to each object. This article uses Bayesian Gaussian Mixture (BGM) to solve this problem. In addition, we investigate different values for the dropout rate and other techniques, such as focal loss and calibration, which we integrate into the Mask-RCNN model to obtain the most accurate uncertainty approximation of each instance and showcase it graphically.
@article{heidecker2023sampling, abstract = {The examination of uncertainty in the predictions of machine learning (ML) models is receiving increasing attention. One uncertainty modeling technique used for this purpose is Monte-Carlo (MC)-Dropout, where repeated predictions are generated for a single input. Therefore, clustering is required to describe the resulting uncertainty, but only through efficient clustering is it possible to describe the uncertainty from the model attached to each object. This article uses Bayesian Gaussian Mixture (BGM) to solve this problem. In addition, we investigate different values for the dropout rate and other techniques, such as focal loss and calibration, which we integrate into the Mask-RCNN model to obtain the most accurate uncertainty approximation of each instance and showcase it graphically.}, author = {Heidecker, Florian and El-Khateeb, Ahmad and Sick, Bernhard}, journal = {arXiv e-prints}, keywords = {itegpub}, pages = {arXiv:2305.14977}, title = {Sampling-based Uncertainty Estimation for an Instance Segmentation Network}, year = 2023 }
%0 Journal Article %1 heidecker2023sampling %A Heidecker, Florian %A El-Khateeb, Ahmad %A Sick, Bernhard %D 2023 %J arXiv e-prints %P arXiv:2305.14977 %T Sampling-based Uncertainty Estimation for an Instance Segmentation Network %U https://arxiv.org/abs/2305.14977 %X The examination of uncertainty in the predictions of machine learning (ML) models is receiving increasing attention. One uncertainty modeling technique used for this purpose is Monte-Carlo (MC)-Dropout, where repeated predictions are generated for a single input. Therefore, clustering is required to describe the resulting uncertainty, but only through efficient clustering is it possible to describe the uncertainty from the model attached to each object. This article uses Bayesian Gaussian Mixture (BGM) to solve this problem. In addition, we investigate different values for the dropout rate and other techniques, such as focal loss and calibration, which we integrate into the Mask-RCNN model to obtain the most accurate uncertainty approximation of each instance and showcase it graphically.
Corner Cases in Machine Learning Processes. Heidecker, Florian; Bieshaar, Maarten; Sick, Bernhard. In AI Perspectives & Advances, 6(1), bll 1–17. 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Applications using machine learning (ML), such as highly autonomous driving, depend highly on the performance of the ML model. The data amount and quality used for model training and validation are crucial. If the model cannot detect and interpret a new, rare, or perhaps dangerous situation, often referred to as a corner case, we will likely blame the data for not being good enough or too small in number. However, the implemented ML model and its associated architecture also influence the behavior. Therefore, the occurrence of prediction errors resulting from the ML model itself is not surprising. This work addresses a corner case definition from an ML model's perspective to determine which aspects must be considered. To achieve this goal, we present an overview of properties for corner cases that are beneficial for the description, explanation, reproduction, or synthetic generation of corner cases. To define ML corner cases, we review different considerations in the literature and summarize them in a general description and mathematical formulation, whereby the expected relevance-weighted loss is the key to distinguishing corner cases from common data. Moreover, we show how to operationalize the corner case characteristics to determine the value of a corner case. To conclude, we present the extended taxonomy for ML corner cases by adding the input, model, and deployment levels, considering the influence of the corner case properties.
@article{heidecker2023corner, abstract = {Applications using machine learning (ML), such as highly autonomous driving, depend highly on the performance of the ML model. The data amount and quality used for model training and validation are crucial. If the model cannot detect and interpret a new, rare, or perhaps dangerous situation, often referred to as a corner case, we will likely blame the data for not being good enough or too small in number. However, the implemented ML model and its associated architecture also influence the behavior. Therefore, the occurrence of prediction errors resulting from the ML model itself is not surprising. This work addresses a corner case definition from an ML model's perspective to determine which aspects must be considered. To achieve this goal, we present an overview of properties for corner cases that are beneficial for the description, explanation, reproduction, or synthetic generation of corner cases. To define ML corner cases, we review different considerations in the literature and summarize them in a general description and mathematical formulation, whereby the expected relevance-weighted loss is the key to distinguishing corner cases from common data. Moreover, we show how to operationalize the corner case characteristics to determine the value of a corner case. To conclude, we present the extended taxonomy for ML corner cases by adding the input, model, and deployment levels, considering the influence of the corner case properties.}, author = {Heidecker, Florian and Bieshaar, Maarten and Sick, Bernhard}, journal = {AI Perspectives & Advances}, keywords = {itegpub}, number = 1, pages = {1–17}, title = {Corner Cases in Machine Learning Processes}, volume = 6, year = 2023 }
%0 Journal Article %1 heidecker2023corner %A Heidecker, Florian %A Bieshaar, Maarten %A Sick, Bernhard %D 2023 %J AI Perspectives & Advances %N 1 %P 1--17 %R 10.1186/s42467-023-00015-y %T Corner Cases in Machine Learning Processes %U https://aiperspectives.springeropen.com/articles/10.1186/s42467-023-00015-y %V 6 %X Applications using machine learning (ML), such as highly autonomous driving, depend highly on the performance of the ML model. The data amount and quality used for model training and validation are crucial. If the model cannot detect and interpret a new, rare, or perhaps dangerous situation, often referred to as a corner case, we will likely blame the data for not being good enough or too small in number. However, the implemented ML model and its associated architecture also influence the behavior. Therefore, the occurrence of prediction errors resulting from the ML model itself is not surprising. This work addresses a corner case definition from an ML model's perspective to determine which aspects must be considered. To achieve this goal, we present an overview of properties for corner cases that are beneficial for the description, explanation, reproduction, or synthetic generation of corner cases. To define ML corner cases, we review different considerations in the literature and summarize them in a general description and mathematical formulation, whereby the expected relevance-weighted loss is the key to distinguishing corner cases from common data. Moreover, we show how to operationalize the corner case characteristics to determine the value of a corner case. To conclude, we present the extended taxonomy for ML corner cases by adding the input, model, and deployment levels, considering the influence of the corner case properties.
Context Information for Corner Case Detection in Highly Automated Driving. Heidecker, Florian; Susetzky, Tobias; Fuchs, Erich; Sick, Bernhard. In IEEE International Conference on Intelligent Transportation Systems (ITSC), bll 1522–1529. IEEE, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Context information provided along with a dataset can be very helpful for solving a problem because the additional knowledge is already available and does not need to be extracted. Moreover, the context indicates how diverse a dataset is, i.e., how many samples per context category are available to train and test machine learning (ML) models. In this article, we present context annotations for the BDD100k image dataset. The annotations comprise, for instance, information about daytime, road condition (dry/wet), and dirt on the windshield. Sometimes, no or only little data are available for unique or rare combinations of these context attributes. However, data that matches these context conditions is crucial when discussing corner cases: Firstly, most ML models, e.g., object detectors, are not trained on such data, which leads to the assumption that they will perform poorly in those situations. Secondly, data containing corner cases are required for validating ML models. With this in mind, separate ML models dedicated to context detection are useful for expanding the training set with additional data of special interest, such as corner cases.
@inproceedings{heidecker2023context, abstract = {Context information provided along with a dataset can be very helpful for solving a problem because the additional knowledge is already available and does not need to be extracted. Moreover, the context indicates how diverse a dataset is, i.e., how many samples per context category are available to train and test machine learning (ML) models. In this article, we present context annotations for the BDD100k image dataset. The annotations comprise, for instance, information about daytime, road condition (dry/wet), and dirt on the windshield. Sometimes, no or only little data are available for unique or rare combinations of these context attributes. However, data that matches these context conditions is crucial when discussing corner cases: Firstly, most ML models, e.g., object detectors, are not trained on such data, which leads to the assumption that they will perform poorly in those situations. Secondly, data containing corner cases are required for validating ML models. With this in mind, separate ML models dedicated to context detection are useful for expanding the training set with additional data of special interest, such as corner cases.}, author = {Heidecker, Florian and Susetzky, Tobias and Fuchs, Erich and Sick, Bernhard}, booktitle = {IEEE International Conference on Intelligent Transportation Systems (ITSC)}, keywords = {itegpub}, pages = {1522–1529}, publisher = {IEEE}, title = {Context Information for Corner Case Detection in Highly Automated Driving}, year = 2023 }
%0 Conference Paper %1 heidecker2023context %A Heidecker, Florian %A Susetzky, Tobias %A Fuchs, Erich %A Sick, Bernhard %B IEEE International Conference on Intelligent Transportation Systems (ITSC) %D 2023 %I IEEE %P 1522--1529 %R 10.1109/ITSC57777.2023.10422414 %T Context Information for Corner Case Detection in Highly Automated Driving %X Context information provided along with a dataset can be very helpful for solving a problem because the additional knowledge is already available and does not need to be extracted. Moreover, the context indicates how diverse a dataset is, i.e., how many samples per context category are available to train and test machine learning (ML) models. In this article, we present context annotations for the BDD100k image dataset. The annotations comprise, for instance, information about daytime, road condition (dry/wet), and dirt on the windshield. Sometimes, no or only little data are available for unique or rare combinations of these context attributes. However, data that matches these context conditions is crucial when discussing corner cases: Firstly, most ML models, e.g., object detectors, are not trained on such data, which leads to the assumption that they will perform poorly in those situations. Secondly, data containing corner cases are required for validating ML models. With this in mind, separate ML models dedicated to context detection are useful for expanding the training set with additional data of special interest, such as corner cases.

2022[ to top ]

Space, Time, and Interaction: A Taxonomy of Corner Cases in Trajectory Datasets for Automated Driving. Rösch, Kevin; Heidecker, Florian; Truetsch, Julian; Kowol, Kamil; Schicktanz, Clemens; Bieshaar, Maarten; Sick, Bernhard; Stiller, Christoph. In IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems (IEEE CIVTS), IEEE SSCI, bll 86–93. IEEE, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Trajectory data analysis is an essential component for highly automated driving. Complex models developed with these data predict other road users’ movement and behavior patterns. Based on these predictions — and additional contextual information such as the course of the road, (traffic) rules, and interaction with other road users — the highly automated vehicle (HAV) must be able to reliably and safely perform the task assigned to it, e.g., moving from point A to B. Ideally, the HAV moves safely through its environment, just as we would expect a human driver to do. However, if unusual trajectories occur, so-called trajectory corner cases, a human driver can usually cope well, but an HAV can quickly get into trouble. In the definition of trajectory corner cases, which we provide in this work, we will consider the relevance of unusual trajectories with respect to the task at hand. Based on this, we will also present a taxonomy of different trajectory corner cases. The categorization of corner cases into the taxonomy will be shown with examples and is done by cause and required data sources. To illustrate the complexity between the machine learning (ML) model and the corner case cause, we present a general processing chain underlying the taxonomy.
@inproceedings{rosch2022space, abstract = {Trajectory data analysis is an essential component for highly automated driving. Complex models developed with these data predict other road users’ movement and behavior patterns. Based on these predictions — and additional contextual information such as the course of the road, (traffic) rules, and interaction with other road users — the highly automated vehicle (HAV) must be able to reliably and safely perform the task assigned to it, e.g., moving from point A to B. Ideally, the HAV moves safely through its environment, just as we would expect a human driver to do. However, if unusual trajectories occur, so-called trajectory corner cases, a human driver can usually cope well, but an HAV can quickly get into trouble. In the definition of trajectory corner cases, which we provide in this work, we will consider the relevance of unusual trajectories with respect to the task at hand. Based on this, we will also present a taxonomy of different trajectory corner cases. The categorization of corner cases into the taxonomy will be shown with examples and is done by cause and required data sources. To illustrate the complexity between the machine learning (ML) model and the corner case cause, we present a general processing chain underlying the taxonomy.}, author = {Rösch, Kevin and Heidecker, Florian and Truetsch, Julian and Kowol, Kamil and Schicktanz, Clemens and Bieshaar, Maarten and Sick, Bernhard and Stiller, Christoph}, booktitle = {IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems (IEEE CIVTS), IEEE SSCI}, keywords = {itegpub}, pages = {86–93}, publisher = {IEEE}, title = {Space, Time, and Interaction: A Taxonomy of Corner Cases in Trajectory Datasets for Automated Driving}, year = 2022 }
%0 Conference Paper %1 rosch2022space %A Rösch, Kevin %A Heidecker, Florian %A Truetsch, Julian %A Kowol, Kamil %A Schicktanz, Clemens %A Bieshaar, Maarten %A Sick, Bernhard %A Stiller, Christoph %B IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems (IEEE CIVTS), IEEE SSCI %D 2022 %I IEEE %P 86--93 %R 10.1109/SSCI51031.2022.10022241 %T Space, Time, and Interaction: A Taxonomy of Corner Cases in Trajectory Datasets for Automated Driving %U https://ieeexplore.ieee.org/document/10022241 %X Trajectory data analysis is an essential component for highly automated driving. Complex models developed with these data predict other road users’ movement and behavior patterns. Based on these predictions — and additional contextual information such as the course of the road, (traffic) rules, and interaction with other road users — the highly automated vehicle (HAV) must be able to reliably and safely perform the task assigned to it, e.g., moving from point A to B. Ideally, the HAV moves safely through its environment, just as we would expect a human driver to do. However, if unusual trajectories occur, so-called trajectory corner cases, a human driver can usually cope well, but an HAV can quickly get into trouble. In the definition of trajectory corner cases, which we provide in this work, we will consider the relevance of unusual trajectories with respect to the task at hand. Based on this, we will also present a taxonomy of different trajectory corner cases. The categorization of corner cases into the taxonomy will be shown with examples and is done by cause and required data sources. To illustrate the complexity between the machine learning (ML) model and the corner case cause, we present a general processing chain underlying the taxonomy.
Detecting Corner Case in the Context of Highly Automated Driving. Heidecker, Florian. In Organic Computing -- Doctoral Dissertation Colloquium 2021, S. Tomforde, C. Krupitzer (reds.), bll 60–73. kassel university press, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
This article introduces a research proposal that aims to deﬁne, detect, and evaluate corner cases in the context of machine learning (ML) systems and highly automated driving. Corner cases are scenarios or data in a dataset that are recorded only very rarely and therefore only available in small quantities or not at all in the dataset. However, corner cases are very important for model training, as they are needed to improve the model performance in these rare scenarios. On the other hand, in safety- and security-critical applications, such as highly automated driving, corner case data is extremely important for testing and verifying the ML system. The research proposal addresses these challenges and focuses on the deﬁnition and categorization of corner cases. Based on this, ML methods for corner case detection are developed, focusing on object detection for automated driving and trajectory data for intention detection of pedestrians and cyclists. Finally, the research proposal addresses corner case metrics and the evaluation of the developed detection models.
@incollection{florianheidecker2022detecting, abstract = {This article introduces a research proposal that aims to deﬁne, detect, and evaluate corner cases in the context of machine learning (ML) systems and highly automated driving. Corner cases are scenarios or data in a dataset that are recorded only very rarely and therefore only available in small quantities or not at all in the dataset. However, corner cases are very important for model training, as they are needed to improve the model performance in these rare scenarios. On the other hand, in safety- and security-critical applications, such as highly automated driving, corner case data is extremely important for testing and verifying the ML system. The research proposal addresses these challenges and focuses on the deﬁnition and categorization of corner cases. Based on this, ML methods for corner case detection are developed, focusing on object detection for automated driving and trajectory data for intention detection of pedestrians and cyclists. Finally, the research proposal addresses corner case metrics and the evaluation of the developed detection models.}, author = {Heidecker, Florian}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2021}, editor = {Tomforde, Sven and Krupitzer, Christian}, keywords = {itegpub}, pages = {60–73}, publisher = {kassel university press}, title = {Detecting Corner Case in the Context of Highly Automated Driving}, year = 2022 }
%0 Book Section %1 florianheidecker2022detecting %A Heidecker, Florian %B Organic Computing -- Doctoral Dissertation Colloquium 2021 %D 2022 %E Tomforde, Sven %E Krupitzer, Christian %I kassel university press %P 60--73 %T Detecting Corner Case in the Context of Highly Automated Driving %X This article introduces a research proposal that aims to deﬁne, detect, and evaluate corner cases in the context of machine learning (ML) systems and highly automated driving. Corner cases are scenarios or data in a dataset that are recorded only very rarely and therefore only available in small quantities or not at all in the dataset. However, corner cases are very important for model training, as they are needed to improve the model performance in these rare scenarios. On the other hand, in safety- and security-critical applications, such as highly automated driving, corner case data is extremely important for testing and verifying the ML system. The research proposal addresses these challenges and focuses on the deﬁnition and categorization of corner cases. Based on this, ML methods for corner case detection are developed, focusing on object detection for automated driving and trajectory data for intention detection of pedestrians and cyclists. Finally, the research proposal addresses corner case metrics and the evaluation of the developed detection models.

2021[ to top ]

Towards Corner Case Detection by Modeling the Uncertainty of Instance Segmentation Networks. Heidecker, Florian; Hannan, Abdul; Bieshaar, Maarten; Sick, Bernhard. In Workshop on Integrated Artificial Intelligence in Data Science, ICPR, bll 361–374. IEEE, Milan, Italy, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{heidecker2021towards, address = {Milan, Italy}, author = {Heidecker, Florian and Hannan, Abdul and Bieshaar, Maarten and Sick, Bernhard}, booktitle = {Workshop on Integrated Artificial Intelligence in Data Science, ICPR}, keywords = {itegpub}, pages = {361–374}, publisher = {IEEE}, title = {Towards Corner Case Detection by Modeling the Uncertainty of Instance Segmentation Networks}, year = 2021 }
%0 Conference Paper %1 heidecker2021towards %A Heidecker, Florian %A Hannan, Abdul %A Bieshaar, Maarten %A Sick, Bernhard %B Workshop on Integrated Artificial Intelligence in Data Science, ICPR %C Milan, Italy %D 2021 %I IEEE %P 361--374 %R 10.1007/978-3-030-68799-1_26 %T Towards Corner Case Detection by Modeling the Uncertainty of Instance Segmentation Networks
Out-of-distribution Detection and Generation using Soft Brownian Offset Sampling and Autoencoders. Möller, Felix; Botache, Diego; Huseljic, Denis; Heidecker, Florian; Bieshaar, Maarten; Sick, Bernhard. In Workshop on Safe Artificial Intelligence for Automated Driving (SAIAD), CVPR, bll 1–10. 2021.
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
@inproceedings{moeller2021out, author = {Möller, Felix and Botache, Diego and Huseljic, Denis and Heidecker, Florian and Bieshaar, Maarten and Sick, Bernhard}, booktitle = {Workshop on Safe Artificial Intelligence for Automated Driving (SAIAD), CVPR}, keywords = {itegpub}, pages = {1–10}, title = {{Out-of-distribution Detection and Generation using Soft Brownian Offset Sampling and Autoencoders}}, year = 2021 }
%0 Conference Paper %1 moeller2021out %A Möller, Felix %A Botache, Diego %A Huseljic, Denis %A Heidecker, Florian %A Bieshaar, Maarten %A Sick, Bernhard %B Workshop on Safe Artificial Intelligence for Automated Driving (SAIAD), CVPR %D 2021 %P 1--10 %T Out-of-distribution Detection and Generation using Soft Brownian Offset Sampling and Autoencoders %U https://openaccess.thecvf.com/content/CVPR2021W/SAIAD/papers/Moller_Out-of-Distribution_Detection_and_Generation_Using_Soft_Brownian_Offset_Sampling_and_CVPRW_2021_paper.pdf
Novelty based Driver Identification on RR Intervals from ECG Data. Heidecker, Florian; Gruhl, Christian; Sick, Bernhard. In Workshop on Integrated Artificial Intelligence in Data Science, ICPR, bll 407–421. IEEE, Milan, Italy, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{heidecker2021novelty, address = {Milan, Italy}, author = {Heidecker, Florian and Gruhl, Christian and Sick, Bernhard}, booktitle = {Workshop on Integrated Artificial Intelligence in Data Science, ICPR}, keywords = {itegpub}, pages = {407–421}, publisher = {IEEE}, title = {Novelty based Driver Identification on RR Intervals from ECG Data}, year = 2021 }
%0 Conference Paper %1 heidecker2021novelty %A Heidecker, Florian %A Gruhl, Christian %A Sick, Bernhard %B Workshop on Integrated Artificial Intelligence in Data Science, ICPR %C Milan, Italy %D 2021 %I IEEE %P 407--421 %R 10.1007/978-3-030-68799-1_29 %T Novelty based Driver Identification on RR Intervals from ECG Data
Intelligent and Interactive Video Annotation for Instance Segmentation using Siamese Neural Networks. Schneegans, Jan; Bieshaar, Maarten; Heidecker, Florian; Sick, Bernhard. In Workshop on Integrated Artificial Intelligence in Data Science, ICPR, bll 375–389. IEEE, Milan, Italy, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{schneegans2021intelligent, address = {Milan, Italy}, author = {Schneegans, Jan and Bieshaar, Maarten and Heidecker, Florian and Sick, Bernhard}, booktitle = {Workshop on Integrated Artificial Intelligence in Data Science, ICPR}, keywords = {itegpub}, pages = {375–389}, publisher = {IEEE}, title = {Intelligent and Interactive Video Annotation for Instance Segmentation using Siamese Neural Networks}, year = 2021 }
%0 Conference Paper %1 schneegans2021intelligent %A Schneegans, Jan %A Bieshaar, Maarten %A Heidecker, Florian %A Sick, Bernhard %B Workshop on Integrated Artificial Intelligence in Data Science, ICPR %C Milan, Italy %D 2021 %I IEEE %P 375--389 %R 10.1007/978-3-030-68799-1_27 %T Intelligent and Interactive Video Annotation for Instance Segmentation using Siamese Neural Networks
Description of Corner Cases in Automated Driving: Goals and Challenges. Bogdoll, Daniel; Breitenstein, Jasmin; Heidecker, Florian; Bieshaar, Maarten; Sick, Bernhard; Fingscheidt, Tim; Zöllner, J. Marius. In Embedded and Real-World Computer Vision in Autonomous Driving (ERCVAD), ICCV, bll 1023–1028. IEEE, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{bogdoll2021description, author = {Bogdoll, Daniel and Breitenstein, Jasmin and Heidecker, Florian and Bieshaar, Maarten and Sick, Bernhard and Fingscheidt, Tim and Zöllner, J. Marius}, booktitle = {Embedded and Real-World Computer Vision in Autonomous Driving (ERCVAD), ICCV}, keywords = {itegpub}, pages = {1023–1028,}, publisher = {IEEE}, title = {Description of Corner Cases in Automated Driving: Goals and Challenges}, year = 2021 }
%0 Conference Paper %1 bogdoll2021description %A Bogdoll, Daniel %A Breitenstein, Jasmin %A Heidecker, Florian %A Bieshaar, Maarten %A Sick, Bernhard %A Fingscheidt, Tim %A Zöllner, J. Marius %B Embedded and Real-World Computer Vision in Autonomous Driving (ERCVAD), ICCV %D 2021 %I IEEE %P 1023--1028, %R 10.1109/iccvw54120.2021.00119 %T Description of Corner Cases in Automated Driving: Goals and Challenges
An Application-Driven Conceptualization of Corner Cases for Perception in Highly Automated Driving. Heidecker, Florian; Breitenstein, Jasmin; Rösch, Kevin; Löhdefink, Jonas; Bieshaar, Maarten; Stiller, Christoph; Fingscheidt, Tim; Sick, Bernhard. In IEEE Intelligent Vehicles Symposium (IV), bll 644–651. IEEE, Nagoya, Japan, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{heidecker2021application, address = {Nagoya, Japan}, author = {Heidecker, Florian and Breitenstein, Jasmin and Rösch, Kevin and Löhdefink, Jonas and Bieshaar, Maarten and Stiller, Christoph and Fingscheidt, Tim and Sick, Bernhard}, booktitle = {IEEE Intelligent Vehicles Symposium (IV)}, keywords = {itegpub}, pages = {644–651}, publisher = {IEEE}, title = {{An Application-Driven Conceptualization of Corner Cases for Perception in Highly Automated Driving}}, year = 2021 }
%0 Conference Paper %1 heidecker2021application %A Heidecker, Florian %A Breitenstein, Jasmin %A Rösch, Kevin %A Löhdefink, Jonas %A Bieshaar, Maarten %A Stiller, Christoph %A Fingscheidt, Tim %A Sick, Bernhard %B IEEE Intelligent Vehicles Symposium (IV) %C Nagoya, Japan %D 2021 %I IEEE %P 644--651 %R 10.1109/iv48863.2021.9575933 %T An Application-Driven Conceptualization of Corner Cases for Perception in Highly Automated Driving

2020[ to top ]

Knowledge Representations in Technical Systems -- A Taxonomy. Scharei, Kristina; Heidecker, Florian; Bieshaar, Maarten. In arXiv e-prints, bl arXiv:2001.04835. 2020.
- [ BibTeX ]
- [ EndNote ]
@article{scharei2020knowledge, author = {Scharei, Kristina and Heidecker, Florian and Bieshaar, Maarten}, journal = {arXiv e-prints}, keywords = {Robotics}, pages = {arXiv:2001.04835}, title = {{Knowledge Representations in Technical Systems – A Taxonomy}}, year = 2020 }
%0 Journal Article %1 scharei2020knowledge %A Scharei, Kristina %A Heidecker, Florian %A Bieshaar, Maarten %D 2020 %J arXiv e-prints %P arXiv:2001.04835 %T Knowledge Representations in Technical Systems -- A Taxonomy

2019[ to top ]

Towards Corner Case Identification in Cyclists’ Trajectories. Heidecker, F.; Bieshaar, M.; Sick, B. In ACM Computer Science in Cars Symposium (CSCS). ACM, 2019.
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
@inproceedings{heidecker2019towards, author = {Heidecker, F. and Bieshaar, M. and Sick, B.}, booktitle = {ACM Computer Science in Cars Symposium (CSCS)}, keywords = {imported}, publisher = {ACM}, title = {Towards Corner Case Identification in Cyclists’ Trajectories}, year = 2019 }
%0 Conference Paper %1 heidecker2019towards %A Heidecker, F. %A Bieshaar, M. %A Sick, B. %B ACM Computer Science in Cars Symposium (CSCS) %D 2019 %I ACM %T Towards Corner Case Identification in Cyclists’ Trajectories %U https://cscs19.cispa.saarland/files/cscs19_camera_ready/28_fhmbbs_19_cscs_.pdf