Benjamin Bauchwitz
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Benjamin Bauchwitz has a total of 1 co-authors. Here are the top co-authors by number of shared publications:
- M. L. Cummings
George Mason University, Fairfax, VA, USA
3 shared publications
Latest Publications
- Open Access
- 19 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 9778-9787
Modeling Image Segmentation Label Noise Through Concave Region Removal
The effects of label noise geometry on image segmentation model training are under-studied, in part because prevailing segmentation metrics such as the Intersection over Union are based on pixel counts and cannot describe spatial properties of label noise. It is well established that the degree of label noise randomness affects training, however, the effects of non-random geometric label noise have not been evaluated. To this end, we describe a new class of non-random geometric label noise characterized by removal of concave regions from connected components in segmentation masks. This class of label noise geometry is motivated by the observation that both human and automated annotations have vulnerabilities that disproportionately affect concave regions. We validate this class of label noise by demonstrating its prevalence in a dataset containing noisy crowdsourced labels for the PASCAL, BDD100K, and COCO benchmarks. We then show that concave region label noise affects model training differently than uniformly applied geometric transformations across a range of model architectures and image domains. These results motivate the study of new segmentation metrics better tuned to detect label noise geometries most detrimental to model training.
- 19 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 9778-9787
Open AccessModeling Image Segmentation Label Noise Through Concave Region Removal
The effects of label noise geometry on image segmentation model training are under-studied, in part because prevailing segmentation metrics such as the Intersection over Union are based on pixel counts and cannot describe spatial properties of label noise. It is well established that the degree of label noise randomness affects training, however, the effects of non-random geometric label noise have not been evaluated. To this end, we describe a new class of non-random geometric label noise characterized by removal of concave regions from connected components in segmentation masks. This class of label noise geometry is motivated by the observation that both human and automated annotations have vulnerabilities that disproportionately affect concave regions. We validate this class of label noise by demonstrating its prevalence in a dataset containing noisy crowdsourced labels for the PASCAL, BDD100K, and COCO benchmarks. We then show that concave region label noise affects model training differently than uniformly applied geometric transformations across a range of model architectures and image domains. These results motivate the study of new segmentation metrics better tuned to detect label noise geometries most detrimental to model training.
- Open Access
- 4 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 10 (11) , 4903-4912
Identifying Research Gaps Through Self-Driving Car Data Analysis
There are currently around thirty companies testing self-driving cars in San Francisco, CA, effectively creating a living laboratory. Of these companies, only Waymo is engaged in commercial operations, while Zoox conducts routine driverless testing operations in San Francisco. Despite these successes, federal investigations have been opened into both companies for safety concerns, and Cruise is attempting to reinstate its permit after a near-fatal pedestrian crash. An analysis of these three companies' crash data from required reporting illustrates that many areas of self-driving need improvement. The most significant crash type for Waymo and Zoox are struck-from-behind events, while Cruise struggled most with unexpected actions by others. Computer vision systems are very brittle and likely play an outsized role in crashes. Self-driving cars also struggle to reason under uncertainty, and simulations are not effectively bridging the physical-to-real-world testing gap. This analysis underscores that research is lacking, especially for artificial intelligence involving computer vision and reasoning under uncertainty.
- 4 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 10 (11) , 4903-4912
Open AccessIdentifying Research Gaps Through Self-Driving Car Data Analysis
There are currently around thirty companies testing self-driving cars in San Francisco, CA, effectively creating a living laboratory. Of these companies, only Waymo is engaged in commercial operations, while Zoox conducts routine driverless testing operations in San Francisco. Despite these successes, federal investigations have been opened into both companies for safety concerns, and Cruise is attempting to reinstate its permit after a near-fatal pedestrian crash. An analysis of these three companies' crash data from required reporting illustrates that many areas of self-driving need improvement. The most significant crash type for Waymo and Zoox are struck-from-behind events, while Cruise struggled most with unexpected actions by others. Computer vision systems are very brittle and likely play an outsized role in crashes. Self-driving cars also struggle to reason under uncertainty, and simulations are not effectively bridging the physical-to-real-world testing gap. This analysis underscores that research is lacking, especially for artificial intelligence involving computer vision and reasoning under uncertainty.
- Open Access
- 19 January 2022
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2676 (5) , 489-499
Effects of Individual Vehicle Differences on Advanced Driver-Assist System Takeover Alert Behavior
Disengagement of advanced driver-assist systems (ADAS) has significant safety implications in partially automated vehicles where drivers may not be paying attention; this requires rigorous testing to ensure vehicles can safely transfer control to drivers. Existing testing and regulation on this topic are minimal, and do not address the role of difficult-to-measure but potentially important variables relating to individual vehicle differences or variations in environmental conditions. This study assessed variability in takeover alerting performance in three Model 3 Tesla vehicles in a demanding driving setting on a closed track. Results revealed that once an alerting sequence had begun, the ADAS systems performed as designed, but the vehicles were highly variable in the timing of alert initiation following the loss of lane marking tracking. In addition, luminosity and sun angle were found to potentially have a role in alert initiation, but dashboard-mounted cameras may be insufficient for measuring variations in atmospheric brightness. We recommend that future work studies brightness, as well as more comprehensive sampling guidelines for vehicle test protocols to ensure differences are adequately considered.
- 19 January 2022
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2676 (5) , 489-499
Open AccessEffects of Individual Vehicle Differences on Advanced Driver-Assist System Takeover Alert Behavior
Disengagement of advanced driver-assist systems (ADAS) has significant safety implications in partially automated vehicles where drivers may not be paying attention; this requires rigorous testing to ensure vehicles can safely transfer control to drivers. Existing testing and regulation on this topic are minimal, and do not address the role of difficult-to-measure but potentially important variables relating to individual vehicle differences or variations in environmental conditions. This study assessed variability in takeover alerting performance in three Model 3 Tesla vehicles in a demanding driving setting on a closed track. Results revealed that once an alerting sequence had begun, the ADAS systems performed as designed, but the vehicles were highly variable in the timing of alert initiation following the loss of lane marking tracking. In addition, luminosity and sun angle were found to potentially have a role in alert initiation, but dashboard-mounted cameras may be insufficient for measuring variations in atmospheric brightness. We recommend that future work studies brightness, as well as more comprehensive sampling guidelines for vehicle test protocols to ensure differences are adequately considered.