Time-of-Flight Based Optical Communication for Safety-Critical Applications in Autonomous Driving

Plank, Hannes; Holweg, Gerald; Steger, Christian; Druml, Norbert

doi:10.1007/978-3-319-45480-1_15

Cited by 4 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods originate with stereocameras [24], calculating the disparity between images. More modern approaches use either time-of-flight lasers [25] or triangulated light emission [26], where structured light triangulation improves depth precision to millimeters. Many of the best competition works utilize these methods [13]; again, the issue is cost.…”

Section: Presentation Attack Detection General Methodologiesmentioning

confidence: 99%

Improving Monocular Facial Presentation–Attack–Detection Robustness with Synthetic Noise Augmentations

Hassani,

Diedrich,

Malik

2023

Sensors

View full text Add to dashboard Cite

We present a synthetic augmentation approach towards improving monocular face presentation–attack–detection (PAD) robustness to real-world noise additions. Face PAD algorithms secure authentication systems against spoofing attacks, such as pictures, videos, and 2D-inspired masks. Best-in-class PAD methods typically use 3D imagery, but these can be expensive. To reduce application cost, there is a growing field investigating monocular algorithms that detect facial artifacts. These approaches work well in laboratory conditions, but can be sensitive to the imaging environment (e.g., sensor noise, dynamic lighting, etc.). The ideal solution for noise robustness is training under all expected conditions; however, this is time consuming and expensive. Instead, we propose that physics-informed noise-augmentations can pragmatically achieve robustness. Our toolbox contains twelve sensor and lighting effect generators. We demonstrate that our toolbox generates more robust PAD features than popular augmentation methods in noisy test-evaluations. We also observe that the toolbox improves accuracy on clean test data, suggesting that it inherently helps discern spoof artifacts from imaging artifacts. We validate this hypothesis through an ablation study, where we remove liveliness pairs (e.g., live or spoof imagery only for participants) to identify how much real data can be replaced with synthetic augmentations. We demonstrate that using these noise augmentations allows us to achieve better test accuracy while only requiring 30% of participants to be fully imaged under all conditions. These findings indicate that synthetic noise augmentations are a great way to improve PAD, addressing noise robustness while simplifying data collection.

show abstract

Section: Presentation Attack Detection General Methodologiesmentioning

confidence: 99%

Improving Monocular Facial Presentation–Attack–Detection Robustness with Synthetic Noise Augmentations

Hassani,

Diedrich,

Malik

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Hence, three different cases have to be considered. Background fluorescence with much longer lifetime than the modulation frequency will appear as an offset value on both separation capacities, which is eliminated by (4). Those with lifetimes shorter or equal than the reference fluorophore will be added to the reference intensity, which requires a calibration to take care of those proportions.…”

Section: Principle Of Operationmentioning

confidence: 99%

“…In order to decrease the influence of background fluorescence, we use an optical correlation sensor called P hotonic M ixer D evice (PMD) which correlates an optical with an electrical signal. This sensor type is widely applied in distance measurement systems as well as multiphoton tomography (MPT) and fluorescence lifetime imaging (FLIM) . The optical signal is the emitted light collected from two kinds of fluorophores with different lifetimes, excited by a quasi continuous light source.…”

Section: Principle Of Operationmentioning

confidence: 99%

Introduction of a New Method for a Quantitative Detection of Biological Analyte

Bier

Keusgen

Frey

2019

Physica Status Solidi (a)

View full text Add to dashboard Cite

Fluorescence spectroscopy is a method for clinical diagnostics and drug screening. The authors introduce a new way to detect fluorescence markers quantitatively by using an optical sensor which works as a correlation receiver. The evaluable signals from the sensor array are time‐resolved and, due to the sensor's characteristics, less affected by background fluorescence. Thereby, we expect a significant improvement of the sensor platform's sensitivity. A mathematical approach on how to analyze the time‐resolved signal from the sample is done in this paper as well as simulations to prove the approach.

show abstract

“…That is particularly useful for tracing non‐intelligent products such as electronic accessories, supplies, and consumables. Secondly, we can use the technique for identifying a transmitter in visible‐light communication (VLC) to thwart analogue‐domain attacks in VLC in the same way as RF fingerprinting [6].…”

Section: Introductionmentioning

confidence: 99%

Fingerprinting light emitting diodes using spectrometer

et al. 2019

View full text Add to dashboard Cite

Fingerprinting refers to a class of techniques to distinguish products using their unique features originated during production. Fingerprinting has a wide range of applications including supplychain integrity and device authentication. The authors propose the first fingerprinting technique of light-emitting diode (LED), which is pervasively used in electronics products. The key idea is to use spectral features of LEDs obtained by a spectrometer. Combined with a machine-learning classifier, the proposed method successfully distinguishes ten individual LED samples from the same lot at 99% accuracy.

show abstract

Time-of-Flight Based Optical Communication for Safety-Critical Applications in Autonomous Driving

Cited by 4 publications

References 17 publications

Improving Monocular Facial Presentation–Attack–Detection Robustness with Synthetic Noise Augmentations

Improving Monocular Facial Presentation–Attack–Detection Robustness with Synthetic Noise Augmentations

Introduction of a New Method for a Quantitative Detection of Biological Analyte

Fingerprinting light emitting diodes using spectrometer

Contact Info

Product

Resources

About