Through the windshield driver recognition

Cornett, David; Yen, A.; Nayola, Grace; Diane, Montez,; Johnson, Christi; Baird, Seth T.; Santos-Villalobos, Hector; Bolme, David S.

doi:10.2352/issn.2470-1173.2019.13.coimg-140

Cited by 3 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We utilize this method of registration to achieve accurate correspondence and alignment without the need to detect facial landmark points, which are often noisy or incorrect within our dataset. It should be noted that this method deviates from the previous work,, 3 which uses Hamming windows to perform alignment instead. The images are then cropped to 256 × 256 pixels and then fed into the HDR fusion neural network outlined in Figure 5.…”

Section: Overview Of Image Pipelinementioning

confidence: 86%

“…• PeceptionGAN 3 is a GAN network trained specifically for visual perception and was the initial design for the system used in. 3 To analyze the efficacy of MU-Net, we performed a verification study on the dataset introduced in Section 7.1, comparing performance against the 5 baselines described in Section 7.2. We also include the baseline Single Camera, which uses a randomly-selected, non-processed image from each HDR burst.…”

Section: Baseline Methodsmentioning

confidence: 99%

“…Most external driver recognition research has been performed in the commercial sector 7 and public sector. 8 Beyond an initial case study at Oak Ridge National Laboratory, 3 very little open research has been published on the topic. While little work has been done in the field of driver recognition through the windshield , there has been significant related work two related fields: Vehicle occupancy detection, and glass artifact suppression.…”

Section: Related Workmentioning

confidence: 99%

“…To provide the best possible input to a deep learning algorithm, a custom multi-camera imaging system was developed to specifically mitigate these hurdles while remaining non-intrusive. 3 The system is modular in design, where each unit is composed of both an imaging system and an associated computational system, seen in Figures 2, 3, and 4. The raw images captured by the system can subsequently be processed by any HDR method to ultimately provide the processed input to facial recognition software.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

The Mertens Unrolled Network (MU-Net): A high dynamic range fusion neural network for through the windshield driver recognition

Ruby

Bolme

Brogan

et al. 2020

Autonomous Systems: Sensors, Processing, and Security for Vehicles and Infrastructure 2020

Self Cite

View full text Add to dashboard Cite

Face recognition of vehicle occupants through windshields in unconstrained environments poses a number of unique challenges ranging from glare, poor illumination, driver pose and motion blur. In this paper, we further develop the hardware and software components of a custom vehicle imaging system to better overcome these challenges. After the build out of a physical prototype system that performs High Dynamic Range (HDR) imaging, we collect a small dataset of through-windshield image captures of known drivers. We then re-formulate the classical Mertens-Kautz-Van Reeth HDR fusion algorithm as a pre-initialized neural network, which we name the Mertens Unrolled Network (MU-Net), for the purpose of fine-tuning the HDR output of through-windshield images. Reconstructed faces from this novel HDR method are then evaluated and compared against other traditional and experimental HDR methods in a pre-trained state-of-the-art (SOTA) facial recognition pipeline, verifying the efficacy of our approach.

show abstract

Section: Overview Of Image Pipelinementioning

confidence: 86%

Section: Baseline Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

The Mertens Unrolled Network (MU-Net): A high dynamic range fusion neural network for through the windshield driver recognition

Ruby

Bolme

Brogan

et al. 2020

Autonomous Systems: Sensors, Processing, and Security for Vehicles and Infrastructure 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Cornett et al explored the construction of a multi-unit computational camera system to get consistent face recognition results [90,91]. The system performs HDR (High Dynamic Range) imagining to create a dataset of through-windshield images.…”

Section: Noninvasive Occupancy Estimation Methodsmentioning

confidence: 99%

Passenger Occupancy Estimation in Vehicles: A Review of Current Methods and Research Challenges

et al. 2023

View full text Add to dashboard Cite

Passenger detection and occupancy estimation are vital tasks in many fields. The existing literature emphasises that the increasing demand for such systems will continue to grow. This paper reviews the existing literature specializing in the field of transportation safety and efficiency concerning occupancy estimation in vehicles and passenger detection at public transport stations. A comparison between different approaches to passenger estimation is presented. Discussion on the advantages and disadvantages is highlighted. Hence, this paper provides an analysis of 146 papers on the current state of the field. This review paper concludes that invasive methods provide high accuracy with relatively cheap implementation, while noninvasive systems do not violate passenger privacy but lack state-of-the-art accuracy. Future work will include a systematic literature review and a comparative analysis of systems considering the existing window tinting and solar windshields heavily blocking certain parts of the electromagnetic spectrum. Moreover, future work will investigate the critical challenges of noninvasive passenger estimation in different types of vehicles: trucks, buses, or even motorcycles.

show abstract

VDiSC: An Open Source Framework for Distributed Smart City Vision and Biometric Surveillance Networks

Brogan¹,

Barber²,

Cornett³

et al. 2023

2023 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)

View full text Add to dashboard Cite

Through the windshield driver recognition

Cited by 3 publications

References 0 publications

The Mertens Unrolled Network (MU-Net): A high dynamic range fusion neural network for through the windshield driver recognition

The Mertens Unrolled Network (MU-Net): A high dynamic range fusion neural network for through the windshield driver recognition

Passenger Occupancy Estimation in Vehicles: A Review of Current Methods and Research Challenges

VDiSC: An Open Source Framework for Distributed Smart City Vision and Biometric Surveillance Networks

Contact Info

Product

Resources

About