Active gated imaging in driver assistance system

Grauer, Yoav

doi:10.1515/aot-2014-0001

Cited by 14 publications

(8 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the industry side, [113] first apply a NIR range-gated camera to aid driving at night. Grauer et al [114] and [115] present a high resolution (1.2M pixel) range-gated camera based on NIR VCSEL laser (808nm) and a gated CMOS image sensor. This sensor is suitable for use in active safety systems such as vulnerable object detection, forward collision warning, lane departure warning, traffic sign detection, etc.…”

Section: B Applications Of In Adas/admentioning

confidence: 99%

Unconventional Visual Sensors for Autonomous Vehicles

Li¹,

Moreau²,

Ibañez‐Guzmán³

2022

Preprint

View full text Add to dashboard Cite

Autonomous vehicles rely on perception systems to understand their surroundings for further navigation missions. Cameras are essential for perception systems due to the advantages of object detection and recognition provided by modern computer vision algorithms, comparing to other sensors, such as LiDARs and radars. However, limited by its inherent imaging principle, a standard RGB camera may perform poorly in a variety of adverse scenarios, including but not limited to: low illumination, high contrast, bad weather such as fog/rain/snow, etc. Meanwhile, estimating the 3D information from the 2D image detection is generally more difficult when compared to LiDARs or radars. Several new sensing technologies have emerged in recent years to address the limitations of conventional RGB cameras. In this paper, we review the principles of four novel image sensors: infrared cameras, range-gated cameras, polarization cameras, and event cameras. Their comparative advantages, existing or potential applications, and corresponding data processing algorithms are all presented in a systematic manner. We expect that this study will assist practitioners in the autonomous driving society with new perspectives and insights.

show abstract

Section: B Applications Of In Adas/admentioning

confidence: 99%

Unconventional Visual Sensors for Autonomous Vehicles

Li¹,

Moreau²,

Ibañez‐Guzmán³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In order to provide a variety of training cues for ZeroScatter, we utilize an adverse weather dataset containing real world automotive captures from northern Europe [5]. In addition to RGB captures, the dataset consists of multi-modal data in the form of gated images [15], multi-view stereo data, and temporal sequences.…”

Section: Domain Adaptationmentioning

confidence: 99%

“…We employ a multi-modal indirect supervision approach to facilitate training on real data, which makes use of emerging gated imagers [15,17,5] that uses active flash illumination to acquire high contrast images by temporally gating out scattering components.…”

Section: Multi-modal Indirect Supervisionmentioning

confidence: 99%

ZeroScatter: Domain Transfer for Long Distance Imaging and Vision through Scattering Media

Shi¹,

Tseng²,

Bijelic³

et al. 2021

Preprint

View full text Add to dashboard Cite

Adverse weather conditions, including snow, rain, and fog pose a challenge for both human and computer vision in outdoor scenarios. Handling these environmental conditions is essential for safe decision making, especially in autonomous vehicles, robotics, and drones. Most of today's supervised imaging and vision approaches, however, rely on training data collected in the real world that is biased towards good weather conditions, with dense fog, snow, and heavy rain as outliers in these datasets. Without training data, let alone paired data, existing autonomous vehicles often limit themselves to good conditions and stop when dense fog or snow is detected. In this work, we tackle the lack of supervised training data by combining synthetic and indirect supervision. We present ZeroScatter, a domain transfer method for converting RGB-only captures taken in adverse weather into clear daytime scenes. ZeroScatter exploits model-based, temporal, multi-view, multi-modal, and adversarial cues in a joint fashion, allowing us to train on unpaired, biased data. We assess the proposed method using real-world captures, and the proposed method outperforms existing monocular de-scattering approaches by 2.8 dB PSNR on controlled fog chamber measurements.

show abstract

“…Gated imaging has first been proposed by Heckman et al [21]. This acquisition mode allows to gate out backscatter from fog, rain, and snow [18]. Busck et al [3,6,7] use gated imaging for high-resolution depth sensing by capturing large sequences of narrow gated slices.…”

Section: Related Workmentioning

confidence: 99%

“…Note that using narrow slices does not offer a solution, because the slice width is inversely proportional to the number of captures, and thus frame-rate and narrow slices also means integrating less photons. With maximum frame rates of 120 Hz to 240 Hz, existing systems [18] are limited to a range of 4 to 7 slices for dynamic scenes.…”

Section: Introductionmentioning

confidence: 99%

Gated2Depth: Real-Time Dense Lidar From Gated Images

Gruber

Julca-Aguilar²,

Bijelic

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

We present an imaging framework which converts three images from a gated camera into high-resolution depth maps with depth accuracy comparable to pulsed lidar measurements. Existing scanning lidar systems achieve low spatial resolution at large ranges due to mechanicallylimited angular sampling rates, restricting scene understanding tasks to close-range clusters with dense sampling. Moreover, today's pulsed lidar scanners suffer from high cost, power consumption, large form-factors, and they fail in the presence of strong backscatter. We depart from point scanning and demonstrate that it is possible to turn a low-cost CMOS gated imager into a dense depth camera with at least 80 m range -by learning depth from three gated images. The proposed architecture exploits semantic context across gated slices, and is trained on a synthetic discriminator loss without the need of dense depth labels. The proposed replacement for scanning lidar systems is real-time, handles back-scatter and provides dense depth at long ranges. We validate our approach in simulation and on real-world data acquired over 4,000 km driving in northern Europe. Data and code are available at

show abstract

Active gated imaging in driver assistance system

Cited by 14 publications

References 1 publication

Unconventional Visual Sensors for Autonomous Vehicles

Unconventional Visual Sensors for Autonomous Vehicles

ZeroScatter: Domain Transfer for Long Distance Imaging and Vision through Scattering Media

Gated2Depth: Real-Time Dense Lidar From Gated Images

Contact Info

Product

Resources

About