Review of advanced driver assistance systems (ADAS)

Ziębiński, Adam; Cupek, Rafał; Grzechca, Damian; Chruszczyk, Ł.

doi:10.1063/1.5012394

Cited by 136 publications

(52 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…With the introduction of autonomous vehicles, and the explosion of drones for civilian applications, light detection and ranging (LIDAR) uses for collision avoidance and topological measurement is becoming ubiquitous. [21][22][23][24] Proc. of SPIE Vol.…”

Section: Holography For Lidarmentioning

confidence: 99%

Holography for automotive applications: from HUD to LIDAR

Blanche

Bigler

Draper

et al. 2018

Optical Data Storage 2018: Industrial Optical Devices and Systems

View full text Add to dashboard Cite

Holography can offer unique solutions to the specific problems faced by automotive optical systems. Frequently, when possibilities have been exhausted using refractive and reflective designs, diffraction can come to the rescue by opening a new dimension to explore. Holographic optical elements (HOEs), for example, are thin film optics that can advantageously replace lenses, prisms, or mirrors. Head up display (HUD) and LIDAR for autonomous vehicles are two of the systems where our group have used HOEs to provide original answers to the limitations of classical optic. With HUD, HOEs address the problems of the limited field of view, and small eye box usually found in projection systems. Our approach is to recycle the light multiple times inside a waveguide so the combiner can be as large as the entire windshield. In this system, a hologram is used to inject a small image at one end of a waveguide, and another hologram is used to extract the image several times, providing an expanded eye box. In the case of LIDAR systems, non-mechanical beam scanning based on diffractive spatial light modulator (SLM), are only able to achieve an angular range of few degrees. We used multiplexed volume holograms (VH) to amplify the initial diffraction angle from the SLM to achieve up to 4π steradian coverage in a compact form factor.

show abstract

Section: Holography For Lidarmentioning

confidence: 99%

Holography for automotive applications: from HUD to LIDAR

Blanche

Bigler

Draper

et al. 2018

Optical Data Storage 2018: Industrial Optical Devices and Systems

View full text Add to dashboard Cite

show abstract

“…Communication with the sensors is based on an I2C interface, SPI, RS232, GPIO and CAN. This allows typical ADAS modules [4] [6] or other solutions [7] to be connected and results in sensor fusion [8]. An STM32 is equipped with many more interfaces that are accessible to users than a RPi, which allows for greater system scalability.…”

Section: Amp Architecturementioning

confidence: 99%

“…The main purpose of this article is to verify the concept of distributed control architecture for the Autonomous Mobile Platform (AMP) with a focus on on-board communication that enables the efficiency of control algorithms to be increased by dividing the tasks related to the processing of environmental information that is collected by sensors. The proposed idea is presented in the section "AMP Architecture" using the example of a control system that is based on two data processing units: an STM32F3 Discovery board and a Raspberry Pi3 (RPi) and a number of sensors that are typical for Advanced Driver Assistance Systems (ADAS) [4]. The achieved efficiency of onboard the communication system is presented in the section "Experiment" and "Conclusions" are given at the end of this article.…”

Section: Introductionmentioning

confidence: 99%

Distributed control architecture for the autonomous mobile platform

Ziębiński

Cupek

Piech

2018

AIP Conference Proceedings

Self Cite

View full text Add to dashboard Cite

This paper presents a proof of the concept of distributed control architecture dedicated for the Autonomous Mobile Platform. The greatest advantage of the proposed solution is its scalability, which enables the application of advanced control algorithms that are based on multiple sensors that supply information to multiple processing units. The key is a highly effective on-board communication system. The proposed method is based on Serial Peripheral Interface SPI communication that joins the STM32 and Raspberry Pi processing units, which share the tasks of processing the signals that are necessary for AMP control. The proposed architecture and test results for on-board communication performance are presented.

show abstract

“…One of the most representative examples of improving safety is pedestrian detection with collision avoiding systems [15], which are increasingly used by well-known manufacturers of the automotive industry. Generally, these types of the methods are categorized as advanced driver assistance systems (ADAS) [16], which, in general, try to warn the driver in case of hazardous situations by stopping the car or only warning the driver about a probable near collision with a pedestrian or group of pedestrians in stationary or in a moving behavior. Information about some usage of pedestrian detection systems (PDS) in ADAS systems can be found in References [17,18].…”

Section: Introductionmentioning

confidence: 99%

Improved Human Detection with a Fusion of Laser Scanner and Vision/Infrared Information for Mobile Applications

2018

View full text Add to dashboard Cite

This paper presents a method for human detection using a laser scanner with vision or infrared images. Mobile applications require reliable and efficient methods for human detection, especially as a part of driver assistance systems, including pedestrian collision systems. The authors propose an efficient method for multimodal human detection based on a combination of the features and context information. Strictly, the human is detected in the vision/infrared images using a combination of local binary patterns and histogram of oriented gradients features with a neural network in a cascade manner. Next, using coordinates of detected humans from the vision system, the moving trajectory is predicted until the scanner working distance is reached by the individual human. Then the segmentation of data from the laser scanner is further carried out with respect to the predicted trajectory. Finally, human detection in the laser scanner working distance is performed based on modelling of the human legs. The modelling is based on the adaptive breakpoint detection algorithm and proposed improved polylines definition and fitting algorithm. The authors conducted a set of experiments in predefined scenarios, discussed the identified weakness and advantages of the proposed method, and outlined detailed future work, especially for night-time and low-light conditions.

show abstract

Review of advanced driver assistance systems (ADAS)

Cited by 136 publications

References 10 publications

Holography for automotive applications: from HUD to LIDAR

Holography for automotive applications: from HUD to LIDAR

Distributed control architecture for the autonomous mobile platform

Improved Human Detection with a Fusion of Laser Scanner and Vision/Infrared Information for Mobile Applications

Contact Info

Product

Resources

About