The Effect of Spray Water on an Automotive LIDAR Sensor: A Real-Time Simulation Study

Vargasrivero, Jose Roberto; Gerbich, Thiemo; Buschardt, Boris; Chen, Jia

doi:10.1109/tiv.2021.3067892

Cited by 15 publications

(20 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The region at which spray detections are usually seen, based on our measurements on the highway and considering that the spray is generated by one leading vehicle (LV), corresponds approximately to 6 m to each side of the ego vehicle and up to 20 m in front of it [ 10 ]. These measurements were taken with an average ego speed of 89 km/h.…”

Section: Methodsmentioning

confidence: 99%

“…The simulation setup used is presented in Figure 4 . This setup is based on the model introduced in [ 10 ]. The original simulation setup was based on the following assumptions: Simulating real water drops as well as the exact forces that act upon them cannot be done in real time.…”

Section: Methodsmentioning

confidence: 99%

“…Recently, LIDAR sensors have also been used mostly due to their high resolution, ability to work under low light conditions and direct distance measurement [ 4 , 5 ]. However, the high resolution obtained by using infrared light comes at the cost of a reduced performance when dirt [ 6 ], rain, fog [ 7 ], snow [ 8 ], exhaust gases [ 9 ] and spray water [ 10 ] are present. Besides reducing range, these phenomena cause extra detections which can have negative effects like phantom braking.…”

Section: Introductionmentioning

confidence: 99%

“…Spray water is especially problematic because it can generate point clouds with characteristics that highly resemble those of solid objects. Figure 1 shows a real example in which the spray cloud generates detections with a shape close to the ‘L’ shape of a vehicle [ 10 ]. True positives are needed to train a classifier to remove this kind of false positive.…”

Section: Introductionmentioning

confidence: 99%

“…In our case, a physically based render is used to simulate the LIDAR sensor [ 27 ] with material properties based on real reflection values. Spray and rain are simulated using particle systems which generate detections with a spatial distribution similar to those caused by real spray [ 10 ]. After rendering, the detections caused by the obstacle are extracted and concatenated into the real point clouds.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Data Augmentation of Automotive LIDAR Point Clouds under Adverse Weather Situations

Rivero

Gerbich

Buschardt

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

In contrast to previous works on data augmentation using LIDAR (Light Detection and Ranging), which mostly consider point clouds under good weather conditions, this paper uses point clouds which are affected by spray. Spray water can be a cause of phantom braking and understanding how to handle the extra detections caused by it is an important step in the development of ADAS (Advanced Driver Assistance Systems)/AV (Autonomous Vehicles) functions. The extra detections caused by spray cannot be safely removed without considering cases in which real solid objects may be present in the same region in which the detections caused by spray take place. As collecting real examples would be extremely difficult, the use of synthetic data is proposed. Real scenes are reconstructed virtually with an added extra object in the spray region, in a way that the detections caused by this obstacle match the characteristics a real object in the same position would have regarding intensity, echo number and occlusion. The detections generated by the obstacle are then used to augment the real data, obtaining, after occlusion effects are added, a good approximation of the desired training data. This data is used to train a classifier achieving an average F-Score of 92. The performance of the classifier is analyzed in detail based on the characteristics of the synthetic object: size, position, reflection, duration. The proposed method can be easily expanded to different kinds of obstacles and classifier types.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Data Augmentation of Automotive LIDAR Point Clouds under Adverse Weather Situations

Rivero

Gerbich

Buschardt

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

Event Vision for Autonomous Off-Road Navigation

AlRemeithi

Zayer

Dias

et al. 2023

Artificial Intelligence for Robotics and Autonomous Systems Applications

View full text Add to dashboard Cite

NIR-Triggered High-Efficiency Self-Healable Protective Optical Coating for Vision Systems

Jeong

Lee

Bae

et al. 2023

ACS Appl. Mater. Interfaces

View full text Add to dashboard Cite

Recently, self-healing materials have evolved to recover specific functions such as electronic, magnetic, acoustic, structural or hierarchical, and biological properties. In particular, the development of self-healing protection coatings that can be applied to lens components in vision systems such as augmented reality glasses, actuators, and image and time-of-flight sensors has received intensive attention from the industry. In the present study, we designed polythiourethane dynamic networks containing a photothermal N-butyl-substituted diimmonium borate dye to demonstrate their potential applications in self-healing protection coatings for the optical components of vision systems. The optimized self-healing coating exhibited a high transmittance (∼95% in the visible-light region), tunable refractive index (up to 1.6), a moderate Abbe number (∼35), and high surface hardness (>200 MPa). When subjected to near-infrared (NIR) radiation (1064 nm), the surface temperature of the coating increased to 75 °C via the photothermal effect and self-healing of the scratched coatings occurred via a dynamic thiourethane exchange reaction. The coating was applied to a lens protector, and its self-healing performance was demonstrated. The light signal distorted by the scratched surface of the coating was perfectly restored after NIR-induced self-healing. The photoinduced self-healing process can also autonomously occur under sunlight with low energy consumption.

show abstract

The Effect of Spray Water on an Automotive LIDAR Sensor: A Real-Time Simulation Study

Cited by 15 publications

References 43 publications

Data Augmentation of Automotive LIDAR Point Clouds under Adverse Weather Situations

Data Augmentation of Automotive LIDAR Point Clouds under Adverse Weather Situations

Event Vision for Autonomous Off-Road Navigation

NIR-Triggered High-Efficiency Self-Healable Protective Optical Coating for Vision Systems

Contact Info

Product

Resources

About