Event-Based Vision Meets Deep Learning on Steering Prediction for Self-Driving Cars

Maqueda, Ana I.; Loquercio, Antonio; Gallego, Guillermo; García, Narciso; Scaramuzza, Davide

doi:10.1109/cvpr.2018.00568

Cited by 441 publications

(356 citation statements)

References 19 publications

Supporting

Mentioning

328

Contrasting

Order By: Relevance

“…Maqueda et al . [MLG*18] propose a deep neural network approach to predict the steering angles of vehicles.…”

Section: Applications In Autonomous Drivingmentioning

confidence: 99%

A Survey on Visual Traffic Simulation: Models, Evaluations, and Applications in Autonomous Driving

Chao

et al. 2019

Computer Graphics Forum

View full text Add to dashboard Cite

Virtualized traffic via various simulation models and real‐world traffic data are promising approaches to reconstruct detailed traffic flows. A variety of applications can benefit from the virtual traffic, including, but not limited to, video games, virtual reality, traffic engineering and autonomous driving. In this survey, we provide a comprehensive review on the state‐of‐the‐art techniques for traffic simulation and animation. We start with a discussion on three classes of traffic simulation models applied at different levels of detail. Then, we introduce various data‐driven animation techniques, including existing data collection methods, and the validation and evaluation of simulated traffic flows. Next, we discuss how traffic simulations can benefit the training and testing of autonomous vehicles. Finally, we discuss the current states of traffic simulation and animation and suggest future research directions.

show abstract

“…Maqueda et al . [MLG*18] propose a deep neural network approach to predict the steering angles of vehicles.…”

Section: Applications In Autonomous Drivingmentioning

confidence: 99%

A Survey on Visual Traffic Simulation: Models, Evaluations, and Applications in Autonomous Driving

Chao

et al. 2019

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…Event-to-frame conversion works. There are several stateof-the-art works [12,19,24,25,36,40] proposed to convert asynchronous retinal events to synchronous frames. However, all these works rely on one or more empirical cut-off thresholds, which limits their applications.…”

Section: Related Workmentioning

confidence: 99%

“…Because the spatial neighborhood is defined in the context of a timestamp map, the fixed radius can be treated as another form of the time window. The representations in [12,25,36,40] respectively use a fixed size of time window as their cut-off thresholds. The Adaptive Time-Slice representation in [24] uses either a constant event number or a fixed search radius as its cut-off threshold.…”

Section: Related Workmentioning

confidence: 99%

“…Meanwhile, the object contours should not have too much displacement, and should not be too sparse. The state-of-theart event-to-frame conversion algorithms [12,19,24,25,36,40] use either a fixed time window or a constant event number as the cut-off threshold to perform the event-to-frame conversion. For the Fixed-Time-Window (FTW) event-to-frame conversion algorithms, we show some results obtained by an example FTW event-to-frame conversion algorithm using a fixed time window of 9 ms in the FTW Frames (a-c) of Fig.…”

Section: Adaptive Time-surface With Linear Time Decaymentioning

confidence: 99%

See 1 more Smart Citation

Asynchronous Tracking-by-Detection on Adaptive Time Surfaces for Event-based Object Tracking

Chen

Liang

et al. 2019

Proceedings of the 27th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Event cameras, which are asynchronous bio-inspired vision sensors, have shown great potential in a variety of situations, such as fast motion and low illumination scenes. However, most of the event-based object tracking methods are designed for scenarios with untextured objects and uncluttered backgrounds. There are few event-based object tracking methods that support bounding box-based object tracking. The main idea behind this work is to propose an asynchronous Event-based Tracking-by-Detection (ETD) method for generic bounding box-based object tracking. To achieve this goal, we present an Adaptive Time-Surface with Linear Time Decay (AT-SLTD) event-to-frame conversion algorithm, which asynchronously and effectively warps the spatio-temporal information of asynchronous retinal events to a sequence of ATSLTD frames with clear object contours. We feed the sequence of ATSLTD frames to the proposed ETD method to perform accurate and efficient object tracking, which leverages the high temporal resolution property of event cameras. We compare the proposed ETD method with seven popular object tracking methods, that are based on conventional cameras or event cameras, and two variants of ETD. The experimental results show the superiority of the proposed ETD method in handling various challenging environments.

show abstract

“…There is a class of cameras called event based cameras which encode information at the sensor level. Recently, deep learning algorithms were demonstrated on event based camera data (Maqueda et al, 2018).…”

Section: Use Cases In Automated Drivingmentioning

confidence: 99%

Exploring Deep Spiking Neural Networks for Automated Driving Applications

Mohapatra

Gotzig

Yogamani

et al. 2019

Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Application

View full text Add to dashboard Cite

Neural networks have become the standard model for various computer vision tasks in automated driving including semantic segmentation, moving object detection, depth estimation, visual odometry, etc. The main flavors of neural networks which are used commonly are convolutional (CNN) and recurrent (RNN). In spite of rapid progress in embedded processors, power consumption and cost is still a bottleneck. Spiking Neural Networks (SNNs) are gradually progressing to achieve low-power event-driven hardware architecture which has a potential for high efficiency. In this paper, we explore the role of deep spiking neural networks (SNN) for automated driving applications. We provide an overview of progress on SNN and argue how it can be a good fit for automated driving applications.

show abstract

Event-Based Vision Meets Deep Learning on Steering Prediction for Self-Driving Cars

Cited by 441 publications

References 19 publications

A Survey on Visual Traffic Simulation: Models, Evaluations, and Applications in Autonomous Driving

A Survey on Visual Traffic Simulation: Models, Evaluations, and Applications in Autonomous Driving

Asynchronous Tracking-by-Detection on Adaptive Time Surfaces for Event-based Object Tracking

Exploring Deep Spiking Neural Networks for Automated Driving Applications

Contact Info

Product

Resources

About