End-to-end Prediction of Driver Intention using 3D Convolutional Neural Networks

Gebert, Patrick; Roitberg, Alina; Haurilet, Monica; Stiefelhagen, Rainer

doi:10.1109/ivs.2019.8814249

Cited by 58 publications

(52 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using videos of drivers, endto-end prediction is also accurate. For instance, in [50] the 3D ResNeXt-101 with a LSTM layer on the top is trained in end-to-end style. The results in [51] prove that videos towards roads have complementary information as driver videos, which should also be considered in driver maneuver prediction.…”

Section: B Driving Assistancementioning

confidence: 99%

Artificial Intelligence Methods in In-Cabin Use Cases: A Survey

Han

Hellert

et al. 2021

Preprint

View full text Add to dashboard Cite

As interest in autonomous driving increases, efforts are being made to meet requirements for the high-level automation of vehicles. In this context, the functionality inside the vehicle cabin plays a key role in ensuring a safe and pleasant journey for driver and passenger alike. At the same time, recent advances in the field of artificial intelligence (AI) have enabled a whole range of new applications and assistance systems to solve automated problems in the vehicle cabin. This paper presents a thorough survey on existing work that utilizes AI methods for use-cases inside the driving cabin, focusing, in particular, on application scenarios related to (1) driving safety and (2) driving comfort. Results from the surveyed works show that AI technology has a promising future in tackling in-cabin tasks within the autonomous driving aspect.

show abstract

Section: B Driving Assistancementioning

confidence: 99%

Artificial Intelligence Methods in In-Cabin Use Cases: A Survey

Han

Hellert

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Additionally, there were related issues such as driver intention prediction to anticipate driver maneuvers. In Reference [49], Gebert et al proposed an end-to-end network architecture which consisted of FlowNet [26] to extract optical flow, a 3D residual network for maneuver classification, and an LSTM model for handling temporal data with varying length. Note that FlowNet was used to extract the optical flow in the video interpolation as well; however, labeling the ground-truth flow data to train FlowNet for a specific task is hard work and time-consuming.…”

Section: Related Workmentioning

confidence: 99%

Driver Behavior Analysis via Two-Stream Deep Convolutional Neural Network

et al. 2020

View full text Add to dashboard Cite

According to the World Health Organization global status report on road safety, traffic accidents are the eighth leading cause of death in the world, and nearly one-fifth of the traffic accidents were cause by driver distractions. Inspired by the famous two-stream convolutional neural network (CNN) model, we propose a driver behavior analysis system using one spatial stream ConvNet to extract the spatial features and one temporal stream ConvNet to capture the driver’s motion information. Instead of using three-dimensional (3D) ConvNet, which would suffer from large parameters and the lack of a pre-trained model, two-dimensional (2D) ConvNet is used to construct the spatial and temporal ConvNet streams, and they were pre-trained by the large-scale ImageNet. In addition, in order to integrate different modalities, the feature-level fusion methodology was applied, and a fusion network was designed to integrate the spatial and temporal features for further classification. Moreover, a self-compiled dataset of 10 actions in the vehicle was established. According to the experimental results, the proposed system can increase the accuracy rate by nearly 30% compared to the two-stream CNN model with a score-level fusion.

show abstract

“…Uncertainty-aware models are vital for safety-critical applications of activity recognition approaches, which range from robotics and manufacturing to autonomous driving and surveillance [7], [26], [28]. While obtaining well-calibrated probability estimates is a growing area in general image recognition [8], [10], this performance aspect did not yet receive any attention in the field of video classification.…”

Section: Introductionmentioning

confidence: 99%

Uncertainty-sensitive Activity Recognition: A Reliability Benchmark and the CARING Models

Roitberg

Haurilet

Martínez

et al. 2021

2020 25th International Conference on Pattern Recognition (ICPR)

Self Cite

View full text Add to dashboard Cite

Beyond assigning the correct class, an activity recognition model should also be able to determine, how certain it is in its predictions. We present the first study of how well the confidence values of modern action recognition architectures indeed reflect the probability of the correct outcome and propose a learning-based approach for improving it. First, we extend two popular action recognition datasets with a reliability benchmark in form of the expected calibration error and reliability diagrams. Since our evaluation highlights that confidence values of standard action recognition architectures do not represent the uncertainty well, we introduce a new approach which learns to transform the model output into realistic confidence estimates through an additional calibration network. The main idea of our Calibrated Action Recognition with Input Guidance (CARING) model is to learn an optimal scaling parameter depending on the video representation. We compare our model with the native action recognition networks and the temperature scaling approach -a wide spread calibration method utilized in image classification. While temperature scaling alone drastically improves the reliability of the confidence values, our CARING method consistently leads to the best uncertainty estimates in all benchmark settings.

show abstract

End-to-end Prediction of Driver Intention using 3D Convolutional Neural Networks

Cited by 58 publications

References 13 publications

Artificial Intelligence Methods in In-Cabin Use Cases: A Survey

Artificial Intelligence Methods in In-Cabin Use Cases: A Survey

Driver Behavior Analysis via Two-Stream Deep Convolutional Neural Network

Uncertainty-sensitive Activity Recognition: A Reliability Benchmark and the CARING Models

Contact Info

Product

Resources

About