Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning (2020-08-01T00:00:00.000000Z)

TL;DR

An uncertainty-based accident anticipation model with spatio-temporal relational learning that sequentially predicts the probability of traffic accident occurrence with dashcam videos is proposed to take advantage of graph convolution and recurrent networks for relational feature learning, and leverage Bayesian neural networks to address the intrinsic variability of latent relational representations.

Abstract

Traffic accident anticipation aims to predict accidents from dashcam videos as early as possible, which is critical to safety-guaranteed self-driving systems. With cluttered traffic scenes and limited visual cues, it is of great challenge to predict how long there will be an accident from early observed frames. Most existing approaches are developed to learn features of accident-relevant agents for accident anticipation, while ignoring the features of their spatial and temporal relations. Besides, current deterministic deep neural networks could be overconfident in false predictions, leading to high risk of traffic accidents caused by self-driving systems. In this paper, we propose an uncertainty-based accident anticipation model with spatio-temporal relational learning. It sequentially predicts the probability of traffic accident occurrence with dashcam videos. Specifically, we propose to take advantage of graph convolution and recurrent networks for relational feature learning, and leverage Bayesian neural networks to address the intrinsic variability of latent relational representations. The derived uncertainty-based ranking loss is found to significantly boost model performance by improving the quality of relational features. In addition, we collect a new Car Crash Dataset (CCD) for traffic accident anticipation which contains environmental attributes and accident reasons annotations. Experimental results on both public and the newly-compiled datasets show state-of-the-art performance of our model. Our code and CCD dataset are available at https://github.com/Cogito2012/UString.

Authors

Wentao Bao

5 papers

Qi Yu

3 papers

Yu Kong

2 papers

TL;DR

Abstract

Authors

References42 items

PyTorch: An Imperative Style, High-Performance Deep Learning Library

Predicting Traffic Accidents with Event Recorder Data

Bayesian Graph Convolution LSTM for Skeleton Based Action Recognition

Variational Graph Recurrent Neural Networks

Future Event Prediction: If and When

Traffic Risk Assessment: A Two-Stream Approach Using Dynamic-Attention

DADA-2000: Can Driving Accident be Predicted by Driver Attentionƒ Analyzed by A Benchmark

Unsupervised Traffic Accident Detection in First-Person Videos

CADP: A Novel Dataset for CCTV Traffic Camera based Accident Analysis

Uncertainty Estimations by Softplus normalization in Bayesian Convolutional Neural Networks with Variational Inference

Bayesian Convolutional Neural Networks with Variational Inference

BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning

Uncertainty quantification using Bayesian neural networks in classification: Application to ischemic stroke lesion segmentation

Anticipating Traffic Accidents with Adaptive Loss and Large-Scale Incident DB

Cascade R-CNN: Delving Into High Quality Object Detection

Attention is All you Need

Agent-Centric Risk Assessment: Accident Anticipation and Risky Region Localization

What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?

Structured Sequence Modeling with Graph Convolutional Recurrent Networks

Feature Pyramid Networks for Object Detection

Variational Graph Auto-Encoders

Anticipating Accidents in Dashcam Videos

Aggregated Residual Transformations for Deep Neural Networks

Quasi-Recurrent Neural Networks

Semi-Supervised Classification with Graph Convolutional Networks

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

Learning Activity Progression in LSTMs for Activity Detection and Early Detection

Weight Uncertainty in Neural Network

A Recurrent Latent Variable Model for Sequential Data

Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

A Critical Review of Recurrent Neural Networks for Sequence Learning

Weight Uncertainty in Neural Networks

Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

Stochastic Backpropagation and Approximate Inference in Deep Generative Models

Auto-Encoding Variational Bayes

Are we ready for autonomous driving? The KITTI vision benchmark suite

Practical Variational Inference for Neural Networks

Long Short-Term Memory

Transforming Neural-Net Output Levels to Probability Distributions

Kaiming He, Bharath Hariharan, and Serge Belongie

Bayesian learning for neural networks

Field of Study

Journal Information

Name

Venue Information

Name

Type

URL

Alternate Names