# Cyclist Intention Detection: A Probabilistic Approach

arXiv: https://arxiv.org/abs/2104.09176 · HTML: https://mlsanity.com/paper/2104.09176/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 29 references that are in the map.
- First posted on arXiv 19 Apr 2021.

## Builds on (most cited first, 8 of 8)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Speed/accuracy trade-offs for modern convolutional object detectors](https://mlsanity.com/paper/1611.10012/) (2016)
- [Pedestrian Path, Pose and Intention Prediction through Gaussian Process Dynamical Models and Pedestrian Activity Recognition](https://mlsanity.com/paper/2004.14747/) (2020)
- [Intentions of Vulnerable Road Users - Detection and Forecasting by Means of Machine Learning](https://mlsanity.com/paper/1803.03577/) (2018)
- [Cooperative Starting Movement Detection of Cyclists Using Convolutional Neural Networks and a Boosted Stacking Ensemble](https://mlsanity.com/paper/1803.03487/) (2018)
- [Early Start Intention Detection of Cyclists Using Motion History Images and a Deep Residual Network](https://mlsanity.com/paper/1803.02242/) (2018)
- [Quantile Surfaces -- Generalizing Quantile Regression to Multivariate Targets](https://mlsanity.com/paper/2010.05898/) (2020)

## Abstract (arXiv)

This article presents a holistic approach for probabilistic cyclist intention detection. A basic movement detection based on motion history images (MHI) and a residual convolutional neural network (ResNet) are used to estimate probabilities for the current cyclist motion state. These probabilities are used as weights in a probabilistic ensemble trajectory forecast. The ensemble consists of specialized models, which produce individual forecasts in the form of Gaussian distributions under the assumption of a certain motion state of the cyclist (e.g. cyclist is starting or turning left). By weighting the specialized models, we create forecasts in the from of Gaussian mixtures that define regions within which the cyclists will reside with a certain probability. To evaluate our method, we rate the reliability, sharpness, and positional accuracy of our forecasted distributions. We compare our method to a single model approach which produces forecasts in the form of Gaussian distributions and show that our method is able to produce more reliable and sharper outputs while retaining comparable positional accuracy. Both methods are evaluated using a dataset created at a public traffic intersection. Our code and the dataset are made publicly available.