# Cooperative Starting Movement Detection of Cyclists Using Convolutional Neural Networks and a Boosted Stacking Ensemble

arXiv: https://arxiv.org/abs/1803.03487 · HTML: https://mlsanity.com/paper/1803.03487/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Mar 2018.

## Built on by (most cited first, 7 of 7)

- [Vulnerable Road User Detection and Safety Enhancement: A Comprehensive Survey](https://mlsanity.com/paper/2405.19202/) (2024)
- [The IMPTC Dataset: An Infrastructural Multi-Person Trajectory and Context Dataset](https://mlsanity.com/paper/2307.06165/) (2023)
- [Smart Infrastructure: A Research Junction](https://mlsanity.com/paper/2307.06177/) (2023)
- [Instance-Wise Monotonic Calibration by Constrained Transformation](https://mlsanity.com/paper/2507.06516/) (2025)
- [Adaptive Degradation Process with Deep Learning-Driven Trajectory](https://mlsanity.com/paper/2103.11598/) (2021)
- [Cyclist Intention Detection: A Probabilistic Approach](https://mlsanity.com/paper/2104.09176/) (2021)
- [A Review of Uncertainty Calibration in Pretrained Object Detectors](https://mlsanity.com/paper/2210.02935/) (2022)

## Abstract (arXiv)

In future, vehicles and other traffic participants will be interconnected and equipped with various types of sensors, allowing for cooperation on different levels, such as situation prediction or intention detection. In this article we present a cooperative approach for starting movement detection of cyclists using a boosted stacking ensemble approach realizing feature- and decision level cooperation. We introduce a novel method based on a 3D Convolutional Neural Network (CNN) to detect starting motions on image sequences by learning spatio-temporal features. The CNN is complemented by a smart device based starting movement detection originating from smart devices carried by the cyclist. Both model outputs are combined in a stacking ensemble approach using an extreme gradient boosting classifier resulting in a fast and yet robust cooperative starting movement detector. We evaluate our cooperative approach on real-world data originating from experiments with 49 test subjects consisting of 84 starting motions.