Saved in:
Bibliographic Details
Main Authors: Bouraffa, Tayssir, Carlson, Elias Kjellberg, Wessman, Erik, Nouri, Ali, Lamart, Pierre, Berger, Christian
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.00768
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917739369594880
author Bouraffa, Tayssir
Carlson, Elias Kjellberg
Wessman, Erik
Nouri, Ali
Lamart, Pierre
Berger, Christian
author_facet Bouraffa, Tayssir
Carlson, Elias Kjellberg
Wessman, Erik
Nouri, Ali
Lamart, Pierre
Berger, Christian
contents Gathering data and identifying events in various traffic situations remains an essential challenge for the systematic evaluation of a perception system's performance. Analyzing large-scale, typically unstructured, multi-modal, time series data obtained from video, radar, and LiDAR is computationally demanding, particularly when meta-information or annotations are missing. We compare Optical Flow (OF) and Deep Learning (DL) to feed computationally efficient event detection via space-filling curves on video data from a forward-facing, in-vehicle camera. Our first approach leverages unexpected disturbances in the OF field from vehicle surroundings; the second approach is a DL model trained on human visual attention to predict a driver's gaze to spot potential event locations. We feed these results to a space-filling curve to reduce dimensionality and achieve computationally efficient event retrieval. We systematically evaluate our concept by obtaining characteristic patterns for both approaches from a large-scale virtual dataset (SMIRK) and applied our findings to the Zenseact Open Dataset (ZOD), a large multi-modal, real-world dataset, collected over two years in 14 different European countries. Our results yield that the OF approach excels in specificity and reduces false positives, while the DL approach demonstrates superior sensitivity. Both approaches offer comparable processing speed, making them suitable for real-time applications.
format Preprint
id arxiv_https___arxiv_org_abs_2408_00768
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Comparing Optical Flow and Deep Learning to Enable Computationally Efficient Traffic Event Detection with Space-Filling Curves
Bouraffa, Tayssir
Carlson, Elias Kjellberg
Wessman, Erik
Nouri, Ali
Lamart, Pierre
Berger, Christian
Computer Vision and Pattern Recognition
Artificial Intelligence
Gathering data and identifying events in various traffic situations remains an essential challenge for the systematic evaluation of a perception system's performance. Analyzing large-scale, typically unstructured, multi-modal, time series data obtained from video, radar, and LiDAR is computationally demanding, particularly when meta-information or annotations are missing. We compare Optical Flow (OF) and Deep Learning (DL) to feed computationally efficient event detection via space-filling curves on video data from a forward-facing, in-vehicle camera. Our first approach leverages unexpected disturbances in the OF field from vehicle surroundings; the second approach is a DL model trained on human visual attention to predict a driver's gaze to spot potential event locations. We feed these results to a space-filling curve to reduce dimensionality and achieve computationally efficient event retrieval. We systematically evaluate our concept by obtaining characteristic patterns for both approaches from a large-scale virtual dataset (SMIRK) and applied our findings to the Zenseact Open Dataset (ZOD), a large multi-modal, real-world dataset, collected over two years in 14 different European countries. Our results yield that the OF approach excels in specificity and reduces false positives, while the DL approach demonstrates superior sensitivity. Both approaches offer comparable processing speed, making them suitable for real-time applications.
title Comparing Optical Flow and Deep Learning to Enable Computationally Efficient Traffic Event Detection with Space-Filling Curves
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2408.00768