EC-IoU: Orienting Safety for Object Detectors via Ego-Centric Intersection-over-Union

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liao, Brian Hsuan-Cheng, Cheng, Chih-Hong, Esen, Hasan, Knoll, Alois
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929655286595584
author Liao, Brian Hsuan-Cheng
Cheng, Chih-Hong
Esen, Hasan
Knoll, Alois
author_facet Liao, Brian Hsuan-Cheng
Cheng, Chih-Hong
Esen, Hasan
Knoll, Alois
contents This paper presents Ego-Centric Intersection-over-Union (EC-IoU), addressing the limitation of the standard IoU measure in characterizing safety-related performance for object detectors in navigating contexts. Concretely, we propose a weighting mechanism to refine IoU, allowing it to assign a higher score to a prediction that covers closer points of a ground-truth object from the ego agent's perspective. The proposed EC-IoU measure can be used in typical evaluation processes to select object detectors with better safety-related performance for downstream tasks. It can also be integrated into common loss functions for model fine-tuning. While geared towards safety, our experiment with the KITTI dataset demonstrates the performance of a model trained on EC-IoU can be better than that of a variant trained on IoU in terms of mean Average Precision as well.
format Preprint
id arxiv_https___arxiv_org_abs_2403_15474
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EC-IoU: Orienting Safety for Object Detectors via Ego-Centric Intersection-over-Union
Liao, Brian Hsuan-Cheng
Cheng, Chih-Hong
Esen, Hasan
Knoll, Alois
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Robotics
This paper presents Ego-Centric Intersection-over-Union (EC-IoU), addressing the limitation of the standard IoU measure in characterizing safety-related performance for object detectors in navigating contexts. Concretely, we propose a weighting mechanism to refine IoU, allowing it to assign a higher score to a prediction that covers closer points of a ground-truth object from the ego agent's perspective. The proposed EC-IoU measure can be used in typical evaluation processes to select object detectors with better safety-related performance for downstream tasks. It can also be integrated into common loss functions for model fine-tuning. While geared towards safety, our experiment with the KITTI dataset demonstrates the performance of a model trained on EC-IoU can be better than that of a variant trained on IoU in terms of mean Average Precision as well.
title EC-IoU: Orienting Safety for Object Detectors via Ego-Centric Intersection-over-Union
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Robotics
url https://arxiv.org/abs/2403.15474