Transfer-LMR: Heavy-Tail Driving Behavior Recognition in Diverse Traffic Scenarios

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Parikh, Chirag, Mishra, Ravi Shankar, Chandra, Rohan, Sarvadevabhatla, Ravi Kiran
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916239456075776
author Parikh, Chirag
Mishra, Ravi Shankar
Chandra, Rohan
Sarvadevabhatla, Ravi Kiran
author_facet Parikh, Chirag
Mishra, Ravi Shankar
Chandra, Rohan
Sarvadevabhatla, Ravi Kiran
contents Recognizing driving behaviors is important for downstream tasks such as reasoning, planning, and navigation. Existing video recognition approaches work well for common behaviors (e.g. "drive straight", "brake", "turn left/right"). However, the performance is sub-par for underrepresented/rare behaviors typically found in tail of the behavior class distribution. To address this shortcoming, we propose Transfer-LMR, a modular training routine for improving the recognition performance across all driving behavior classes. We extensively evaluate our approach on METEOR and HDD datasets that contain rich yet heavy-tailed distribution of driving behaviors and span diverse traffic scenarios. The experimental results demonstrate the efficacy of our approach, especially for recognizing underrepresented/rare driving behaviors.
format Preprint
id arxiv_https___arxiv_org_abs_2405_05354
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Transfer-LMR: Heavy-Tail Driving Behavior Recognition in Diverse Traffic Scenarios
Parikh, Chirag
Mishra, Ravi Shankar
Chandra, Rohan
Sarvadevabhatla, Ravi Kiran
Computer Vision and Pattern Recognition
Recognizing driving behaviors is important for downstream tasks such as reasoning, planning, and navigation. Existing video recognition approaches work well for common behaviors (e.g. "drive straight", "brake", "turn left/right"). However, the performance is sub-par for underrepresented/rare behaviors typically found in tail of the behavior class distribution. To address this shortcoming, we propose Transfer-LMR, a modular training routine for improving the recognition performance across all driving behavior classes. We extensively evaluate our approach on METEOR and HDD datasets that contain rich yet heavy-tailed distribution of driving behaviors and span diverse traffic scenarios. The experimental results demonstrate the efficacy of our approach, especially for recognizing underrepresented/rare driving behaviors.
title Transfer-LMR: Heavy-Tail Driving Behavior Recognition in Diverse Traffic Scenarios
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.05354