ContextVLM: Zero-Shot and Few-Shot Context Understanding for Autonomous Driving using Vision Language Models [IEEE ITSC 2024] [supporting dataset]

Rajkumar, Ragunathan (Raj); Sahu, Nishad; Sural, Shounak

i

ContextVLM: Zero-Shot and Few-Shot Context Understanding for Autonomous Driving using Vision Language Models [IEEE ITSC 2024] [supporting dataset]

Dataset

2024-09-01
By Rajkumar, Ragunathan (Raj) ; Sahu, Nishad ; Sural, Shounak

File Language:

English

Select the Download button to view the document

This document file type cannot be previewed

Details

Creators:

Rajkumar, Ragunathan (Raj) ; Sahu, Nishad ; Sural, Shounak
Corporate Creators:

Carnegie Mellon University. Traffic21 Institute. Safety21 University Transportation Center (UTC)
Corporate Contributors:

United States. Department of Transportation. University Transportation Centers (UTC) Program ; United States. Department of Transportation. Office of the Assistant Secretary for Research and Technology
Subject/TRT Terms:
Resource Type:

Dataset
Right Statement:

Open Access; http://creativecommons.org/publicdomain/zero/1.0
Geographical Coverage:

United States
Corporate Publisher:

Carnegie Mellon University. Traffic21 Institute. Safety21 University Transportation Center (UTC)
Abstract:

In this work, we introduce a dataset called DrivingContexts for the detection of relevant driving contexts for autonomous driving. Additionally, we propose the use of vision language models such as LLaVa and ViLT with zero-shot and few-shot approaches, to solve the problem of detecting such contexts. With our approach, we reduce the need for fully supervised training on large annotated datasets to detect these contexts and also the need for hand-crafted approaches to understand specific contexts of importance.
Content Notes:

This item is made available under the terms of the Creative Commons Attribution 1.0 Universal (CC0 1.0) license https://creativecommons.org/publicdomain/zero/1.0/. External Repository Note: This dataset additional data and software in a GitHub repository. This repository is accessible online: https://github.com/ssuralcmu/ContextVLM.git
Format:

ZIP
Funding:

69A3552344811
Download URL:

https://rosap.ntl.bts.gov/view/dot/87498/dot_87498_DS1.zip
File Type:

[ZIP - 2.22 MB]
Collection(s):

Artificial Intelligence Deployment Center of Excellence (AI COE) ; Autonomous Vehicles ; University Transportation Centers
Main Document Checksum:

urn:sha-512:afef8c9690e9b4c1c77408b79bb8ed04bf726739f46816bf06cb10506d2cb4e71245f6fb32de2a1fa398a7e5deebd418156f1bde666f6c6e49e6a014ef635455

Safety Assurance and Demonstration of Connected Autonomous Vehicles

This proposed larger-scale effort aims to re-define and demonstrate the vision of full autonomy to one of safe autonomy, where a learning-enabled syst ...

Rajkumar, Ragunathan (Raj)

;

Sahu, Nishad

File Language:

English

ON THIS PAGE

Details Publications

Found an issue?

Send us an email at:

publishinghd@cdc.gov

ROSA P serves as an archival repository of USDOT-published products including scientific findings, journal articles, guidelines, recommendations, or other information authored or co-authored by USDOT or funded partners. As a repository, ROSA P retains documents in their original published format to ensure public access to scientific information.