roadscene2vec: A tool for extracting and embedding road scene-graphs

Malawade, Arnav Vaibhav; Yu, Shih-Yuan; Hsu, Brandon; Kaeley, Harsimrat; Anurag, Karra,; Faruque, Mohammad Abdullah Al

doi:10.1016/j.knosys.2022.108245

Cited by 15 publications

(2 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our study focused on a relatively small number of pedestrian behavioural intentions, and many more types should be considered in the future to improve trajectory prediction accuracy (4). The input triads of our model were extracted manually, and the scene information triads could be extracted automatically by algorithms such as roadscene2vec in the later stage [44].…”

Section: Discussionmentioning

confidence: 99%

Pedestrian intention estimation and trajectory prediction based on data and knowledge‐driven method

Zhou,

Bai,

et al. 2023

IET Intelligent Trans Sys

View full text Add to dashboard Cite

With the development of deep learning technology, the problem of data‐driven trajectory prediction and intention recognition has been widely studied. However, the pedestrian trajectory prediction and intention recognition methods based solely on data‐driven have weak data description ability and black‐box characteristics, which cannot reason about pedestrian crossing intention and predict pedestrian crossing trajectory as humans do. To address the above problems, the authors proposed a data and knowledge‐driven pedestrian intention estimation and trajectory prediction method by imitating human cognitive mechanisms. In the pedestrian intention inference process, the authors adopted the knowledge‐driven method. As a first step, the authors built a knowledge graph of pedestrian crossing scenes, and then paired it with a Bayesian network to estimate pedestrian crossing intentions. In the pedestrian trajectory prediction process, the authors used a data‐driven approach, combining pedestrian crossing trajectory features and knowledge‐based pedestrian intentions. Experiments show that all evaluation metrics of pedestrian trajectory prediction were improved after adding pedestrian intentions obtained by knowledge‐driven.

show abstract

Section: Discussionmentioning

confidence: 99%

Pedestrian intention estimation and trajectory prediction based on data and knowledge‐driven method

Zhou,

Bai,

et al. 2023

IET Intelligent Trans Sys

View full text Add to dashboard Cite

show abstract

“…The unique perspective offered by egocentric videos allows for a different approach to understand human interactions and activities. Scene graphs from the perspective of autonomous vehicles have been more extensively researched by the community [19,26] than the human-centric view videos. However, there are a few previous works studying the applicability of scene graph representation in egovision.…”

Section: Graph-based Representations In Egocentric Visionmentioning

confidence: 99%