Understanding Dynamic Scenes using Graph Convolution Networks
- URL: http://arxiv.org/abs/2005.04437v5
- Date: Fri, 14 Aug 2020 15:56:51 GMT
- Title: Understanding Dynamic Scenes using Graph Convolution Networks
- Authors: Sravan Mylavarapu, Mahtab Sandhu, Priyesh Vijayan, K Madhava Krishna,
Balaraman Ravindran, Anoop Namboodiri
- Abstract summary: We present a novel framework to model on-road vehicle behaviors from a sequence of temporally ordered frames as grabbed by a moving camera.
We show a seamless transfer of learning to multiple datasets without resorting to fine-tuning.
Such behavior prediction methods find immediate relevance in a variety of navigation tasks.
- Score: 22.022759283770377
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We present a novel Multi-Relational Graph Convolutional Network (MRGCN) based
framework to model on-road vehicle behaviors from a sequence of temporally
ordered frames as grabbed by a moving monocular camera. The input to MRGCN is a
multi-relational graph where the graph's nodes represent the active and passive
agents/objects in the scene, and the bidirectional edges that connect every
pair of nodes are encodings of their Spatio-temporal relations. We show that
this proposed explicit encoding and usage of an intermediate spatio-temporal
interaction graph to be well suited for our tasks over learning end-end
directly on a set of temporally ordered spatial relations. We also propose an
attention mechanism for MRGCNs that conditioned on the scene dynamically scores
the importance of information from different interaction types. The proposed
framework achieves significant performance gain over prior methods on
vehicle-behavior classification tasks on four datasets. We also show a seamless
transfer of learning to multiple datasets without resorting to fine-tuning.
Such behavior prediction methods find immediate relevance in a variety of
navigation tasks such as behavior planning, state estimation, and applications
relating to the detection of traffic violations over videos.
Related papers
- Multi-Scene Generalized Trajectory Global Graph Solver with Composite
Nodes for Multiple Object Tracking [61.69892497726235]
Composite Node Message Passing Network (CoNo-Link) is a framework for modeling ultra-long frames information for association.
In addition to the previous method of treating objects as nodes, the network innovatively treats object trajectories as nodes for information interaction.
Our model can learn better predictions on longer-time scales by adding composite nodes.
arXiv Detail & Related papers (2023-12-14T14:00:30Z) - Local-Global Information Interaction Debiasing for Dynamic Scene Graph
Generation [51.92419880088668]
We propose a novel DynSGG model based on multi-task learning, DynSGG-MTL, which introduces the local interaction information and global human-action interaction information.
Long-temporal human actions supervise the model to generate multiple scene graphs that conform to the global constraints and avoid the model being unable to learn the tail predicates.
arXiv Detail & Related papers (2023-08-10T01:24:25Z) - A Dynamic Temporal Self-attention Graph Convolutional Network for
Traffic Prediction [7.23135508361981]
This paper proposes a temporal self-attention graph convolutional network (DT-SGN) model which considers the adjacent matrix as a trainable attention score matrix.
Experiments demonstrate the superiority of our method over state-of-art model-driven model and data-driven models on real-world traffic datasets.
arXiv Detail & Related papers (2023-02-21T03:51:52Z) - Multi-Task Edge Prediction in Temporally-Dynamic Video Graphs [16.121140184388786]
We propose MTD-GNN, a graph network for predicting temporally-dynamic edges for multiple types of relations.
We show that modeling multiple relations in our temporal-dynamic graph network can be mutually beneficial.
arXiv Detail & Related papers (2022-12-06T10:41:00Z) - Dynamic Graph Message Passing Networks for Visual Recognition [112.49513303433606]
Modelling long-range dependencies is critical for scene understanding tasks in computer vision.
A fully-connected graph is beneficial for such modelling, but its computational overhead is prohibitive.
We propose a dynamic graph message passing network, that significantly reduces the computational complexity.
arXiv Detail & Related papers (2022-09-20T14:41:37Z) - D2-TPred: Discontinuous Dependency for Trajectory Prediction under
Traffic Lights [68.76631399516823]
We present a trajectory prediction approach with respect to traffic lights, D2-TPred, using a spatial dynamic interaction graph (SDG) and a behavior dependency graph (BDG)
Our experimental results show that our model achieves more than 20.45% and 20.78% in terms of ADE and FDE, respectively, on VTP-TL.
arXiv Detail & Related papers (2022-07-21T10:19:07Z) - Spatial-Temporal Adaptive Graph Convolution with Attention Network for
Traffic Forecasting [4.1700160312787125]
We propose a novel network, Spatial-Temporal Adaptive graph convolution with Attention Network (STAAN) for traffic forecasting.
Firstly, we adopt an adaptive dependency matrix instead of using a pre-defined matrix during GCN processing to infer the inter-dependencies among nodes.
Secondly, we integrate PW-attention based on graph attention network which is designed for global dependency, and GCN as spatial block.
arXiv Detail & Related papers (2022-06-07T09:08:35Z) - Spatial-Temporal Interactive Dynamic Graph Convolution Network for
Traffic Forecasting [1.52292571922932]
We propose a neural network-based Spatial-Temporal Interactive Dynamic Graph Convolutional Network (STIDGCN) for traffic forecasting in this paper.
In STIDGCN, we propose an interactive dynamic graph convolution structure, which first divides the sequences at intervals and captures the spatial-temporal dependence of the traffic data simultaneously.
Experiments on four real-world traffic flow datasets demonstrate that STIDGCN outperforms the state-of-the-art baseline.
arXiv Detail & Related papers (2022-05-18T01:59:30Z) - Spatio-Temporal Joint Graph Convolutional Networks for Traffic
Forecasting [75.10017445699532]
Recent have shifted their focus towards formulating traffic forecasting as atemporal graph modeling problem.
We propose a novel approach for accurate traffic forecasting on road networks over multiple future time steps.
arXiv Detail & Related papers (2021-11-25T08:45:14Z) - Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting [47.19400232038575]
We argue that learning node-specific patterns is essential for traffic forecasting while the pre-defined graph is avoidable.
We propose two adaptive modules for enhancing Graph Conal Network (GCN) with new capabilities.
Our experiments on two real-world traffic datasets show AGCRN outperforms state-of-the-art by a significant margin without pre-defined graphs about spatial connections.
arXiv Detail & Related papers (2020-07-06T15:51:10Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.