Detecting Owner-member Relationship with Graph Convolution Network in Fisheye Camera System
This addresses a specific challenge in 3D vehicle perception for embedded and vehicle-mounted systems, though it appears incremental as it builds on existing graph network techniques.
The paper tackles the problem of detecting owner-member relationships between wheels and vehicles in fisheye camera systems, proposing DeepWORD, a graph convolutional network method that achieves state-of-the-art accuracy and real-time performance.
The owner-member relationship between wheels and vehicles contributes significantly to the 3D perception of vehicles, especially in embedded environments. However, to leverage this relationship we must face two major challenges: i) Traditional IoU-based heuristics have difficulty handling occluded traffic congestion scenarios. ii) The effectiveness and applicability of the solution in a vehicle-mounted system is difficult. To address these issues, we propose an innovative relationship prediction method, DeepWORD, by designing a graph convolutional network (GCN). Specifically, to improve the information richness, we use feature maps with local correlation as input to the nodes. Subsequently, we introduce a graph attention network (GAT) to dynamically correct the a priori estimation bias. Finally, we designed a dataset as a large-scale benchmark which has annotated owner-member relationship, called WORD. In the experiments we learned that the proposed method achieved state-of-the-art accuracy and real-time performance. The WORD dataset is made publicly available at https://github.com/NamespaceMain/ownermember-relationship-dataset.