Selective attention to specific areas and specific targets according to driving intention is of great significance for autonomous vehicles to efficiently obtain external environment information. In order to achieve efficient environmental perception, we propose an intention-driven visual attention selection model by simulating human active perception of the external environment. Meanwhile, in order to improve the integrity of the target category attention heatmap, a deep network training method with feature region enhancement is proposed. In this paper, FIMF Score-CAM which can fast integrate multiple features of local space is proposed. It generates intention-related target attention map by weighting the feature map extracted by forward convolution calculation, and combines spatial attention and feature attention to improve the ability of target category location. At the same time, the network is forced to pay more attention to the more comprehensive target-related region by using the guided random erasing in training process, which overcomes the deficiency that the model only pays attention to the most discriminative feature region, and achieves the purpose of feature region enhancement. Experiments on KITTI dataset show that the positioning integrity and accuracy of our model are significantly improved compared with other top-down attention models.
Enhancement of Target Feature Regions and Intention-Driven Visual Attention Selection in Traffic Scenes
2022-06-05
1503217 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Visual Attention of Pedestrians in Traffic Scenes: A Crowdsourcing Experiment
Springer Verlag | 2021
|Understanding Pedestrians’ Car-Hailing Intention in Traffic Scenes
Springer Verlag | 2022
|Feature selection for object tracking in traffic scenes [2344-30]
British Library Conference Proceedings | 1995
|