In this paper, an image captioning network is proposed for traffic scene modeling, which incorporates element attention into the encoder-decoder mechanism to generate more reasonable scene captions. Firstly, the traffic scene elements are detected and segmented according to their clustered locations. Then, the image captioning network is applied to generate the corresponding caption of each subregion. The static and dynamic traffic elements are appropriately organized to construct a 3D corridor scene model. The semantic relationships between the traffic elements are specified according to the captions. The constructed 3D scene model can be utilized for the offline test of unmanned vehicles. The evaluations and comparisons based on the TSD-max and COCO datasets prove the effectiveness of the proposed framework.
Caption Generation from Road Images for Traffic Scene Construction
2020 IEEE Intelligent Vehicles Symposium (IV) ; 1271-1276
2020-10-19
4116179 byte
Conference paper
Electronic Resource
English
CAPTION GENERATION FROM ROAD IMAGES FOR TRAFFIC SCENE CONSTRUCTION
British Library Conference Proceedings | 2020
|Road Traffic Scene Acquisition
TIBKAT | 2019
|Road Traffic Scene Acquisition
Springer Verlag | 2018
|Caption Generation for Traffic Signs Using a Deep Neural Scheme
SAE Technical Papers | 2022
|