BEV-TSR: Text-Scene Retrieval in BEV Space for Autonomous Driving
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916290005827584 |
|---|---|
| author | Tang, Tao Wei, Dafeng Jia, Zhengyu Gao, Tian Cai, Changwei Hou, Chengkai Jia, Peng Zhan, Kun Sun, Haiyang Fan, Jingchen Zhao, Yixing Liu, Fu Liang, Xiaodan Lang, Xianpeng Wang, Yang |
| author_facet | Tang, Tao Wei, Dafeng Jia, Zhengyu Gao, Tian Cai, Changwei Hou, Chengkai Jia, Peng Zhan, Kun Sun, Haiyang Fan, Jingchen Zhao, Yixing Liu, Fu Liang, Xiaodan Lang, Xianpeng Wang, Yang |
| contents | The rapid development of the autonomous driving industry has led to a significant accumulation of autonomous driving data. Consequently, there comes a growing demand for retrieving data to provide specialized optimization. However, directly applying previous image retrieval methods faces several challenges, such as the lack of global feature representation and inadequate text retrieval ability for complex driving scenes. To address these issues, firstly, we propose the BEV-TSR framework which leverages descriptive text as an input to retrieve corresponding scenes in the Bird's Eye View (BEV) space. Then to facilitate complex scene retrieval with extensive text descriptions, we employ a large language model (LLM) to extract the semantic features of the text inputs and incorporate knowledge graph embeddings to enhance the semantic richness of the language embedding. To achieve feature alignment between the BEV feature and language embedding, we propose Shared Cross-modal Embedding with a set of shared learnable embeddings to bridge the gap between these two modalities, and employ a caption generation task to further enhance the alignment. Furthermore, there lack of well-formed retrieval datasets for effective evaluation. To this end, we establish a multi-level retrieval dataset, nuScenes-Retrieval, based on the widely adopted nuScenes dataset. Experimental results on the multi-level nuScenes-Retrieval show that BEV-TSR achieves state-of-the-art performance, e.g., 85.78% and 87.66% top-1 accuracy on scene-to-text and text-to-scene retrieval respectively. Codes and datasets will be available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_01065 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BEV-TSR: Text-Scene Retrieval in BEV Space for Autonomous Driving Tang, Tao Wei, Dafeng Jia, Zhengyu Gao, Tian Cai, Changwei Hou, Chengkai Jia, Peng Zhan, Kun Sun, Haiyang Fan, Jingchen Zhao, Yixing Liu, Fu Liang, Xiaodan Lang, Xianpeng Wang, Yang Computer Vision and Pattern Recognition Artificial Intelligence The rapid development of the autonomous driving industry has led to a significant accumulation of autonomous driving data. Consequently, there comes a growing demand for retrieving data to provide specialized optimization. However, directly applying previous image retrieval methods faces several challenges, such as the lack of global feature representation and inadequate text retrieval ability for complex driving scenes. To address these issues, firstly, we propose the BEV-TSR framework which leverages descriptive text as an input to retrieve corresponding scenes in the Bird's Eye View (BEV) space. Then to facilitate complex scene retrieval with extensive text descriptions, we employ a large language model (LLM) to extract the semantic features of the text inputs and incorporate knowledge graph embeddings to enhance the semantic richness of the language embedding. To achieve feature alignment between the BEV feature and language embedding, we propose Shared Cross-modal Embedding with a set of shared learnable embeddings to bridge the gap between these two modalities, and employ a caption generation task to further enhance the alignment. Furthermore, there lack of well-formed retrieval datasets for effective evaluation. To this end, we establish a multi-level retrieval dataset, nuScenes-Retrieval, based on the widely adopted nuScenes dataset. Experimental results on the multi-level nuScenes-Retrieval show that BEV-TSR achieves state-of-the-art performance, e.g., 85.78% and 87.66% top-1 accuracy on scene-to-text and text-to-scene retrieval respectively. Codes and datasets will be available. |
| title | BEV-TSR: Text-Scene Retrieval in BEV Space for Autonomous Driving |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2401.01065 |