@inproceedings{Ayar2024,

title = {LiDAR-Camera Fusion for Video Panoptic Segmentation without Video Training},

author = {Fardin Ayar and Ehsan Javanmardi and Manabu Tsukada and Mahdi Javanmardi and Mohammad Rahmati},

url = {https://arxiv.org/abs/2412.20881},

year  = {2024},

date = {2024-11-28},

urldate = {2024-11-28},

booktitle = {International Conference on Intelligent Computing and its Emerging Applications (ICEA2024)},

address = {Tokyo, Japan},

abstract = {Panoptic segmentation, which combines instance and semantic segmentation, has gained a lot of attention in autonomous vehicles, due to its comprehensive representation of the scene. This task can

be applied for cameras and LiDAR sensors, but there has been a limited focus on combining both sensors to enhance image panoptic segmentation (PS). Although previous research has acknowledged the benefit of 3D data on camera-based scene perception, no specific study has explored the influence of 3D data on image and video panoptic segmentation (VPS). This work seeks to introduce a feature fusion module that enhances PS and VPS by fusing LiDAR and image data for autonomous vehicles. We also illustrate that, in

addition to this fusion, our proposed model, which utilizes two simple modifications, can further deliver even more high-quality VPS without being trained on video data. The results demonstrate a substantial improvement in both the image and video panoptic segmentation evaluation metrics by up to 5 points.},

note = {Best Paper Award (Bronze)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Li2024,

title = {Cross-Attention Enhanced Imitation Learning for End-to-end Autonomous Driving in Unprotected Turns},

author = {Dongyang Li and Ehsan Javanmardi and Naren Bao and Manabu Tsukada},

year  = {2024},

date = {2024-11-28},

urldate = {2024-11-28},

booktitle = {International Conference on Intelligent Computing and its Emerging Applications (ICEA2024)},

address = {Tokyo, Japan},

abstract = {Performing an unprotected turn in the intersection is a complex scenario for autonomous vehicles. It not only requires a comprehensive understanding of the surrounding environment but also highly relies on the ego vehicle’s current state to make safe decisions. A conventional way to learn end-to-end autonomous driving is imitation learning, which is learning from expert demonstrations. While most imitation learning methods focus on imitating the expert action, they often fail to imitate a complex policy efficiently when the ego vehicle’s states are crucial to the scenario because there might be arbitrary optimal actions under different states. To address this issue and investigate how vehicle states affect autonomous driving, we present a novel cross-attention enhanced imitation learning approach for end-to-end autonomous driving in unprotected turns, focusing on capturing the relationships between the ego vehicle’s states and its perception of the environment. We evaluate our model in AWSIM, an open-source autonomous driving

simulator, and the results demonstrate that our model outperformed conventional imitation learning-based baselines in performing unprotected turn scenarios, showcasing its ability to imitate a complex policy efficiently.},

note = {Best Paper Award (Silver)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}