no code implementations • 1 Mar 2022 • Yancheng Pan, Fan Xie, Huijing Zhao
(3) The trust scores are unreliable for classes whose features are confused with other classes.
no code implementations • 21 Feb 2022 • Zeyu Zhu, Huijing Zhao
A multi-task conditional imitation learning framework is proposed to adapt both lateral and longitudinal control tasks for safe and efficient interaction.
no code implementations • 18 Feb 2022 • Biao Gao, Xijun Zhao, Huijing Zhao
Off-road semantic segmentation with fine-grained labels is necessary for autonomous vehicles to understand driving scenes, as the coarse-grained road detection can not satisfy off-road vehicles with various mechanical properties.
no code implementations • 10 Mar 2021 • Shaochi Hu, Hanwei Fan, Biao Gao, XijunZhao, Huijing Zhao
A measure is learned to discriminate the scenes of different semantic attributes via contrastive learning, and a driving scene profiling and categorization method is developed based on that measure.
no code implementations • 5 Mar 2021 • Biao Gao, Shaochi Hu, Xijun Zhao, Huijing Zhao
With a set of human-annotated anchor patches, a feature representation is learned to discriminate regions with different traversability, a method of fine-grained semantic segmentation and mapping is subsequently developed for off-road scene understanding.
no code implementations • 8 Jun 2020 • Biao Gao, Yancheng Pan, Chengkun Li, Sibo Geng, Huijing Zhao
Finally, a systematic survey to the existing efforts to solve the data hunger problem is conducted on both methodological and dataset's viewpoints, followed by an insightful discussion of remaining problems and open questions To the best of our knowledge, this is the first work to analyze the data hunger problem for 3D semantic segmentation using deep learning techniques that are addressed in the literature review, statistical analysis, and cross-dataset and cross-algorithm experiments.
no code implementations • 23 May 2020 • Donghao Xu, Zhezhang Ding, Xu He, Huijing Zhao, Mathieu Moze, François Aioun, Franck Guillemard
In this study, a method of learning cost parameters of a motion planner from naturalistic driving data is proposed.
no code implementations • 22 May 2020 • Donghao Xu, Zhezhang Ding, Chenfeng Tu, Huijing Zhao, Mathieu Moze, François Aioun, Franck Guillemard
In this study, a joint model of the two types of heterogeneity in car-following behavior is proposed as an approach of driver profiling and identification.
no code implementations • 31 Mar 2020 • Shaochi Hu, Donghao Xu, Huijing Zhao
A method is proposed to solve the problem via modeling dynamic correlation using latent space shared auto-encoders.
no code implementations • 10 Mar 2020 • Biao Gao, Anran Xu, Yancheng Pan, Xijun Zhao, Wen Yao, Huijing Zhao
We propose a method for off-road drivable area extraction using 3D LiDAR data with the goal of autonomous driving application.
no code implementations • 21 Feb 2020 • Yancheng Pan, Biao Gao, Jilin Mei, Sibo Geng, Chengkun Li, Huijing Zhao
3D semantic segmentation is one of the key tasks for autonomous driving system.
no code implementations • 16 Sep 2019 • Zeyu Zhu, Nan Li, Ruoyu Sun, Huijing Zhao, Donghao Xu
Different cost functions of traversability analysis are learned and tested at various scenes of capability in guiding the trajectory planning of different behaviors.
no code implementations • 23 May 2019 • Jilin Mei, Huijing Zhao
We propose a new method that makes full use of the advantages of traditional methods and deep learning methods via incorporating human domain knowledge into the neural network model to reduce the demand for large numbers of manual annotations and improve the training efficiency.
no code implementations • 3 Sep 2018 • Jilin Mei, Biao Gao, Donghao Xu, Wen Yao, Xijun Zhao, Huijing Zhao
This work studies the semantic segmentation of 3D LiDAR data in dynamic scenes for autonomous driving applications.
Robotics
no code implementations • CVPR 2014 • Quanshi Zhang, Xuan Song, Xiaowei Shao, Huijing Zhao, Ryosuke Shibasaki
Graph matching and graph mining are two typical areas in artificial intelligence.
no code implementations • CVPR 2014 • Quanshi Zhang, Xuan Song, Xiaowei Shao, Huijing Zhao, Ryosuke Shibasaki
3D reconstruction from a single image is a classical problem in computer vision.
no code implementations • CVPR 2013 • Quanshi Zhang, Xuan Song, Xiaowei Shao, Ryosuke Shibasaki, Huijing Zhao
We design a graphical model that uses object edges to represent object structures, and this paper aims to incrementally learn this category model from one labeled object and a number of casually captured scenes.