Jun Hu

Jun Hu

Auto-generated profile, based on publicly available information

Jun Hu

Shenyang University of Technology

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 July 2023
Verified
Conference Paper
Open access
HJHaoxiang Jie
Haoxiang Jie
XZXinyi Zuo
Xinyi Zuo
JGJian Gao
Jian Gao
WLWei Liu
Wei Liu
JHJun Hu
Jun Hu
SCShuai Cheng
Shuai Cheng
Lane detection has been one of the most important functions in the autonomous driving perception module. Most of the current research require complex post-processing and curve fitting processes before they can be used by subsequent regulation modules. In this paper, we propose the LLFormer algorithm combining CNN and Transformer structure, which is the first attempt to perform end-to-end lane detection based on laser point cloud and output its cubic polynomial coefficients. In addition, this paper modifies the structure of the conventional transformer and proposes the Generating Lane Query (GLQ) module. The output of encoder is plugged into GLQ for initialization of lane query in decoder, preserving the uniqueness of each frame of point cloud data. We test the performance of the proposed algorithm in the public dataset K-Lane, and the results show that the accuracy of the proposed LLFormer is close to the existing SOTA algorithm. The number of model parameters of LLFormer is only 9.01M, and the amount of operations is only 0.19GFLOPs, which are 1/26 and 1/2937 of the existing SOTA algorithm, respectively. The frequency of inference calculation is 35.9FPS, which can fully meet the real-time requirements for industrial deployment.

1 February 2023 in Neural Networks
Verified
Journal Article
Closed access
ZLZhaoshuo Liu
Zhaoshuo Liu
CFChaolu Feng
Chaolu Feng
SCShuaizheng Chen
Shuaizheng Chen
JHJun Hu
Jun Hu

9 October 2024 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
LLLinhui Li
Linhui Li
XWXuecheng Wang
Xuecheng Wang
JLJing Lian
Jing Lian
JZJian Zhao
Jian Zhao
JHJun Hu
Jun Hu
Real-time and efficient prediction of plausible trajectories of surrounding traffic agents is essential for autonomous driving. In reality, the motion of agents depends not only on their goal intents, but is also constrained by road topology. Especially for vehicles, lane geometry can significantly influence their future trajectories. In this paper, the constraining and guiding roles of lane networks are investigated, and a novel vehicle trajectory prediction model based on the goal lane segment is proposed. Specifically, a Dual-Stream Cross Attention Module (DSCAM) is developed that incorporates goal lane segment prediction into the process of collecting various interaction information. This achieves scene-consistent predictions while reducing resource consumption and inference latency. Then, learnable refinement tokens are used to adaptively refine coarse-grained trajectories during the feature decoding process, with the goal of improving prediction accuracy and ensuring temporal consistency. Extensive experiments with the Argoverse-1 and nuScenes datasets demonstrate that our model performs competitively and well-balanced. Notably, on the nuScenes, our model with only 0.44 million (M) parameters has an inference latency of less than six milliseconds (ms), making it ideal for large-scale production autonomous driving systems that require high computational resources, operational efficiency, and prediction performance.

12 December 2023 in Journal of Systems Science and Complexity
Verified
Journal Article
Closed access
PDF file
YLYing Liu
Ying Liu
JHJun Hu
Jun Hu
Yongming LiYongming Li
Yongming Li

9 January 2023 in IEEE Transactions on Circuits and Systems II: Express Briefs
Verified
Journal Article
Closed access
WLWei Liu
Wei Liu
JHJun Hu
Jun Hu
Yongming LiYongming Li
Yongming Li
In this brief, a formation control problem is studied for a class of second-order nonlinear multi-agent systems (MASs) with unknown state-delays. In MAS formation control, the uncertainties of the system are approximated by neural networks (NNs). Moreover, a novel Lyapunov function is constructed to offset the unknown state delays. The effectiveness of the proposed control scheme is demonstrated by simulation results.

10 May 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
JNJiwei Nie
Jiwei Nie
DXDingyu Xue
Dingyu Xue
FPFeng Pan
Feng Pan
ZNZuotao Ning
Zuotao Ning
WLWei Liu
Wei Liu
SCShuai Cheng
Shuai Cheng
The letter introduces a novel Visual Place Recognition (VPR) method called Lightweight Pooling-centric Saliency-aware VPR (LPS-VPR), a high-performance VPR method capable of exploiting saliency information without computational burden. The key contribution of the method is a pooling-based saliency encoder (PSE) that efficiently extracts and integrates local context saliency cues into the image embedding, avoiding using computationally intensive operations such as attention for saliency cues extraction. The method employs a multi-level feature pyramid fusion with a cascaded backtracking structure, merging multi-scale embedding information from different levels of the backbone network with negligible computational demand. The LPS-VPR method demonstrates superior performance on mainstream VPR benchmarks, showcasing state-of-the-art (SoTA) runtime efficiency and detailed ablation studies highlight the effectiveness of each LPS-VPR component. Extended visual demonstrations further underscore the effectiveness and superiority of LPS-VPR, making it a promising solution for real-world large-scale VPR applications.