Peng Yun

Peng Yun

Auto-generated profile, based on publicly available information

Peng Yun

Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

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

Representative Publications

View All Publications
4 June 2020 in IEEE Transactions on Automation Science and Engineering
Verified
Journal Article
Closed access
YSYuxiang Sun
Yuxiang Sun
WZWeixun Zuo
Weixun Zuo
PYPeng Yun
Peng Yun
HWHengli Wang
Hengli Wang
MLMing Liu
Ming Liu
Semantic segmentation of urban scenes is an essential component in various applications of autonomous driving. It makes great progress with the rise of deep learning technologies. Most of the current semantic segmentation networks use single-modal sensory data, which are usually the RGB images produced by visible cameras. However, the segmentation performance of these networks is prone to be degraded when lighting conditions are not satisfied, such as dim light or darkness. We find that thermal images produced by thermal imaging cameras are robust to challenging lighting conditions. Therefore, in this article, we propose a novel RGB and thermal data fusion network named FuseSeg to achieve superior performance of semantic segmentation in urban scenes. The experimental results demonstrate that our network outperforms the state-of-the-art networks.

21 January 2019 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
JZJingwei Zhang
Jingwei Zhang
LTLei Tai
Lei Tai
PYPeng Yun
Peng Yun
YXYufeng Xiong
Yufeng Xiong
MLMing Liu
Ming Liu
WBWolfram Burgard
Wolfram Burgard
In this paper, we deal with the reality gap from a novel perspective, targeting transferring Deep Reinforcement Learning (DRL) policies learned in simulated environments to the real-world domain for visual control tasks. Instead of adopting the common solutions to the problem by increasing the visual fidelity of synthetic images output from simulators during the training phase, we seek to tackle the problem by translating the real-world image streams back to the synthetic domain during the deployment phase, to make the robot feel at home. We propose this as a lightweight, flexible, and efficient solution for visual control, as 1) no extra transfer steps are required during the expensive training of DRL agents in simulation; 2) the trained DRL agents will not be constrained to being deployable in only one specific real-world environment; 3) the policy training and the transfer operations are decoupled, and can be conducted in parallel. Besides this, we propose a simple yet effective shift loss that is agnostic to the downstream task, to constrain the consistency between subsequent frames which is important for consistent policy outputs.We validate the shift loss for artistic style transfer for videos and domain adaptation, and validate our visual control approach in indoor and outdoor robotics experiments.

17 April 2024 in IEEE Transactions on Intelligent Vehicles
Verified
Journal Article
Closed access
JLJiahang Li
Jiahang Li
YZYikang Zhang
Yikang Zhang
PYPeng Yun
Peng Yun
GZGuangliang Zhou
Guangliang Zhou
QCQijun Chen
Qijun Chen
RFRui Fan
Rui Fan
The recent advancements in deep convolutional neural networks have shown significant promise in the domain of road scene parsing. Nevertheless, the existing works focus primarily on freespace detection, with little attention given to hazardous road defects that could compromise both driving safety and comfort. In this article, we introduce RoadFormer, a novel Transformer-based data-fusion network developed for road scene parsing. RoadFormer utilizes a duplex encoder architecture to extract heterogeneous features from both RGB images and surface normal information. The encoded features are subsequently fed into a novel heterogeneous feature synergy block for effective feature fusion and recalibration. The pixel decoder then learns multi-scale long-range dependencies from the fused and recalibrated heterogeneous features, which are subsequently processed by a Transformer decoder to produce the final semantic prediction. Additionally, we release SYN-UDTIRI, the first large-scale road scene parsing dataset that contains over 10,407 RGB images, dense depth images, and the corresponding pixel-level annotations for both freespace and road defects of different shapes and sizes. Extensive experimental evaluations conducted on our SYN-UDTIRI dataset, as well as on three public datasets, including KITTI road, CityScapes, and ORFD, demonstrate that RoadFormer outperforms all other state-of-the-art networks for road scene parsing. Specifically, RoadFormer ranks first on the KITTI road benchmark. Our source code, created dataset, and demo video are publicly available at mias.group/RoadFormer .

23 January 2019 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
PYPeng Yun
Peng Yun
LTLei Tai
Lei Tai
YWYuan Wang
Yuan Wang
CLChengju Liu
Chengju Liu
MLMing Liu
Ming Liu
3D object detection is still an open problem in autonomous driving scenes. When recognizing and localizing key objects from sparse 3D inputs, autonomous vehicles suffer from a larger continuous searching space and higher fore-background imbalance compared to image-based object detection. In this letter, we aim to solve this fore-background imbalance in 3D object detection. Inspired by the recent use of focal loss in image-based object detection, we extend this hard-mining improvement of binary cross entropy to point-cloud-based object detection and conduct experiments to show its performance based on two different 3D detectors: 3D-FCN and VoxelNet. The evaluation results show up to 11.2AP gains through the focal loss in a wide range of hyperparameters for 3D object detection.

29 January 2021 in IEEE Robotics & Automation Magazine
Verified
Journal Article
Closed access
TLTianyu Liu
Tianyu Liu
QLQing Hai Liao
Qing Hai Liao
LGLu Gan
Lu Gan
FMFulong Ma
Fulong Ma
JCJie Cheng
Jie Cheng
MLMing Liu
Ming Liu

23 October 2022
Verified
Book Chapter
Closed access
PDF file
JCJun Cen
Jun Cen
PYPeng Yun
Peng Yun
SZShiwei Zhang
Shiwei Zhang
JCJunhao Cai
Junhao Cai
DLDi Luan
Di Luan
MWMichael Yu Wang
Michael Yu Wang