国华 刘

Prof. 国华 刘

orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
12 March 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
KWKun Wu
Kun Wu
ZZZhijian Zhang
Zhijian Zhang
ZCZeyu Chen
Zeyu Chen
国刘国华 刘
国华 刘
Synthetic aperture radar (SAR) enables precise object localization and imaging, which has propelled the rapid development of algorithms for maritime ship identification and detection. However, most current deep learning-based algorithms tend to increase network depth to improve detection accuracy, which may result in the loss of effective features of the target. In response to this challenge, this paper innovatively proposes an object-enhanced network, OE-YOLO, designed specifically for SAR ship detection. Firstly, we input the original image into an improved CFAR detector, which enhances the network’s ability to localize and perform object extraction by providing more information through an additional channel. Additionally, the Coordinate Attention mechanism (CA) is introduced into the backbone of YOLOv7-tiny to improve the model’s ability to capture spatial and positional information in the image, thereby alleviating the problem of losing the position of small objects. Furthermore, to enhance the model’s detection capability for multi-scale objects, we optimize the neck part of the original model to integrate the Asymptotic Feature Fusion (AFF) network. Finally, the proposed network model is thoroughly tested and evaluated using publicly available SAR image datasets, including the SAR-Ship-Dataset and HRSID dataset. In comparison to the baseline method YOLOv7-tiny, OE-YOLO exhibits superior performance with a lower parameter count. When compared with other commonly used deep learning-based detection methods, OE-YOLO demonstrates optimal performance and more accurate detection results.

19 January 2023 in Cluster Computing
Verified
Journal Article
Closed access
PDF file
HLHaiying Liu
Haiying Liu
KWKun Wu
Kun Wu
KHKuihua Huang
Kuihua Huang
GCGuangquan Cheng
Guangquan Cheng
RWRui Wang
Rui Wang
国刘国华 刘
国华 刘

29 October 2024 in Drones
Verified
Journal Article
Open access
PDF file
ZCZeyu Chen
Zeyu Chen
HLHaiying Liu
Haiying Liu
国刘国华 刘
国华 刘
Multi-agent decision-making faces many challenges such as non-stationarity and sparse rewards, while the complexity and randomness of the real environment further complicate policy development. This paper addresses the high-dimensional policy optimization problems of unmanned aerial vehicle (UAV) swarms. By modeling the problem scenario as a Markov decision process, a real-time policy optimization algorithm based on evolution strategy (ES) pre-training is proposed. This approach combines decision-time planning with background planning to evaluate and integrate different sets of policy parameters in a temporal context. In the experimental phase, the policy network is trained using both ES and REINFORCE algorithms on a constructed simulation platform. Comparative experiments demonstrate the effectiveness of using ES for policy pre-training. Finally, the proposed real-time policy optimization algorithm further improves the performance of the swarm by approximately 10% in simulations, offering a feasible solution for adversarial games between swarms and extending the research scope of evolutionary algorithms.

27 August 2020 in Mathematical Problems in Engineering
Verified
Journal Article
Open access
PDF file
国刘国华 刘
国华 刘
JGJuan Guan
Juan Guan
HLHaiying Liu
Haiying Liu
CWChenlin Wang
Chenlin Wang
Collaborative navigation is the key technology for multimobile robot system. In order to improve the performance of collaborative navigation system, the collaborative navigation algorithms based on odometer/vision multisource information fusion are presented in this paper. Firstly, the multisource information fusion collaborative navigation system model is established, including mobile robot model, odometry measurement model, lidar relative measurement model, UWB relative measurement model, and the SLAM model based on lidar measurement. Secondly, the frameworks of centralized and decentralized collaborative navigation based on odometer/vision fusion are given, and the SLAM algorithms based on vision are presented. Then, the centralized and decentralized odometer/vision collaborative navigation algorithms are derived, including the time update, single node measurement update, relative measurement update between nodes, and covariance cross filtering algorithm. Finally, different simulation experiments are designed to verify the effectiveness of the algorithms. Two kinds of multirobot collaborative navigation experimental scenes, which are relative measurement aided odometer and odometer/SLAM fusion, are designed, respectively. The advantages and disadvantages of centralized versus decentralized collaborative navigation algorithms in different experimental scenes are analyzed.

25 November 2023 in Algorithms
Verified
Journal Article
Open access
PDF file
XHxiaoyu Han
xiaoyu Han
CLChenyu Li
Chenyu Li
ZWZifan Wang
Zifan Wang
国刘国华 刘
国华 刘
Neural architecture search (NAS) has shown great potential in discovering powerful and flexible network models, becoming an important branch of automatic machine learning (AutoML). Although search methods based on reinforcement learning and evolutionary algorithms can find high-performance architectures, these search methods typically require hundreds of GPU days. Unlike searching in a discrete search space based on reinforcement learning and evolutionary algorithms, the differentiable neural architecture search (DARTS) continuously relaxes the search space, allowing for optimization using gradient-based methods. Based on DARTS, we propose NDARTS in this article. The new algorithm uses the Implicit Function Theorem and the Neumann series to approximate the hyper-gradient, which obtains better results than DARTS. In the simulation experiment, an ablation experiment was carried out to study the influence of the different parameters on the NDARTS algorithm and to determine the optimal weight, then the best performance of the NDARTS algorithm was searched for in the DARTS search space and the NAS-BENCH-201 search space. Compared with other NAS algorithms, the results showed that NDARTS achieved excellent results on the CIFAR-10, CIFAR-100, and ImageNet datasets, and was an effective neural architecture search algorithm.

20 June 2022 in Journal of Systems Science and Complexity
Verified
Journal Article
Closed access
PDF file
MZMiaosen Zhang
Miaosen Zhang
YLYuezu Lü
Yuezu Lü
QWQishao Wang
Qishao Wang
Guanghui WenGuanghui Wen
Guanghui Wen
国刘国华 刘
国华 刘
Wenying XuWenying Xu
Wenying Xu