Huan Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Huan Liu has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
Chuanyun Xu
School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China
1 shared publicationGang Li
School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China
1 shared publicationTenghui Li
School of Artificial Intelligence, Chongqing University of Technology, Chongqing, China
1 shared publicationTian Li
Computer Science Department, RWTH Aachen University, Aachen, Germany
1 shared publication- Xi Wu
School of Computer Science and Engineering, Xi’an Technological University, Xi’an, Shaanxi, P. R. China
1 shared publication - Xiuhua Hu
School of Computer Science and Engineering, Xi’an Technological University, Xi’an, People’s Republic of China
1 shared publication
Latest Publications
- Open Access
- 25 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Intelligent Transportation Systems
- Vol. 3, 340-350
Cascaded Feature-Mask Fusion for Foreground Segmentation
Foreground segmentation aims at extracting moving objects from the background in a robust manner under various challenging scenarios. The deep learning-based methods have achieved remarkable improvement in this field. These methods produce semantically correct predictions based on extracted rich semantic features yet perform poorly on segmentation of edge details. The main reason is that the high-level features extracted by the deep network lose the high-frequency information for the successful edge segmentation. On this basis, we propose a novel segmentation network with a cascade architecture to refine segmentation results step by step by introducing detailed information into high-level features. The network recorrects and optimizes the segmentation maps in each step so that more accurate segmentation results are obtained. Furthermore, we evaluate our approach on the challenging CDnet2014 dataset and achieve an F-measure of 0.9868. Our approach thus outperforms previous methods, such as FgSegNet_v2, FgSegNet, BSPVGan, Cascade CNN, IUTIS-5, WeSamBE, DeepBS, and GMM-Stauffer.
- 25 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Intelligent Transportation Systems
- Vol. 3, 340-350
Open AccessCascaded Feature-Mask Fusion for Foreground Segmentation
Foreground segmentation aims at extracting moving objects from the background in a robust manner under various challenging scenarios. The deep learning-based methods have achieved remarkable improvement in this field. These methods produce semantically correct predictions based on extracted rich semantic features yet perform poorly on segmentation of edge details. The main reason is that the high-level features extracted by the deep network lose the high-frequency information for the successful edge segmentation. On this basis, we propose a novel segmentation network with a cascade architecture to refine segmentation results step by step by introducing detailed information into high-level features. The network recorrects and optimizes the segmentation maps in each step so that more accurate segmentation results are obtained. Furthermore, we evaluate our approach on the challenging CDnet2014 dataset and achieve an F-measure of 0.9868. Our approach thus outperforms previous methods, such as FgSegNet_v2, FgSegNet, BSPVGan, Cascade CNN, IUTIS-5, WeSamBE, DeepBS, and GMM-Stauffer.
- 1 February 2022
- Published by World Scientific Pub Co Pte Ltd in International Journal of Pattern Recognition and Artificial Intelligence
- Vol. 36 (02)
Person Re-Identification Combined with Style Transfer and Pose Generation
The number of existing person re-identification datasets is limited, and there are a series of changes such as illumination, background occlusion and pose among each dataset, which makes it difficult for the existing methods to learn robust feature representation, leading to a decline in recognition performance. To solve these problems, a person re-identification method combining style and pose generation is proposed in this paper. First with the impact of camera style differences in collecting images from different cameras, a style transformation method based on generative adversarial network is introduced into a person re-identification model, and cyclic generative adversarial networks (CycleGAN) is used to realize style transfer and reduce the influence of camera differences. Second, in view of the problem that when pedestrian pose changes greatly, easy to ignore identity-sensitive related information, AlphaPose is introduced to implement pose estimation. Combining style and posture for the first time and using improved deep convolution generative adversarial network (DCGAN) structure enrich the input sample information and generate unified style pose image; while using new synthetic data to train person re-identification network model improves the recognition performance of the model. Finally, further introducing random erasure method during data enhancement, in order to reduce the overfitting phenomena, improves the generalization ability of the network simultaneously and solves partial occlusion. The experimental results show that the proposed method outperforms typical style-based or pose-based methods. The accuracy of rank-1 and mAP on Market-1501 dataset is 90.4% and 74.5%, respectively, which are 2.28% and 5.78% higher, respectively. To a certain extent, the performance of person re-identification is improved.
- 1 February 2022
- Published by World Scientific Pub Co Pte Ltd in International Journal of Pattern Recognition and Artificial Intelligence
- Vol. 36 (02)
Person Re-Identification Combined with Style Transfer and Pose Generation
The number of existing person re-identification datasets is limited, and there are a series of changes such as illumination, background occlusion and pose among each dataset, which makes it difficult for the existing methods to learn robust feature representation, leading to a decline in recognition performance. To solve these problems, a person re-identification method combining style and pose generation is proposed in this paper. First with the impact of camera style differences in collecting images from different cameras, a style transformation method based on generative adversarial network is introduced into a person re-identification model, and cyclic generative adversarial networks (CycleGAN) is used to realize style transfer and reduce the influence of camera differences. Second, in view of the problem that when pedestrian pose changes greatly, easy to ignore identity-sensitive related information, AlphaPose is introduced to implement pose estimation. Combining style and posture for the first time and using improved deep convolution generative adversarial network (DCGAN) structure enrich the input sample information and generate unified style pose image; while using new synthetic data to train person re-identification network model improves the recognition performance of the model. Finally, further introducing random erasure method during data enhancement, in order to reduce the overfitting phenomena, improves the generalization ability of the network simultaneously and solves partial occlusion. The experimental results show that the proposed method outperforms typical style-based or pose-based methods. The accuracy of rank-1 and mAP on Market-1501 dataset is 90.4% and 74.5%, respectively, which are 2.28% and 5.78% higher, respectively. To a certain extent, the performance of person re-identification is improved.