Xianlin Zeng

Xianlin Zeng

Auto-generated profile, based on publicly available information

Xianlin Zeng

School of Electrical and Information Engineering, Beihang University, Beijing, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
10 December 2021 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
XZXianlin Zeng
Xianlin Zeng
YJYalong Jiang
Yalong Jiang
WDWenrui Ding
Wenrui Ding
HLHongguang Li
Hongguang Li
YHYafeng Hao
Yafeng Hao
ZQZifeng Qiu
Zifeng Qiu
Deep learning models have been widely used for anomaly detection in surveillance videos. Typical models are equipped with the capability to reconstruct normal videos and evaluate the reconstruction errors on anomalous videos to indicate the extent of abnormalities. However, existing approaches suffer from two disadvantages. Firstly, they can only encode the movements of each identity independently, without considering the interactions among identities which may also indicate anomalies. Secondly, they leverage inflexible models whose structures are fixed under different scenes, this configuration disables the understanding of scenes. In this paper, we propose a Hierarchical Spatio-Temporal Graph Convolutional Neural Network (HSTGCNN) to address these problems, the HSTGCNN is composed of multiple branches that correspond to different levels of graph representations. High-level graph representations encode the trajectories of people and the interactions among multiple identities while low-level graph representations encode the local body postures of each person. Furthermore, we propose to weightedly combine multiple branches that are better at different scenes. An improvement over single-level graph representations is achieved in this way. An understanding of scenes is achieved and serves anomaly detection. High-level graph representations are assigned higher weights to encode moving speed and directions of people in low-resolution videos while low-level graph representations are assigned higher weights to encode human skeletons in high-resolution videos. Experimental results show that the proposed HSTGCNN significantly outperforms current state-of-the-art models on four benchmark datasets (UCSD Pedestrian, ShanghaiTech, CUHK Avenue and IITB-Corridor) by using much less learnable parameters.

10 January 2020
Verified
Conference Paper
Open access
HJHongxia Ji
Hongxia Ji
XZXianlin Zeng
Xianlin Zeng
LHLi Hongguang
Li Hongguang
WDWenrui Ding
Wenrui Ding
XNXuehua Nie
Xuehua Nie
ZXZhifeng Xiao
Zhifeng Xiao

20 March 2024 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
YWYufeng Wang
Yufeng Wang
SFShuangkang Fang
Shuangkang Fang
HZHuayu Zhang
Huayu Zhang
LHLi Hongguang
Li Hongguang
ZZZehao Zhang
Zehao Zhang
WDWenrui Ding
Wenrui Ding
3D reconstruction of Unmanned Aerial Vehicle (UAV) scenes is vital for agriculture, environmental protection, urban planning, and disaster response, to name a few. However, data acquisition can be constrained and hazardous under hostile environments, which limits the image data available in real-world applications. In this work, we propose a text-driven online editing framework for UAV scenes, which can generate novel views of existing scenes with abundant editing types. Compared with small single-object scenes, large-scale UAV scene editing suffers from several particular challenges: 1) broader capturing scope exhibits illumination variation and complicated objects that reduce the 3D scene consistency after editing; and 2) high-resolution 2D editing and 3D reconstruction can be computationally expensive with tremendous GPU memory. To tackle these issues, we first design a dual-branch compact NeRF structure to reduce memory usage and enhance accuracy for 3D reconstruction. We then introduce a sub-pixel sampling scheme to expedite the generation of low-resolution images for 2D editing, followed by a super-resolution module that restores the fine details of rendered images. Additionally, we develop a grouped content filtering mechanism to improve the 3D scene consistency of the model by matching the rendering images and text descriptions, which also significantly reduces memory usage during editing. Extensive experiments demonstrate that the proposed method can achieve various editing effects, including different seasons, weather conditions, times of the day, disaster scenarios, etc. Our technique is computationally efficient and conveniently expandable for large-scale UAV scenes, alleviating data scarcity in harsh scenarios.

14 January 2025 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
YWYufeng Wang
Yufeng Wang
HZHuayu Zhang
Huayu Zhang
XZXianlin Zeng
Xianlin Zeng
BWBowen Wang
Bowen Wang
WLWei Li
Wei Li
WDWenrui Ding
Wenrui Ding
Super-resolution (SR) of remote-sensing images (RSI) has been improved significantly with the development of deep learning. However, better performances usually come from complex network architectures and require a substantial number of parameters. Moreover, many methods can only deal with SR of single and fixed-scale factors. As such, we propose a binary lightweight SR (BLiSR) method to decrease the computation and storage burden and increase the practicality of SR, where we employ a binary neural network (BNN) as the backbone and leverage a binary continuous up-sampling module (BCUM) to achieve arbitrary scale RSI SR. Specifically, we introduce an adaptive binary convolution as the basic unit of BLiSR, which can adaptively adjust the learnable parameters to fit the distribution of full-precision weights and activations. Then, a scalable hyperbolic tangent function is presented to approximate the Sign function in backpropagation and increase the learning capability of BNN. Furthermore, we design a lightweight SR network that considers the full-precision information flow of BNN. The network comprises several basic binary units and a multi-layer group fusion block, which can extract and fuse the multi-level information from LR images, respectively. Finally, BCUM can predict the pixel values of HR images based on the frequency implicit representation network and reconstruct the LR images at arbitrary scales. Extensive experiments on four RSI datasets demonstrate that the proposed BLiSR is superior to several lightweight state-of-the-art methods on both fixed and arbitrary scale SR settings, with a better balance of complexity and performance.

3 June 2024 in IET Image Processing
Verified
Journal Article
Open access
XZXianlin Zeng
Xianlin Zeng
YJYalong Jiang
Yalong Jiang
YWYufeng Wang
Yufeng Wang
QFQiang Fu
Qiang Fu
WDWenrui Ding
Wenrui Ding
Video Anomaly Detection (VAD) has been an active research field for several decades. However, most existing approaches merely extract a single type of feature from videos and define a single paradigm to indicate the extent of abnormalities. A coarse‐to‐fine three‐level prediction is built by integrating different levels of spatio‐temporal representations, better highlighting the difference between normal and abnormal behaviors. First, an object‐level trajectory prediction is proposed to model human historical position using a graph transformer network. Subsequently, skeleton‐level prediction is achieved by incorporating the positional information from the trajectory prediction. More importantly, based on the predicted skeleton, a skeleton‐guided pixel‐level region prediction is performed. A novel Skeleton Conditioned Generative Adversarial Network (SCGAN) is designed to explore the correlation between skeleton‐level and pixel‐level motion prediction. Benefiting from SCGAN, the prediction of human regions is contributed by both coarse‐grained and fine‐grained motion features. This three‐level prediction, namely Progressive Prediction Video Anomaly Detection (P 3 VAD), enlarges the prediction error on irregular motion patterns. Besides, a pixel‐level analysis method is proposed to achieve Background‐bias Elimination (BE) and denoise the predicted region. Experimental results validate the effectiveness of P 3 VAD on the four benchmark datasets (ShanghaiTech, CUHK Avenue, IITB‐Corridor, and ADOC).