Xiaofeng Ling

Xiaofeng Ling

Auto-generated profile, based on publicly available information

Xiaofeng Ling

School of Information Science and Engineering and Shanghai Key Laboratory of Intelligent Sensing and Detection Technology, East China University of Science and Technology, Shanghai, China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
11 January 2021 in IEEE Access
Verified
Journal Article
Open access
JZJianmei Zhang
Jianmei Zhang
HZHongQing Zhu
HongQing Zhu
PWPengyu Wang
Pengyu Wang
XLXiaofeng Ling
Xiaofeng Ling
Forest fire is becoming one of the most significant natural disasters at the expense of ecology and economy. In this article, we develop an effective SqueezeNet based asymmetric encoder-decoder U-shape architecture, Attention U-Net and SqueezeNet (ATT Squeeze U-Net), mainly functions as an extractor and a discriminator of forest fire. This model takes attention mechanism to highlight useful features and suppress irrelevant contents by embedding Attention Gate (AG) units in the skip connection of U-shape structure. In this way, salient features are emphasized so that the proposed method could be competent at forest fire segmentation tasks with a small number of parameters. Specifically, we first replace classical convolution layer by a depthwise one and engage a Channel Shuffle operation as a feature communicator in the Fire module of classical SqueezeNet. Then, this modified SqueezeNet is employed as a substitution of the encoder of Attention U-Net and a corresponding DeFire module designed is combined into the decoder as well. Finally, to classify true fire, we take use of a fragment of the encoder in ATT Squeeze U-Net. The experimental results of modified SqueezeNet integrated Attention U-Net show that a competitive accuracy at 0.93 and an average prediction time at 0.89 second per image are achieved for reliable real-time forest fire detection.

23 February 2025 in Journal of Real-Time Image Processing
Verified
Journal Article
Closed access
PDF file
ZLZheming Liu
Zheming Liu
XLXiaofeng Ling
Xiaofeng Ling
YZYu Zhu
Yu Zhu
NWNan Wang
Nan Wang

8 January 2018 in IEEE Access
Verified
Journal Article
Open access
NWNan Wang
Nan Wang
SCSong Chen
Song Chen
JNJianmo Ni
Jianmo Ni
XLXiaofeng Ling
Xiaofeng Ling
YZYu Zhu
Yu Zhu
The high penetration of third-party intellectual property is accompanied with severe security issues, and thus, security constraints during task scheduling have recently been proposed for protecting multiprocessor system-on-chip systems. However, these security constraints incur significant overheads in terms of the schedule length and design cost. In this paper, the multi-dimensional design optimization space (schedule length, design cost, area, and security) is explored, and two task scheduling approaches in the context of security constraints are proposed. In resource-constrained task scheduling approach, the maximum clique of a vendor violation graph is accurately calculated, enabling a minimized number of security constraint violations under the vendor constraint. In addition, task scheduling is conducted alongside vendor assignment to optimize the schedule length. In performance-constrained task scheduling approach, a max-flow min-cut-based task clustering method is first proposed to iteratively reduce the schedule length of the graph containing all critical paths. Then, vendor assignment is performed by solving a graph coloring problem, and all tasks are finally scheduled with an optimization of hardware resources. The experimental results demonstrate that our resource-constrained task scheduling approach reduces the schedule length by 28.2% with all security constraints satisfied; besides, 18.0% cores are saved by our performance-constrained task scheduling approach.

4 November 2024 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
ZZZiming Zhu
Ziming Zhu
YZYu Zhu
Yu Zhu
KZKezhi Zhang
Kezhi Zhang
HLHangyu Li
Hangyu Li
XLXiaofeng Ling
Xiaofeng Ling
The effective representation and feature extraction of 3D scenes from sparse and unstructured point clouds pose a significant challenge in 3D object detection. In this paper, we propose TransMRE, a network that enables fully sparse multiple observation plane feature fusion using LiDAR point clouds as single-modal input. TransMRE achieves this by sparsely factorizing a 3D voxel scene into three separate observation planes: X-Y plane, X-Z plane, and Y-Z plane. Additionally, we propose Observation Plane Sparse Fusion and Interaction to explore the internal relationship between different observation planes. The transformers mechanism is employed to realize feature attention within single observation plane and feature attention across multiple observation planes. This recursive application of attention is done during multiple observation plane projection feature aggregation to effectively model the entire 3D scene. This approach addresses the limitation of insufficient feature representation ability under a single bird’s-eye view constructed by extremely sparse point clouds. Furthermore, TransMRE maintains the full sparsity property of the entire network, eliminating the need to convert sparse feature maps into dense feature maps. As a result, it can be effectively applied to LiDAR point cloud data with large scanning ranges, such as Argoverse 2, while ensuring low computational complexity. Extensive experiments were conducted to evaluate the effectiveness of TransMRE, achieving 64.9 mAP and 70.4 NDS on the nuScenes detection benchmark, and 32.3 mAP on the Argoverse 2 detection benchmark. These results demonstrate that our method outperforms state-of-the-art methods.

5 October 2022 in European Polymer Journal
Verified
Journal Article
Closed access
DSDongyong Sha
Dongyong Sha
STShuaimin Tang
Shuaimin Tang
ZDZeyu Dong
Zeyu Dong
KCKai Chen
Kai Chen
NWNan Wang
Nan Wang
YYYuan Yuan
Yuan Yuan

11 February 2020 in IEEE Access
Verified
Journal Article
Open access
PWPengyu Wang
Pengyu Wang
HZHongQing Zhu
HongQing Zhu
XLXiaofeng Ling
Xiaofeng Ling
This paper addresses an image matching methodology designed for correspondence problem in computer vision. Firstly, a novel superpixel segmentation model driven by spatially constrained Student's-t mixture model (SMM) is proposed. The tails of Student's t-distribution are heavier than that of traditional Gaussian distribution, therefore, SMM is more insensitive to outliers and noise. In this model, a spatially constraint term based on Markov random field (MRF) is designed, so that good boundary adherence and intensity homogeneity would be achieved. Next, by constructing an adaptive superpixel Gaussian filter and a superpixel salient detector, this paper establishes an innovative key-superpixel detection method by building a superpixel scale-space pyramid. Different from conventional keypoint based detection, two images could then be matched directly in a superpixel-to-superpixel manner. During the matching process, a combinatorial feature descriptor that merges color, shape, gradient and texture features is set up to distinguish each considered key-superpixel. One main advantage of this approach is that implementation time would be largely reduced by less matching demand for key-superpixels and few corresponding local features. Some experiments on datasets at the end would demonstrate a relatively better performance of our model.