Zhiqiang Xiao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zhiqiang Xiao has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Kuntao Ye
School of Science, Jiangxi University of Science and Technology, Ganzhou, China
3 shared publications - Guolong Cui
University of Electronic Science and Technology of China
2 shared publications - Youli Zou
School of Science, Jiangxi University of Science and Technology, China
1 shared publication
Latest Publications
- 4 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (4) , 5370-5382
PointNet-Transformer Fusion Network for In-Cabin Occupancy Monitoring With mm-Wave Radar
Due to the irregular distribution of 3D point clouds and the random movement of the passengers, it is difficult to accurately and rapidly determine the passenger occupancy based on the multiple-input and multiple-output (MIMO) radar. In this study, we present a lightweight neural network, dubbed PTFNet, that fuses the PointNet and Transformer to quickly and accurately detect the occupancy of three rear seats and two footwells. PTFNet adapts an input transform block to encode the 3D point cloud directly, which makes it more lightweight than conventional voxelization, heatmap, and PointNet based algorithms. Meanwhile, a cross-attention mechanism block inspired by Transformer is employed to efficiently extract features from 3D point clouds, resulting in an improvement in detection accuracy. An in-cabin occupancy monitoring system is implemented in a real vehicle to obtain 3D point cloud datasets, which are then used to evaluate the detection performance of PTFNet. Our datasets cover both the rear seat area and the footwell area. The footwell space is considered for the first time in the point cloud datasets. The experimental results demonstrate that PTFNet outperforms other popular approaches in terms of detection accuracy by at least 1.6%, while the consumption of memory and running time are reduced by at least 44% and 34%, respectively.
- 4 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (4) , 5370-5382
PointNet-Transformer Fusion Network for In-Cabin Occupancy Monitoring With mm-Wave Radar
Due to the irregular distribution of 3D point clouds and the random movement of the passengers, it is difficult to accurately and rapidly determine the passenger occupancy based on the multiple-input and multiple-output (MIMO) radar. In this study, we present a lightweight neural network, dubbed PTFNet, that fuses the PointNet and Transformer to quickly and accurately detect the occupancy of three rear seats and two footwells. PTFNet adapts an input transform block to encode the 3D point cloud directly, which makes it more lightweight than conventional voxelization, heatmap, and PointNet based algorithms. Meanwhile, a cross-attention mechanism block inspired by Transformer is employed to efficiently extract features from 3D point clouds, resulting in an improvement in detection accuracy. An in-cabin occupancy monitoring system is implemented in a real vehicle to obtain 3D point cloud datasets, which are then used to evaluate the detection performance of PTFNet. Our datasets cover both the rear seat area and the footwell area. The footwell space is considered for the first time in the point cloud datasets. The experimental results demonstrate that PTFNet outperforms other popular approaches in terms of detection accuracy by at least 1.6%, while the consumption of memory and running time are reduced by at least 44% and 34%, respectively.
- 13 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-17
Differential Self-Feedback Dilated Convolution Network With Dual-Tree Channel Attention Mechanism for Hyperspectral Image Classification
Overfitting and inadequate ability of feature extraction result in low classification accuracy when fulfilling hyperspectral image (HSI) classification tasks by deep learning models (DLMs). Unfortunately, it is very common that insufficient labeled training samples of HSI lead to overfitting and that redundant spectral information of HSI asks for high feature extraction ability in classification tasks. In general, reducing model complexity helps alleviate overfitting, whereas increasing the number of convolutional layers and kernel size helps enhance feature extraction ability. Designing DLMs for better classification accuracy requires balancing model complexity and feature extraction ability. To achieve this balance, we present a network model of differential self-feedback dilated convolution with dual-tree channel attention mechanism (DSDC-DCAM) model. In this model, a differential self-feedback dilated convolution (DSDC) block is proposed with high extraction ability and low model complexity by connecting 3-D dilated convolutions and the differential self-feedback (DSF) module as a tree structure. A dual-tree channel attention mechanism (DCAM) block is also proposed in DSDC-DCAM to form a better attention mechanism in order to exploit useful features and suppress unfavorable ones while reducing model complexity. Experimental results show that DSDC-DCAM has the best performance consistency compared with the other nine state-of-the-art models, indicating that it is least influenced by overfitting. Meanwhile, the results show that DSDC-DCAM achieves the highest overall accuracy (OA) with a smaller number of model parameters than the other seven models.
- 13 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-17
Differential Self-Feedback Dilated Convolution Network With Dual-Tree Channel Attention Mechanism for Hyperspectral Image Classification
Overfitting and inadequate ability of feature extraction result in low classification accuracy when fulfilling hyperspectral image (HSI) classification tasks by deep learning models (DLMs). Unfortunately, it is very common that insufficient labeled training samples of HSI lead to overfitting and that redundant spectral information of HSI asks for high feature extraction ability in classification tasks. In general, reducing model complexity helps alleviate overfitting, whereas increasing the number of convolutional layers and kernel size helps enhance feature extraction ability. Designing DLMs for better classification accuracy requires balancing model complexity and feature extraction ability. To achieve this balance, we present a network model of differential self-feedback dilated convolution with dual-tree channel attention mechanism (DSDC-DCAM) model. In this model, a differential self-feedback dilated convolution (DSDC) block is proposed with high extraction ability and low model complexity by connecting 3-D dilated convolutions and the differential self-feedback (DSF) module as a tree structure. A dual-tree channel attention mechanism (DCAM) block is also proposed in DSDC-DCAM to form a better attention mechanism in order to exploit useful features and suppress unfavorable ones while reducing model complexity. Experimental results show that DSDC-DCAM has the best performance consistency compared with the other nine state-of-the-art models, indicating that it is least influenced by overfitting. Meanwhile, the results show that DSDC-DCAM achieves the highest overall accuracy (OA) with a smaller number of model parameters than the other seven models.
- Open Access
- 21 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 79-83
Reconstruction of hyperspectral images with compressed sensing based on linear mixing model and affinity propagation clustering algorithm
The increasing spatial and spectral resolution of hyperspectral images results in a significant rise in data volume, which poses a challenge for data storage and transmission. Therefore, improving the efficiency of storage and transmission by enhancing the reconstruction performance of hyperspectral images at low sampling rates or same sampling rates conditions is a crucial topic in compressed sensing. Previous research has shown that a linear mixing model and distributed compressed sensing method outperform traditional compressed sensing reconstruction algorithms in recovering original data. However, the low estimating accuracy of both the endmembers matrix and abundance matrix due to the random selection of reference bands limits the reconstruction performance. To address this problem, we proposed a compressed sensing reconstruction algorithm based on a linear mixing model and affinity propagation clustering algorithm. Our method improves reconstruction performance by enhancing the estimating accuracy of the endmembers and abundance matrices. During the sampling stage, the affinity propagation clustering algorithm is used to group the spectral bands according to the spectral correlation of hyperspectral images, where the clustering center serving as the reference band and the other bands as non-reference bands. During the reconstruction stage, the number of endmembers from the reference band is estimated fist, and the endmembers matrix and the abundance matrix are then estimated. Finally, the endmembers matrix and estimated abundance matrix are used for reconstruction. Experimental results show that our proposed algorithm achieves higher performance in reconstructing hyperspectral images than the linear mixing model-based distributed compressed sensing method.
- 21 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 79-83
Open AccessReconstruction of hyperspectral images with compressed sensing based on linear mixing model and affinity propagation clustering algorithm
The increasing spatial and spectral resolution of hyperspectral images results in a significant rise in data volume, which poses a challenge for data storage and transmission. Therefore, improving the efficiency of storage and transmission by enhancing the reconstruction performance of hyperspectral images at low sampling rates or same sampling rates conditions is a crucial topic in compressed sensing. Previous research has shown that a linear mixing model and distributed compressed sensing method outperform traditional compressed sensing reconstruction algorithms in recovering original data. However, the low estimating accuracy of both the endmembers matrix and abundance matrix due to the random selection of reference bands limits the reconstruction performance. To address this problem, we proposed a compressed sensing reconstruction algorithm based on a linear mixing model and affinity propagation clustering algorithm. Our method improves reconstruction performance by enhancing the estimating accuracy of the endmembers and abundance matrices. During the sampling stage, the affinity propagation clustering algorithm is used to group the spectral bands according to the spectral correlation of hyperspectral images, where the clustering center serving as the reference band and the other bands as non-reference bands. During the reconstruction stage, the number of endmembers from the reference band is estimated fist, and the endmembers matrix and the abundance matrix are then estimated. Finally, the endmembers matrix and estimated abundance matrix are used for reconstruction. Experimental results show that our proposed algorithm achieves higher performance in reconstructing hyperspectral images than the linear mixing model-based distributed compressed sensing method.