Huaijin 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
Huaijin Liu has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
Hongbo Zhang
4 shared publications- Jixiang Du
Fujian Key Laboratory of Big Data Intelligence and Security, Huaqiao University, Xiamen, China
4 shared publications Yong Zhang
College of Mechanical Engineering and Automation Huaqiao University Xiamen China
3 shared publications- Hong-Bo Zhang
Department of Computer Science and Technology, Huaqiao University, Xiamen, China
2 shared publications Jiandian Zeng
2 shared publications- Jiandian Zeng
Institute of Artificial Intelligence and Future Networks, Beijing Normal University, Zhuhai, China
2 shared publications
Latest Publications
- 31 July 2026
- Published by Elsevier in Neural Networks
- Vol. 205
A 4D radar and LiDAR fusion framework for weather-robust 3D object detection
- 31 July 2026
- Published by Elsevier in Neural Networks
- Vol. 205
A 4D radar and LiDAR fusion framework for weather-robust 3D object detection
- 14 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. 40 (3) , 34-41
Multi-Agent Collaborative Reasoning via Cloud-Edge Framework
Large Language Model (LLM)-based agents have significantly advanced the reasoning and problem-solving capabilities of intelligent systems. As tasks grow more complex, there is an increasing need to shift from single-agent framework to Multi-Agent Systems (MAS) for enhanced collaborative performance. Achieving better performance typically requires deploying large-scale LLMs, however, it poses significant challenges on resource-constrained edge devices. In addition, most MAS adopt a fully connected communication topology and require multiple rounds of interaction, resulting in considerable communication redundancy and increased computational overhead. To address the issues, in this paper, we propose a Directed Acyclic Graph-based Multi-Agent System (DAG-MAS) via cloud-edge framework for collaborative reasoning. Specifically, considering the limited resources on the edge, we utilize a 72B-LLM in the cloud finetunes a lightweight Small Language Model (SLM) for edge deployment. To generate a one round interaction graph, the SLM is further employed to analyze task requirements and determine optimal communication topology, minimizing overhead while enabling effective information exchange. Extensive experiments and analyses on four reasoning datasets demonstrate the superiority of our approach compared to several benchmark methods, validating the effectiveness in achieving higher reasoning performance with lower communication costs.
- 14 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. 40 (3) , 34-41
Multi-Agent Collaborative Reasoning via Cloud-Edge Framework
Large Language Model (LLM)-based agents have significantly advanced the reasoning and problem-solving capabilities of intelligent systems. As tasks grow more complex, there is an increasing need to shift from single-agent framework to Multi-Agent Systems (MAS) for enhanced collaborative performance. Achieving better performance typically requires deploying large-scale LLMs, however, it poses significant challenges on resource-constrained edge devices. In addition, most MAS adopt a fully connected communication topology and require multiple rounds of interaction, resulting in considerable communication redundancy and increased computational overhead. To address the issues, in this paper, we propose a Directed Acyclic Graph-based Multi-Agent System (DAG-MAS) via cloud-edge framework for collaborative reasoning. Specifically, considering the limited resources on the edge, we utilize a 72B-LLM in the cloud finetunes a lightweight Small Language Model (SLM) for edge deployment. To generate a one round interaction graph, the SLM is further employed to analyze task requirements and determine optimal communication topology, minimizing overhead while enabling effective information exchange. Extensive experiments and analyses on four reasoning datasets demonstrate the superiority of our approach compared to several benchmark methods, validating the effectiveness in achieving higher reasoning performance with lower communication costs.
- Open Access
- 21 April 2025
- Published by Institution of Engineering and Technology (IET) in CAAI Transactions on Intelligence Technology
- Vol. 10 (3) , 912-928
Syn‐Aug: An Effective and General Synchronous Data Augmentation Framework for 3D Object Detection
Data augmentation plays an important role in boosting the performance of 3D models, while very few studies handle the 3D point cloud data with this technique. Global augmentation and cut‐paste are commonly used augmentation techniques for point clouds, where global augmentation is applied to the entire point cloud of the scene, and cut‐paste samples objects from other frames into the current frame. Both types of data augmentation can improve performance, but the cut‐paste technique cannot effectively deal with the occlusion relationship between the foreground object and the background scene and the rationality of object sampling, which may be counterproductive and may hurt the overall performance. In addition, LiDAR is susceptible to signal loss, external occlusion, extreme weather and other factors, which can easily cause object shape changes, while global augmentation and cut‐paste cannot effectively enhance the robustness of the model. To this end, we propose Syn‐Aug, a synchronous data augmentation framework for LiDAR‐based 3D object detection. Specifically, we first propose a novel rendering‐based object augmentation technique (Ren‐Aug) to enrich training data while enhancing scene realism. Second, we propose a local augmentation technique (Local‐Aug) to generate local noise by rotating and scaling objects in the scene while avoiding collisions, which can improve generalisation performance. Finally, we make full use of the structural information of 3D labels to make the model more robust by randomly changing the geometry of objects in the training frames. We verify the proposed framework with four different types of 3D object detectors. Experimental results show that our proposed Syn‐Aug significantly improves the performance of various 3D object detectors in the KITTI and nuScenes datasets, proving the effectiveness and generality of Syn‐Aug. On KITTI, four different types of baseline models using Syn‐Aug improved mAP by 0.89%, 1.35%, 1.61% and 1.14% respectively. On nuScenes, four different types of baseline models using Syn‐Aug improved mAP by 14.93%, 10.42%, 8.47% and 6.81% respectively. The code is available at https://github.com/liuhuaijjin/Syn‐Aug .
- 21 April 2025
- Published by Institution of Engineering and Technology (IET) in CAAI Transactions on Intelligence Technology
- Vol. 10 (3) , 912-928
Open AccessSyn‐Aug: An Effective and General Synchronous Data Augmentation Framework for 3D Object Detection
Data augmentation plays an important role in boosting the performance of 3D models, while very few studies handle the 3D point cloud data with this technique. Global augmentation and cut‐paste are commonly used augmentation techniques for point clouds, where global augmentation is applied to the entire point cloud of the scene, and cut‐paste samples objects from other frames into the current frame. Both types of data augmentation can improve performance, but the cut‐paste technique cannot effectively deal with the occlusion relationship between the foreground object and the background scene and the rationality of object sampling, which may be counterproductive and may hurt the overall performance. In addition, LiDAR is susceptible to signal loss, external occlusion, extreme weather and other factors, which can easily cause object shape changes, while global augmentation and cut‐paste cannot effectively enhance the robustness of the model. To this end, we propose Syn‐Aug, a synchronous data augmentation framework for LiDAR‐based 3D object detection. Specifically, we first propose a novel rendering‐based object augmentation technique (Ren‐Aug) to enrich training data while enhancing scene realism. Second, we propose a local augmentation technique (Local‐Aug) to generate local noise by rotating and scaling objects in the scene while avoiding collisions, which can improve generalisation performance. Finally, we make full use of the structural information of 3D labels to make the model more robust by randomly changing the geometry of objects in the training frames. We verify the proposed framework with four different types of 3D object detectors. Experimental results show that our proposed Syn‐Aug significantly improves the performance of various 3D object detectors in the KITTI and nuScenes datasets, proving the effectiveness and generality of Syn‐Aug. On KITTI, four different types of baseline models using Syn‐Aug improved mAP by 0.89%, 1.35%, 1.61% and 1.14% respectively. On nuScenes, four different types of baseline models using Syn‐Aug improved mAP by 14.93%, 10.42%, 8.47% and 6.81% respectively. The code is available at https://github.com/liuhuaijjin/Syn‐Aug .
- Open Access
- 29 October 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (10) , 1-23
MSSA: Multi-Representation Semantics-Augmented Set Abstraction for 3D Object Detection
Accurate recognition and localization of 3D objects is a fundamental research problem in 3D computer vision. Benefiting from transformation-free point cloud processing and flexible receptive fields, point-based methods have become accurate in 3D point cloud modeling, but still fall behind voxel-based competitors in 3D detection. We observe that the set abstraction module, commonly utilized by point-based methods for downsampling points, tends to retain excessive irrelevant background information, thus hindering the effective learning of features for object detection tasks. To address this issue, we propose MSSA, a Multi-representation Semantics-augmented Set Abstraction for 3D object detection. Specifically, we first design a backbone network to encode different representation features of point clouds, which extracts point-wise features through PointNet to preserve fine-grained geometric structure features, and adopts VoxelNet to extract voxel features and BEV features to enhance the semantic features of key points. Second, to efficiently fuse different representation features of keypoints, we propose a Point feature-guided Voxel feature and BEV feature fusion (PVB-Fusion) module to adaptively fuse multi-representation features and remove noise. At last, a novel Multi-representation Semantic-guided Farthest Point Sampling (MS-FPS) algorithm is designed to help set abstraction modules progressively downsample point clouds, thereby improving instance recall and detection performance with more important foreground points. We evaluate MSSA on the widely used KITTI dataset and the more challenging nuScenes dataset. Experimental results show that compared to PointRCNN, our method improves the AP of “moderate” level for three classes of objects by 7.02%, 6.76%, and 5.44%, respectively. Compared to the advanced point-voxel-based method PV-RCNN, our method improves the AP of “moderate” level by 1.23%, 2.84%, and 0.55% for the three classes, respectively.
- 29 October 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (10) , 1-23
Open AccessMSSA: Multi-Representation Semantics-Augmented Set Abstraction for 3D Object Detection
Accurate recognition and localization of 3D objects is a fundamental research problem in 3D computer vision. Benefiting from transformation-free point cloud processing and flexible receptive fields, point-based methods have become accurate in 3D point cloud modeling, but still fall behind voxel-based competitors in 3D detection. We observe that the set abstraction module, commonly utilized by point-based methods for downsampling points, tends to retain excessive irrelevant background information, thus hindering the effective learning of features for object detection tasks. To address this issue, we propose MSSA, a Multi-representation Semantics-augmented Set Abstraction for 3D object detection. Specifically, we first design a backbone network to encode different representation features of point clouds, which extracts point-wise features through PointNet to preserve fine-grained geometric structure features, and adopts VoxelNet to extract voxel features and BEV features to enhance the semantic features of key points. Second, to efficiently fuse different representation features of keypoints, we propose a Point feature-guided Voxel feature and BEV feature fusion (PVB-Fusion) module to adaptively fuse multi-representation features and remove noise. At last, a novel Multi-representation Semantic-guided Farthest Point Sampling (MS-FPS) algorithm is designed to help set abstraction modules progressively downsample point clouds, thereby improving instance recall and detection performance with more important foreground points. We evaluate MSSA on the widely used KITTI dataset and the more challenging nuScenes dataset. Experimental results show that compared to PointRCNN, our method improves the AP of “moderate” level for three classes of objects by 7.02%, 6.76%, and 5.44%, respectively. Compared to the advanced point-voxel-based method PV-RCNN, our method improves the AP of “moderate” level by 1.23%, 2.84%, and 0.55% for the three classes, respectively.
- Open Access
- 7 June 2022
- Published by Springer Nature in EURASIP Journal on Image and Video Processing
- Vol. 2022 (1) , 1-18
Performance analysis of different DCNN models in remote sensing image object detection
In recent years, deep learning, especially deep convolutional neural networks (DCNN), has made great progress. Many researchers use different DCNN models to detect remote sensing targets. Different DCNN models have different advantages and disadvantages. In this paper, we use YoloV4 as the detector to “fine-tune” various mainstream deep convolutional neural networks on two large public remote sensing data sets−LEVIR data set and DOTA data set to compare the advantages of various networks. This paper analyzes the reasons why the effect of “fine-tuning” convolutional neural networks is sometimes not good, and points out the difficulties of object detection in optical remote sensing images. To improve the detection accuracy of optical remote sensing targets, in addition to “fine-tuning” convolutional neural network, we also provide a variety of adaptive multi-scale feature fusion methods to improve the detection accuracy. In addition, for the large number of parameters generated by deep convolutional neural network, we provide a method to save storage space.
- 7 June 2022
- Published by Springer Nature in EURASIP Journal on Image and Video Processing
- Vol. 2022 (1) , 1-18
Open AccessPerformance analysis of different DCNN models in remote sensing image object detection
In recent years, deep learning, especially deep convolutional neural networks (DCNN), has made great progress. Many researchers use different DCNN models to detect remote sensing targets. Different DCNN models have different advantages and disadvantages. In this paper, we use YoloV4 as the detector to “fine-tune” various mainstream deep convolutional neural networks on two large public remote sensing data sets−LEVIR data set and DOTA data set to compare the advantages of various networks. This paper analyzes the reasons why the effect of “fine-tuning” convolutional neural networks is sometimes not good, and points out the difficulties of object detection in optical remote sensing images. To improve the detection accuracy of optical remote sensing targets, in addition to “fine-tuning” convolutional neural network, we also provide a variety of adaptive multi-scale feature fusion methods to improve the detection accuracy. In addition, for the large number of parameters generated by deep convolutional neural network, we provide a method to save storage space.
- Open Access
- 21 December 2021
- Published by Wiley in Scientific Programming
- Vol. 2021, 1-11
Enhancing Point Features with Spatial Information for Point-Based 3D Object Detection
Currently, there are many kinds of voxel-based multisensor 3D object detectors, while point-based multisensor 3D object detectors have not been fully studied. In this paper, we propose a new 3D two-stage object detection method based on point cloud and image fusion to improve the detection accuracy. To address the problem of insufficient semantic information of point cloud, we perform multiscale deep fusion of LiDAR point and camera image in a point-wise manner to enhance point features. Due to the imbalance of LiDAR points, the object point cloud in the long-distance area is sparse. We design a point cloud completion module to predict the spatial shape of objects in the candidate boxes and extract the structural information to improve the feature representation ability to further refine the boxes. The framework is evaluated on widely used KITTI and SUN-RGBD dataset. Experimental results show that our method outperforms all state-of-the-art point-based 3D object detection methods and has comparable performance to voxel-based methods as well.
- 21 December 2021
- Published by Wiley in Scientific Programming
- Vol. 2021, 1-11
Open AccessEnhancing Point Features with Spatial Information for Point-Based 3D Object Detection
Currently, there are many kinds of voxel-based multisensor 3D object detectors, while point-based multisensor 3D object detectors have not been fully studied. In this paper, we propose a new 3D two-stage object detection method based on point cloud and image fusion to improve the detection accuracy. To address the problem of insufficient semantic information of point cloud, we perform multiscale deep fusion of LiDAR point and camera image in a point-wise manner to enhance point features. Due to the imbalance of LiDAR points, the object point cloud in the long-distance area is sparse. We design a point cloud completion module to predict the spatial shape of objects in the candidate boxes and extract the structural information to improve the feature representation ability to further refine the boxes. The framework is evaluated on widely used KITTI and SUN-RGBD dataset. Experimental results show that our method outperforms all state-of-the-art point-based 3D object detection methods and has comparable performance to voxel-based methods as well.
- 1 January 2012
- Published by Springer Nature
- p. 143-148
Study on the Integration of College Sports Network Education Resource under Modern Distance Education Background
- 1 January 2012
- Published by Springer Nature
- p. 143-148
Study on the Integration of College Sports Network Education Resource under Modern Distance Education Background