Yu Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yu Sun has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Hua Yang
College of Information Science and Engineering, Shanxi Agricultural University, Jinzhong 030801, China
3 shared publications - Xindong Guo
College of Information Science and Engineering, Shanxi Agricultural University, Jinzhong 030801, China
3 shared publications - Dongwei Zhang
College of Information Science and Engineering, Shanxi Agricultural University, Jinzhong 030801, China
1 shared publication
Latest Publications
- Open Access
Win-Former: Window-Based Transformer for Maize Plant Point Cloud Semantic Segmentation
Semantic segmentation of plant point clouds is essential for high-throughput phenotyping systems, while existing methods still struggle to balance efficiency and performance. Recently, the Transformer architecture has revolutionized the area of computer vision, and has potential for processing 3D point clouds. Applying the Transformer for semantic segmentation of 3D plant point clouds remains a challenge. To this end, we propose a novel window-based Transformer (Win-Former) network for maize 3D organic segmentation. First, we pre-processed the Pheno4D maize point cloud dataset for training. The maize points were then projected onto a sphere surface, and a window partition mechanism was proposed to construct windows into which points were distributed evenly. After that, we employed local self-attention within windows for computing the relationship of points. To strengthen the windows’ connection, we introduced a Cross-Window self-attention (C-SA) module to gather the cross-window features by moving entire windows along the sphere. The results demonstrate that Win-Former outperforms the famous networks and obtains 83.45% mIoU with the lowest latency of 31 s on maize organ segmentation. We perform extensive experiments on ShapeNet to evaluate stability and robustness, and our proposed model achieves competitive results on part segmentation tasks. Thus, our Win-Former model effectively and efficiently segments the maize point cloud and provides technical support for automated plant phenotyping analysis.
Open AccessWin-Former: Window-Based Transformer for Maize Plant Point Cloud Semantic Segmentation
Semantic segmentation of plant point clouds is essential for high-throughput phenotyping systems, while existing methods still struggle to balance efficiency and performance. Recently, the Transformer architecture has revolutionized the area of computer vision, and has potential for processing 3D point clouds. Applying the Transformer for semantic segmentation of 3D plant point clouds remains a challenge. To this end, we propose a novel window-based Transformer (Win-Former) network for maize 3D organic segmentation. First, we pre-processed the Pheno4D maize point cloud dataset for training. The maize points were then projected onto a sphere surface, and a window partition mechanism was proposed to construct windows into which points were distributed evenly. After that, we employed local self-attention within windows for computing the relationship of points. To strengthen the windows’ connection, we introduced a Cross-Window self-attention (C-SA) module to gather the cross-window features by moving entire windows along the sphere. The results demonstrate that Win-Former outperforms the famous networks and obtains 83.45% mIoU with the lowest latency of 31 s on maize organ segmentation. We perform extensive experiments on ShapeNet to evaluate stability and robustness, and our proposed model achieves competitive results on part segmentation tasks. Thus, our Win-Former model effectively and efficiently segments the maize point cloud and provides technical support for automated plant phenotyping analysis.
- Open Access
Lightweight Algorithm for Apple Detection Based on an Improved YOLOv5 Model
The detection algorithm of the apple-picking robot contains a complex network structure and huge parameter volume, which seriously limits the inference speed. To enable automatic apple picking in complex unstructured environments based on embedded platforms, we propose a lightweight YOLOv5-CS model for apple detection based on YOLOv5n. Firstly, we introduced the lightweight C3-light module to replace C3 to enhance the extraction of spatial features and boots the running speed. Then, we incorporated SimAM, a parameter-free attention module, into the neck layer to improve the model’s accuracy. The results showed that the size and inference speed of YOLOv5-CS were 6.25 MB and 0.014 s, which were and 1.2 times that of the YOLOv5n model, respectively. The number of floating-point operations (FLOPs) were reduced by 15.56%, and the average precision (AP) reached 99.1%. Finally, we conducted extensive experiments, and the results showed that the YOLOv5-CS outperformed mainstream networks in terms of AP, speed, and model size. Thus, our real-time YOLOv5-CS model detects apples in complex orchard environments efficiently and provides technical support for visual recognition systems for intelligent apple-picking devices.Open AccessLightweight Algorithm for Apple Detection Based on an Improved YOLOv5 Model
The detection algorithm of the apple-picking robot contains a complex network structure and huge parameter volume, which seriously limits the inference speed. To enable automatic apple picking in complex unstructured environments based on embedded platforms, we propose a lightweight YOLOv5-CS model for apple detection based on YOLOv5n. Firstly, we introduced the lightweight C3-light module to replace C3 to enhance the extraction of spatial features and boots the running speed. Then, we incorporated SimAM, a parameter-free attention module, into the neck layer to improve the model’s accuracy. The results showed that the size and inference speed of YOLOv5-CS were 6.25 MB and 0.014 s, which were and 1.2 times that of the YOLOv5n model, respectively. The number of floating-point operations (FLOPs) were reduced by 15.56%, and the average precision (AP) reached 99.1%. Finally, we conducted extensive experiments, and the results showed that the YOLOv5-CS outperformed mainstream networks in terms of AP, speed, and model size. Thus, our real-time YOLOv5-CS model detects apples in complex orchard environments efficiently and provides technical support for visual recognition systems for intelligent apple-picking devices. - Open Access
FF-Net: Feature-Fusion-Based Network for Semantic Segmentation of 3D Plant Point Cloud
Semantic segmentation of 3D point clouds has played an important role in the field of plant phenotyping in recent years. However, existing methods need to down-sample the point cloud to a relatively small size when processing large-scale plant point clouds, which contain more than hundreds of thousands of points, which fails to take full advantage of the high-resolution of advanced scanning devices. To address this issue, we propose a feature-fusion-based method called FF-Net, which consists of two branches, namely the voxel-branch and the point-branch. In particular, the voxel-branch partitions a point cloud into voxels and then employs sparse 3D convolution to learn the context features, and the point-branch learns the point features within a voxel to preserve the detailed point information. Finally, an attention-based module was designed to fuse the two branch features to produce the final segmentation. We conducted extensive experiments on two large plant point clouds (maize and tomato), and the results showed that our method outperformed three commonly used models on both datasets and achieved the best mIoU of 80.95% on the maize dataset and 86.65% on the tomato dataset. Extensive cross-validation experiments were performed to evaluate the generalization ability of the models, and our method achieved promising segmentation results. In addition, the drawbacks of the proposed method were analyzed, and the directions for future works are given.
Open AccessFF-Net: Feature-Fusion-Based Network for Semantic Segmentation of 3D Plant Point Cloud
Semantic segmentation of 3D point clouds has played an important role in the field of plant phenotyping in recent years. However, existing methods need to down-sample the point cloud to a relatively small size when processing large-scale plant point clouds, which contain more than hundreds of thousands of points, which fails to take full advantage of the high-resolution of advanced scanning devices. To address this issue, we propose a feature-fusion-based method called FF-Net, which consists of two branches, namely the voxel-branch and the point-branch. In particular, the voxel-branch partitions a point cloud into voxels and then employs sparse 3D convolution to learn the context features, and the point-branch learns the point features within a voxel to preserve the detailed point information. Finally, an attention-based module was designed to fuse the two branch features to produce the final segmentation. We conducted extensive experiments on two large plant point clouds (maize and tomato), and the results showed that our method outperformed three commonly used models on both datasets and achieved the best mIoU of 80.95% on the maize dataset and 86.65% on the tomato dataset. Extensive cross-validation experiments were performed to evaluate the generalization ability of the models, and our method achieved promising segmentation results. In addition, the drawbacks of the proposed method were analyzed, and the directions for future works are given.