LSLihui Sun

Lihui Sun

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Lihui Sun has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Three-Dimensional Object Segmentation Method based on YOLO, SAM, and NeRF

    by Xinkai Wang, Liang Yuan, Lihui Sun, Shangzhe Wu, Ajian Liu

    The neural radiance field (NeRF) representation has shown promising results in capturing 3D scenes. However, when it comes to editing or moving specific objects within virtual environments, it is essential to segment individual objects from the neural radiance field. Existing methods primarily rely on feature computation and clustering for 3D segmentation, but they often suffer from poor segmentation quality and low accuracy. Taking advantage of recent advancements in 2D image segmentation, we propose a 3D segmentation method that generates single-object segmentation from multiple viewpoint images. First, we compute camera poses using feature points from the original images. Then, with user guidance, we use the You Only Look Once (YOLO) network model to roughly locate the objects and utilize the resulting information as hints. Subsequently, we employ the Segment Anything Model (SAM) for fine-grained segmentation. The processed dataset is then rendered into a 3D segmented object using the neural radiance field, producing high-quality rendered images. By training on specific objects, we can segment object categories that the publicly available YOLO model cannot recognize, thereby enhancing generalization. Through experiments, we analyze the real-time performance of each module and qualitatively and quantitatively evaluate the effectiveness of our method. Compared to the N3F and ISRF methods, our approach achieves an average 17% improvement in Intersection over Union (IoU) and an average 9% improvement in Pixel Accuracy (Acc). We validate the performance of our method on the LLFF, mip-Nerf360 datasets, demonstrating its generalizability and effectiveness.


  • Open Access

    An Object Detection Algorithm Based on Multiple Attention Mechanisms

    by Jiazhi Guo, Liang Yuan, Lihui Sun, Xiaoyu Ni, Ajian Liu

    In the field of autonomous driving, a novel approach is proposed for detecting and recognizing surrounding vehicles targets. The proposed method combines multiple attention mechanisms within a 3D object detection algorithm, drawing inspiration from the PointPillars network. Firstly, an additional local attention mechanism layer is incorporated into the point cloud pillar feature extraction module. This augmentation allows for a more comprehensive fusion of surrounding point cloud feature during the point cloud feature extraction process. Secondly, a channel attention mechanism module is introduced to the 2D image backbone network. The resulting features are subsequently inputted into the SSD algorithm for object detection. The improved algorithm's effectiveness has been demonstrated through an experimental evaluation on the popular KITTI dataset. The results show a significant improvement in average mean accuracy compared to the original algorithm, indicating that the attention mechanisms successfully enhance the detection and recognition performance of surrounding vehicles in autonomous driving scenarios.

  • A Reconfigurable Wideband Antenna Decoupling Structure by Mode Cancellation Method

    by Shengchi Zhu, Lihui Sun, Mengting Xie, Xin Ouan, Zhenxin Cao

    A novel reconfigurable wideband mutual decoupling structure is presented in this paper. By inserting lumped reactance components between two E-plane broadband $L$ -probe microstrip patch antennas, the parallel resonator composed of inductors and capacitors can reduce the mutual coupling based on common and differential modes cancellation method. To demonstrate the decoupling methodology, a dual-antenna array with proposed structure model is built up and simulated in commercial software HFSS. Simulated results show that a decoupling bandwidth of about 300 MHz with the S 21 less than -25 dB has been achieved at different resonant frequencies. Especially, the mutual coupling can be reduced by near 35 dB, from -15 dB to -50 dB, at both 3.76 GHz and 4.51 GHz. Consequently, by adjusting the inductance and capacitance values to shift the resonant frequencies, an overall decoupling bandwidth of approximately 37.5% (S 21 ≤ -25 dB) has been achieved from 3.5 GHz to 5 GHz, while the whole operating frequency band of the dual-antenna system is 3.23 ~ 5.11 GHz.