Zhichao Song

Zhichao Song

Auto-generated profile, based on publicly available information

Zhichao Song

College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
27 December 2021
Verified
Conference Paper
Closed access
YMYiyang Meng
Yiyang Meng
YYYugen You
Yugen You
PGPengxiu Geng
Pengxiu Geng
ZSZhichao Song
Zhichao Song
HWHongpeng Wang
Hongpeng Wang
YQYanding Qin
Yanding Qin
Optical tracking system (OTS), an essential component of robot-assisted surgery, measures the position and orientation of the surgical tools during surgery operations. OTS has proven to be a reliable intra-operative navigation method in clinical applications. However, OTS suffers from the vision occlusion where obstacles block the vision of the position sensors of the OTS. To tackle with this problem, we propose an active navigation system which can automatically moves the OTS so as to avoid the occlusion and meanwhile maintain the tracking accuracy. The active navigation system is composed of a multi-DOF robot, an optical tracker and an RGB-D camera. The accuracy of OTS is influenced by several factors, such as working distance and relative orientation of the tracked tool. Since in the active navigation system, the OTS moves during navigation, the impact of the movement of OTS on its accuracy is investigated. The corresponding experiments are conducted, and the results are analyzed. Subsequently, an occlusion avoidance strategy is developed to control the OTS to not only avoid the obstacles but also keep the accuracy degradation acceptable. Ultimately, the occlusion avoidance experiment is conducted to verify the proposed strategy. The experimental results demonstrate the effectiveness of the proposed active navigation system.

28 February 2025 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
PZPanpan Zhu
Panpan Zhu
ZSZhichao Song
Zhichao Song
JLJiale Liu
Jiale Liu
JYJiazheng Yan
Jiazheng Yan
XLXiaobo Luo
Xiaobo Luo
YTYuxiang Tao
Yuxiang Tao
Accurate and complete extraction of buildings from very high resolution (VHR) remote sensing (RS) images is highly important for urban planning and land management. However, owing to the limited information available for small buildings and building boundaries, as well as challenges such as the spectral similarity of ground objects, tree occlusions, and shadow interference, automatically extracting buildings from VHR images remains challenging. These issues may result in building extraction errors such as misclassification, small building omission, blurred boundaries, and incorrect segmentation. To address these challenges, we propose a multiscale hybrid transformer (MSHFormer) with boundary enhancement. This approach incorporates a hybrid encoder that combines a multiscale local perception module (MSLP) and a global perception module (GPM), combining the strengths of convolutional neural networks (CNNs) and transformers to achieve efficient synergy between global modelling and local feature extraction. Additionally, we developed an edge enhancement module (EHM) to enhance boundary information, significantly improving building boundary segmentation accuracy. Finally, we design a group alignment feature fusion module (GAFFM) to efficiently integrate low-level features from the encoder with high-level features from the decoder, reducing feature space misalignment. The experimental results on three public datasets demonstrate the effectiveness of MSHFormer. Specifically, the proposed method achieves intersection-over-union (IoU) values of 89.1%, 73.6%, and 89.5% on the Potsdam, Massachusetts, and WHU datasets, respectively.