Lin Zhang
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
Lin Zhang has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Zongfang Ma
School of Information and Control Engineering, Xian University of Architecture and Technology, Xian, China
2 shared publications - Lizhen Ji
University of Michigan, Ann Arbor, USA
1 shared publication MeiTing Xin
1 shared publicationMing Yang
1 shared publication- Ning An
School of Mechanical Engineering, Xi’an Jiaotong University, Xi’an, P.R. China
1 shared publication - Ning An
Department of Mechanical Engineering, Xi’an Jiaotong University, Xi’an, China
1 shared publication
Latest Publications
- 26 December 2025
- Published by Elsevier in Information Sciences
- Vol. 742
YSAM-SLAM: A real-time performance enhancement algorithm for visual SLAM in dynamic environments
- 26 December 2025
- Published by Elsevier in Information Sciences
- Vol. 742
YSAM-SLAM: A real-time performance enhancement algorithm for visual SLAM in dynamic environments
- 28 January 2025
- Published by Springer Nature in Cluster Computing
- Vol. 28 (3) , 1-21
Automatic liver tumor segmentation based on improved Yolo-v5 and B-spline level set
- 28 January 2025
- Published by Springer Nature in Cluster Computing
- Vol. 28 (3) , 1-21
Automatic liver tumor segmentation based on improved Yolo-v5 and B-spline level set
- Open Access
- 1 December 2024
- Published by AIP Publishing in AIP Advances
- Vol. 14 (12)
Trajectory planning of seven-degree-of-freedom redundant manipulator in narrow space
Traditional six-degree-of-freedom manipulators struggle with obstacle avoidance and smooth target point arrival. This paper focuses on trajectory planning for a seven-degree-of-freedom redundant manipulator, introducing a trajectory optimization algorithm based on improved RRT* (I-RRT*) and cubic spline smoothing. The I-RRT* algorithm addresses the randomness in search tree expansion and enhances target orientation through an adaptive growth strategy and mixed sampling. In the experimental section, the I-RRT* method is compared to APF-RRT*, APF-RRT, RRT*, and RRT algorithms. Results demonstrate that I-RRT* outperforms these methods in path length, time efficiency, and overall optimization. In addition, the manipulator’s ability to safely and successfully reach target points in narrow spaces is confirmed. Overall, this study enhances the trajectory planning capabilities of seven-degree-of-freedom redundant manipulators in hazardous environments, enabling flexible navigation, effective obstacle avoidance, and precise target arrival.
- 1 December 2024
- Published by AIP Publishing in AIP Advances
- Vol. 14 (12)
Open AccessTrajectory planning of seven-degree-of-freedom redundant manipulator in narrow space
Traditional six-degree-of-freedom manipulators struggle with obstacle avoidance and smooth target point arrival. This paper focuses on trajectory planning for a seven-degree-of-freedom redundant manipulator, introducing a trajectory optimization algorithm based on improved RRT* (I-RRT*) and cubic spline smoothing. The I-RRT* algorithm addresses the randomness in search tree expansion and enhances target orientation through an adaptive growth strategy and mixed sampling. In the experimental section, the I-RRT* method is compared to APF-RRT*, APF-RRT, RRT*, and RRT algorithms. Results demonstrate that I-RRT* outperforms these methods in path length, time efficiency, and overall optimization. In addition, the manipulator’s ability to safely and successfully reach target points in narrow spaces is confirmed. Overall, this study enhances the trajectory planning capabilities of seven-degree-of-freedom redundant manipulators in hazardous environments, enabling flexible navigation, effective obstacle avoidance, and precise target arrival.
- Open Access
- 1 September 2024
- Published by AIP Publishing in AIP Advances
- Vol. 14 (9)
Research on hybrid segmentation technologies for postprocessing the lung and trachea CT images
This paper introduces a systematic method for segmenting the main trachea and bronchioles in lung computed tomography scans. It begins with a stack-based three-dimensional region growth algorithm to outline the main trachea, which is then refined using morphological techniques to improve accuracy. The segmentation of bronchioles is achieved through domain labeling, lung tissue segmentation, adaptive binarization, and inner product analysis. The main trachea and bronchioles are integrated using an operating room (OR) operation and a novel splicing algorithm to form a complete tracheal tree. The method’s accuracy is validated against manual labeling, showing a Dice coefficient of about 0.99, on average, in lung parenchyma segmentation and a segmentation overlap with expert results ranging from 79.89% to 93.31% in lung trachea tree segmentation. This robust methodology is thoroughly tested and validated.
- 1 September 2024
- Published by AIP Publishing in AIP Advances
- Vol. 14 (9)
Open AccessResearch on hybrid segmentation technologies for postprocessing the lung and trachea CT images
This paper introduces a systematic method for segmenting the main trachea and bronchioles in lung computed tomography scans. It begins with a stack-based three-dimensional region growth algorithm to outline the main trachea, which is then refined using morphological techniques to improve accuracy. The segmentation of bronchioles is achieved through domain labeling, lung tissue segmentation, adaptive binarization, and inner product analysis. The main trachea and bronchioles are integrated using an operating room (OR) operation and a novel splicing algorithm to form a complete tracheal tree. The method’s accuracy is validated against manual labeling, showing a Dice coefficient of about 0.99, on average, in lung parenchyma segmentation and a segmentation overlap with expert results ranging from 79.89% to 93.31% in lung trachea tree segmentation. This robust methodology is thoroughly tested and validated.
- 9 May 2024
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 80 (12) , 18009-18047
Research of hybrid path planning with improved A* and TEB in static and dynamic environments
- 9 May 2024
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 80 (12) , 18009-18047
Research of hybrid path planning with improved A* and TEB in static and dynamic environments
- 24 October 2023
- Published by Springer Nature in Cluster Computing
- Vol. 27 (3) , 3575-3591
Target positioning method based on B-spline level set and GC Yolo-v3
- 24 October 2023
- Published by Springer Nature in Cluster Computing
- Vol. 27 (3) , 3575-3591
Target positioning method based on B-spline level set and GC Yolo-v3
- Open Access
- 14 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 74841-74849
Object Detection Based on Deep Learning and B-Spline Level Set in Color Images
Object detection based on deep learning is a popular trend, and it includes object recognition and positioning. This paper proposes a method that can accurately obtain object type and accurate three-dimensional position. The method is divided into three parts: object recognition and coarse positioning based on deep learning, precise positioning based on deep learning combined with B-spline level set in color images, and precise three-dimensional positioning with depth information of RGB-D camera. The precise positioning of the object provides accurate end pose information for the autonomous grasping of the robotic arm, and it has great significance to the gripping of the robotic arm. Performance metrics include mAP (mean average precision) and IOU (intersection of a union). Experimental results show that the mAP value of Yolo-v3 in this paper can reach 87.62%, the average IOU of Yolo-v3 in this paper can reach 66.74%, the average IOU of Yolo-v3 and B-spline level set can reach 100%, and can get accurate 3D location in the real scene. In addition, the experiments comparisons between VOC dataset and our own dataset validate that our dataset can take higher mAP and average IOU values.
- 14 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 74841-74849
Open AccessObject Detection Based on Deep Learning and B-Spline Level Set in Color Images
Object detection based on deep learning is a popular trend, and it includes object recognition and positioning. This paper proposes a method that can accurately obtain object type and accurate three-dimensional position. The method is divided into three parts: object recognition and coarse positioning based on deep learning, precise positioning based on deep learning combined with B-spline level set in color images, and precise three-dimensional positioning with depth information of RGB-D camera. The precise positioning of the object provides accurate end pose information for the autonomous grasping of the robotic arm, and it has great significance to the gripping of the robotic arm. Performance metrics include mAP (mean average precision) and IOU (intersection of a union). Experimental results show that the mAP value of Yolo-v3 in this paper can reach 87.62%, the average IOU of Yolo-v3 in this paper can reach 66.74%, the average IOU of Yolo-v3 and B-spline level set can reach 100%, and can get accurate 3D location in the real scene. In addition, the experiments comparisons between VOC dataset and our own dataset validate that our dataset can take higher mAP and average IOU values.