Zhi Li

Zhi Li

Auto-generated profile, based on publicly available information

Zhi Li

College of Electric and Information Engineering, Hunan Institute of Engineering, Xiangtan, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
14 August 2023 in IEEE Sensors Journal
Verified
Journal Article
Closed access
QWQin Wan
Qin Wan
RLRuifeng Lv
Ruifeng Lv
YXYueping Xiao
Yueping Xiao
ZLZhi Li
Zhi Li
XZXiaolin Zhu
Xiaolin Zhu
ZZZilong Zeng
Zilong Zeng
In complex tracking scenarios of multi-target occlusion, especially when the target is seriously occluded, feature loss can lead to tracking failure. In this paper, we develop a multi-target occlusion tracking algorithm based on a 3D spatio-temporal context graph model, which can fully utilize the targets’ RGB-D information. Specifically, we first extract target’s 3D features containing appearance, motion, spatial and temporal features. Then, the spatio-temporal context features between different targets are also be acquired. Furthermore, the Attribute Relational Graph (ARG) model with target’s 3D spatio-temporal context features is constructed, which combines spatial features in the current frame and temporal features between consecutive frames. Moreover, if the target is determined to be occluded according to the matching results in the current frame, the probability relaxation method is used to assign the optimal tracking label to clustering blocks in occlusion area by matching these ARG models, which can address the multi-target cross occlusion problem. Extensive experiments on the Princeton Tracking Benchmark Datasets clearly demonstrate that our method can achieve superior performance against the typical algorithms proposed in recent years.

17 July 2024 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
QWQin Wan
Qin Wan
ZLZhi Li
Zhi Li
YWYaonan Wang
Yaonan Wang
RLRuifeng Lv
Ruifeng Lv
HCHuaying Cheng
Huaying Cheng
DWDi Wu
Di Wu
The pedestrian-following robot aims to robustly maintain a standard distance from a specific pedestrian in an unknown complex environment, which is challenging when facing the limited field of view (FOV) and the computing resource constraints. However, the pedestrian-following robot commonly utilizes the long range dependence of targets to construct tracking models via the transformer tracking method, which is often insufficient to achieve real-time following. To address this important issue, we propose a new fast tracking network for the following robot, including a lightweight target detector, a target state prediction decoder, and an adaptive visual servo controller. First, in the lightweight target detector, a dense feature extraction process is designed by stacking depthwise group-separable convolutions. A context encoder is also developed, and is coupled with the proposed person re-identification (Re-ID) branch to detect multiple targets with high precision and speed. Second, in the target state prediction decoder, we introduce a flexible multiattention mechanism to obtain target Re-ID features from the previous frame for predicting the target's position in the current frame. Third, in the adaptive visual servo controller, we design a six-parameter dynamic model for the proportional integral derivative (PID) controller to stably follow the pedestrian under the limited FOV. Extensive experimental results demonstrate that the proposed method is efficient and accurate. Moreover, it also exhibits strong robustness and high real-time performance in unknown complex environments.

4 December 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
QWQin Wan
Qin Wan
SNShunxing Ning
Shunxing Ning
HTHaoran Tan
Haoran Tan
YWYaonan Wang
Yaonan Wang
XDXiaogang Duan
Xiaogang Duan
JQJianhua Qiu
Jianhua Qiu
Effectively integrating the complementary information from RGB-D images presents a significant challenge in robotic grasping. In this letter, we propose a full-flow bidirectional feature fusion grasp detection network (FFBGNet) based on a hybrid architecture to generate accurate grasp poses from RGB-D images. First, we construct an efficient Cross-Modal Feature fusion module as a bridge for information interaction in the full flow of the two branches, where fusion is applied to each encoding and decoding layer. Then, the two branches can fully leverage the appearance information in the RGB images and the geometry information from the depth images. Second, a hybrid architecture module for CNNs and Transformer parallel is developed to achieve better local feature and global information representations. Finally, we conduct qualitative and quantitative comparative experiments on the Cornell and Jacquard datasets, achieving grasping detection accuracies of 99.2${\%}$ and 96.5${\%}$, respectively. Simultaneously, in physical grasping experiments, the FFBGNet achieves a 96.7${\%}$ success rate in cluttered scenes, which further demonstrates the reliability of the proposed method.

20 December 2024
Verified
Conference Paper
Open access
QWQin Wan
Qin Wan
PXPin Xu
Pin Xu
SNShunxing Ning
Shunxing Ning
ZLZhi Li
Zhi Li
This paper proposes a vision-based formation control method for multi-robot systems in the absence of inter-robot communication, employing a leader-follower scheme with a single Kinect camera as the sole sensor. By utilizing a pose estimation algorithm based on RGBD images, the relative position and orientation of the leader are captured. An anticipated formation shape aligned in the same movement direction is generated using a dipole vector field, ensuring formation stability. To address the limited field of view of the Kinect camera, an auxiliary system is designed to transform visibility constraints into input constraints, enabling effective control under non-communicative conditions. Simulation and experimental results demonstrate that the proposed method achieves real-time and robust formation control despite visibility limitations, simplifying the system architecture and enhancing practicality.