jianqi zhong

Mr. jianqi zhong

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
28 January 2020 in IEEE Access
Verified
Journal Article
Open access
JZjianqi zhong
jianqi zhong
HSHao Sun
Hao Sun
WCWenming Cao
Wenming Cao
ZHZhihai He
Zhihai He
Existing methods for pedestrian motion trajectory prediction are learning and predicting the trajectories in the 2D image space. In this work, we observe that it is much more efficient to learn and predict pedestrian trajectories in the 3D space since the human motion occurs in the 3D physical world and and their behavior patterns are better represented in the 3D space. To this end, we use a stereo camera system to detect and track the human pose with deep neural networks. During pose estimation, these twin deep neural networks satisfy the stereo consistence constraint. We adapt the existing SocialGAN method to perform pedestrian motion trajectory prediction from the 2D to the 3D space. Our extensive experimental results demonstrate that our proposed method significantly improves the pedestrian trajectory prediction performance, outperforming existing state-of-the-art methods.

3 November 2023 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
JSJunyu Shi
Junyu Shi
JZjianqi zhong
jianqi zhong
WCWenming Cao
Wenming Cao
Graph convolutional network-based methods have recently shown promising performance in skeleton-based data processing. However, these methods have two critical issues in skeleton-based motion prediction tasks: First, graph modeling of motion poses is based on the fixed graph according to the physical connection of human joints and ignores the exploration of deep implicit information based on human dynamic kinetics. Second, existing methods usually use motion information in a single semantic space to model the whole motion sequences, underestimating diverse semantic patterns for improving the modeling ability. To address the first issue, we propose the Attention-based Dynamic Graph Convolution method, which tries to capture implicit semantic information dynamically. To address the second issue, we propose the Kinematic-based Semantics Aggregation Block (KSAB), which combines various semantic features from four semantic perspectives to rich motion representation. Integrating the above two designs, we propose a novel Multi-Semantics Aggregation Network (MANet), resulting in more comprehensive feature extraction in dynamic implicit semantics learning to enhance motion prediction. Extensive experiments are conducted to validate the effectiveness of MANet, which outperforms state-of-the-art methods by 10.9%, 6.6%, and 19.6% in terms of MPJPE for motion prediction on Human3.6M, CMU Mocap, and 3DPW datasets, respectively.

13 February 2023 in Pattern Recognition
Verified
Journal Article
Closed access
JZjianqi zhong
jianqi zhong
WCWenming Cao
Wenming Cao

30 July 2019 in IEEE Access
Verified
Journal Article
Open access
WCWenming Cao
Wenming Cao
JZjianqi zhong
jianqi zhong
GCGuitao Cao
Guitao Cao
ZHZhiquan He
Zhiquan He
This paper presented a framework based on fog computing for convenient and efficient Physiological Function Assessment, which consists of three parts: 1)measuring the degree of joint mobility; 2) investigating the abnormality of actions of upper limbs; and 3) abnormal gait detection for lower limbs. Especially, we introduced semi-automatic Rapid Upper Limb Assessment (RULA) using Kinect v2 for the upper limb motion evaluation. Since a specific action can be described by action sequences of different length, we used dynamic time warping (DTW) to find the similarity between action sequences with different length. Traditional DTW algorithm does not work well when the action sequences are long and complex. To address this problem, we improved the DTW method by modifying the mapping relationship and limiting the computation space. Our modified DTW algorithm was evaluated on a standard 3D action dataset (SYSU 3D HOI) and Human Upper Action dataset (HUA), achieving the accuracy of 83.75%, 89.50%, respectively. The result is significantly better than the traditional DTW and the reported methods. In our previous work, we described the framework and how to make physiological function assessment. The goal of this paper is to 1) enrich the experiments of previous work and 2) introduce the framework of using RULA for physiological function assessment. All the tests have been done in this framework based on fog computing.


28 October 2022 in Frontiers in Computational Neuroscience
Verified
Journal Article
Open access
MUMuhammad Usman
Muhammad Usman
JZjianqi zhong
jianqi zhong
Human motion prediction based on 3D skeleton data is an active research topic in computer vision and multimedia analysis, which involves many disciplines, such as image processing, pattern recognition, and artificial intelligence. As an effective representation of human motion, human 3D skeleton data is favored by researchers because it provide resistant to light effects, scene changes, etc. earlier studies on human motion prediction focuses mainly on RBG data-based techniques. In recent years, researchers have proposed the fusion of human skeleton data and depth learning methods for human motion prediction and achieved good results. We first introduced human motion prediction research background and significance in this survey. We then summarized the latest deep learning-based techniques for predicting human motion in recent years. Finally, a detailed paper review and future development discussion are provided.