n 主要研究方向
主要研究内容包括：利用计算机视觉技术，研究大众健身、运动训练等领域的应用，重点包括针对人的动作定位、分析与评价，对运动设备的定位与跟踪。相关成果在足篮排、乒乓球、羽毛球、网球、花样滑冰、武术等体育运动项目及运动训练、运动康复等领域得到了广泛的应用。
n 主要学术成果
1.武术动作定位与识别技术
图1 武术动作定位
图2 基于周期运动规律的武术动作识别模型架构
图3 于周期运动规律的武术动作识别特征分析
体育运动动作定位与识别是评价运动者动作姿态的基础。本课题组针对以武术为先期范例开展研究。如图1所示，通过人体骨骼关键点信息，分析动作的对应特征，采用模板匹配的方式与标准动作对比，定位动作的开始与结束区间。在此基础上，如图2所示，采用双支路模型，结合人体骨骼关键点获取运动员的动作信息，通过离散傅里叶变换获取动作的频率信息（如图3所示）。最后将双路特征融合并进行动作的评价。
l Qiurui Wang, Chun Yuan, Feiyue Huang, Chengjie Wang: Human Parsing via Shape Boltzmann Machine Networks. Pacific-Rim Conference on Multimedia 2015: 653-663
l Qiurui Wang, Chun Yuan, Yan Liu: Deep conditional neural network for image segmentation. IEEE International Conference on Multimedia & Expo 2016: 1-6
l Qiurui Wang, Chun Yuan: Video object segmentation by Multi-Scale Pyramidal Multi-Dimensional LSTM with generated depth context. International Conference on Image Processing 2016: 281-285
l Qiurui Wang, Chun Yuan, Zhihui Lin: Learning attentional recurrent neural network for visual tracking. IEEE International Conference on Multimedia & Expo 2017: 1237-1242
l Qiurui Wang, Chun Yuan, Jingdong Wang, Wenjun Zeng: Learning Attentional Recurrent Neural Network for Visual Tracking. IEEE Transactions on Multimedia. 21(4): 930-942 (2019)
l Qiurui Wang, Chun Yuan, Yan Liu: Learning Deep Conditional Neural Network for Image Segmentation. IEEE Transactions on Multimedia. 21(7): 1839-1852 (2019)
l Yiqun Pang, Qiurui Wang*, Changnian Zhang: Time-frequency domain pattern analysis of Tai Chi 12 GONG FA based on skeleton key points detection. Proceeding of SPIE, International Conference on Neural Networks, Information and Communication Engineering 2021: 431-436
l Qiurui Wang, Yiqun Pang, Mingyang Wang, Mingyuan Cui: FI-BRS: A Few-Interaction Backpropagating Refinement Scheme for Video Object Segmentation. 2021 3rd International Academic Exchange Conference on Science and Technology Innovation (IEEE IAECST), 2021. 731-735
l Yiqun Pang，Qiurui Wang*，Changnian Zhang，Mingyang Wang，Yibing Wang: Analysis of Computer Vision Applied in Martial Arts. 2022 2nd IEEE International Conference on Consumer Electronics and Computer Engineering (IEEE ICCECE), 2022. 1-1
l Qiurui Wang, Huijie Zhang,. Exploration of Gesture Recognition for Hand and Fingers Tenosynovitis Prevention and Rehabilitation. International University Sports Federation, 2021 Chengdu, Poster
l Yiqun Pang, Qiurui Wang*. Enlightenment of Computer Vision to Martial Arts Routine Scoring. International University Sports Federation, 2021 Chengdu, Poster
l Yiqun Pang, Yun-Xiang Pang, Qiurui Wang*. Revealing the Inner-relevance of College Students’ Physical Fitness by Association Analysis and Neural Network, Computational Intelligence and Neuroscience, vol. 2022, Article ID 3320942, 1687-5265, 2022, IF 3.12
