Proper stroke posture and rhythm are crucial for kayakers to achieve perfect performance and avoid the occurrence of sport injuries. The traditional video-based analysis method has numerous limitations (e.g., site and occlusion). In this study, we propose a systematic approach for evaluating the training performance of kayakers based on the multiple sensors fusion technology. Kayakers’ motion information is collected by miniature inertial sensor nodes attached on the body. The extend Kalman filter (EKF) method is used for data fusion and updating human posture. After sensor calibration, the kayakers’ actions are reconstructed by rigid-body model. The quantitative kinematic analysis is carried out based on joint angles. Machine learning algorithms are used for differentiating the stroke cycle into different phases, including entry, pull, exit and recovery. The experiment shows that our method can provide comprehensive motion evaluation information under real on-water scenario, and the phase identification of kayaker’s motions is up to 98% validated by videography method. The proposed approach can provide quantitative information for coaches and athletes, which can be used to improve the training effects.

Gait analysis, as a common inspection method for human gait, can provide a series of kinematics, dynamics and other parameters through instrumental measurement. In recent years, gait analysis has been gradually applied to the diagnosis of diseases, the evaluation of orthopedic surgery and rehabilitation progress, especially, gait phase abnormality can be used as a clinical diagnostic indicator of Alzheimer Disease and Parkinson Disease, which usually show varying degrees of gait phase abnormality. This research proposed an inertial sensor based gait analysis method. Smoothed and filtered angular velocity signal was chosen as the input data of the 15-dimensional temporal characteristic feature. Hidden Markov Model and parameter adaptive model are used to segment gait phases. Experimental results show that the proposed model based on HMM and parameter adaptation achieves good recognition rate in gait phases segmentation compared to other classification models, and the recognition results of gait phase are consistent with ground truth. The proposed wearable device used for data collection can be embedded on the shoe, which can not only collect patients’ gait data stably and reliably, ensuring the integrity and objectivity of gait data, but also collect data in daily scene and ambulatory outdoor environment.

Despite encouraging results have been achieved in human pose estimation in recent years, it remains challenging problems. The performance may degrade dramatically when the background is similar to the human body parts, and there are very small persons with low-resolution in the image. This paper addresses problems in background-inference and small-person images human pose estimation. To achieve this, a novel pose estimation algorithm is proposed on the basis of person semantic segmentation deep neural network. Different from most previous methods with a single pose estimation model, we generate mixture models with pose estimation and semantic segmentation. We introduce novel generative adversarial model and auxiliary model to realize the semantic segmentation network, which can handle the confusion of the similar regions in the background. In addition, to address the problem of the scale differences between big and small persons' keypoints, we add additional position and channel attention modules to the first two stages of OpenPose. We conduct extensive experiments on COCO and VOC datasets, and compare the proposed method with the most popular state-of-the-art human pose estimation and semantic segmentation frameworks, including MultiPoseNet, Deterton2 and DeepLab V3. Our experimental results show that the proposed method is more accurate than the state-of-the-art algorithms and performs effectively in tackling the complex situations.