A novel de-noising method for improving the performance of full-waveform light detection and ranging (LiDAR) based on differential optical path is proposed, and the mathematical models of this method are developed and verified. Backscattered full-waveform signal (BFWS) is detected by two avalanche photodiodes placed before and after the focus of the focusing lens. On the basis of the proposed method, some simulations are carried out and conclusions are achieved. (1) Background noise can be suppressed effectively and peak points of the BFWS are transformed into negative-going zero-crossing points as stop timing moments. (2) The relative increment percentage of the signal-to-noise ratio based on the proposed method first dramatically increases with the increase of the distance, and then the improvement gets smaller by increasing the distance. (3) The differential Gaussian fitting with the Levenberg-Marquardt algorithm is applied, and the results show that it can decompose the BFWS with high accuracy. (4) The differential distance should not be larger than c/2 × τ_rmin, and two variable gain amplifiers can eliminate the inconsistency of two differential beams. The results are beneficial for designing a better performance full-waveform LiDAR.

A retina-like 3D computational ghost imaging (R-3DCGI) is proposed to obtain high resolution while maintaining high imaging efficiency. R-3DCGI models are developed, and corresponding simulations are conducted to verify and evaluate the accuracy and features of the R-3DCGI. Results show that the models obtain rotation and scaling invariances and compress redundant information, thereby improving imaging efficiency over the traditional computational ghost imaging. The relationships between parameters of the retina-like models and signal–noise ratio are discussed to optimize the retina-like structures in various applications.

A Fourier single-pixel imaging technique based on lateral inhibition is proposed to improve the reconstruction contrast and quality for low-contrast scenes. The mathematical models are developed, and corresponding simulations and experiments are conducted to verify and evaluate the features. Results show that this strategy strengthens the image contrast and structural similarity index mainly under low sampling ratios compared with the traditional Fourier single-pixel imaging. It offers an optional solution for various Fourier single-pixel imaging applications at low sampling ratios for low-contrast scenes.

Balance ability is one of the important factors in measuring human physical fitness and a common index for evaluating sports performance. Its quality directly affects the coordination ability of human movements and plays an important role in human productive activities. In the field of sports, balance ability is an important indicator of athletes’ selection and training. How to objectively analyze balance performance becomes a problem for every non-professional sports enthusiast. Therefore, in this paper, we used a dataset of lower limb collected by inertial sensors to extract the feature parameters, then designed a RUS Boost classifier for unbalanced data whose basic classifier was SVM model to predict three classifications of balance degree, and, finally, evaluated the performance of the new classifier by comparing it with two basic classifiers (KNN, SVM). The result showed that the new classifier could be used to evaluate the balanced ability of lower limb, and performed higher than basic ones (RUS Boost: 72%; KNN: 60%; SVM: 44%). The results meant the established classification model could be used for and quantitative assessment of balance ability in initial screening and targeted training.

Recent advances in training monitoring are centered on the statistical indicators of the concentric phase of the movement. However, those studies lack consideration of the integrity of the movement. Moreover, training performance evaluation needs valid data on the movement. Thus, this study presents a full-waveform resistance training monitoring system (FRTMS) as a whole-movement-process monitoring solution to acquire and analyze the full-waveform data of resistance training. The FRTMS includes a portable data acquisition device and a data processing and visualization software platform. The data acquisition device monitors the barbell’s movement data. The software platform guides users through the acquisition of training parameters and provides feedback on the training result variables. To validate the FRTMS, we compared the simultaneous measurements of 30–90% 1RM of Smith squat lifts performed by 21 subjects with the FRTMS to similar measurements obtained with a previously validated three-dimensional motion capture system. Results showed that the FRTMS produced practically identical velocity outcomes, with a high Pearson’s correlation coefficient, intraclass correlation coefficient, and coefficient of multiple correlations and a low root mean square error. We also studied the applications of the FRTMS in practical training by comparing the training results of a six-week experimental intervention with velocity-based training (VBT) and percentage-based training (PBT). The current findings suggest that the proposed monitoring system can provide reliable data for refining future training monitoring and analysis.

In this paper, we tackle the new task of video-based Activated Muscle Group Estimation (AMGE) aiming at identifying active muscle regions during physical activity in the wild. To this intent, we provide the MuscleMap dataset featuring >15K video clips with 135 different activities and 20 labeled muscle groups. This dataset opens the vistas to multiple video-based applications in sports and rehabilitation medicine under flexible environment constraints. The proposed MuscleMap dataset is constructed with YouTube videos, specifically targeting High-Intensity Interval Training (HIIT) physical exercise in the wild. To make the AMGE model applicable in real-life situations, it is crucial to ensure that the model can generalize well to numerous types of physical activities not present during training and involving new combinations of activated muscles. To achieve this, our benchmark also covers an evaluation setting where the model is exposed to activity types excluded from the training set. Our experiments reveal that the generalizability of existing architectures adapted for the AMGE task remains a challenge. Therefore, we also propose a new approach, TransM3E, which employs a multi-modality feature fusion mechanism between both the video transformer model and the skeleton-based graph convolution model with novel cross-modal knowledge distillation executed on multi-classification tokens. The proposed method surpasses all popular video classification models when dealing with both, previously seen and new types of physical activities. The database and code can be found at https://github.com/KPeng9510/MuscleMap.