Human interaction recognition method based on parallel multi-feature fusion network

Human activity recognition is a key technology in intelligent video surveillance and an important research direction in the field of computer vision. However, the complexity of human interaction features and the differences in motion characteristics at different time periods have always existed. In this paper, a human interaction recognition algorithm based on parallel multi-feature fusion network is proposed. First of all, in view of the different amount of information provided by the different time periods of action, an improved time-phased video down sampling method based on Gaussian model is proposed. Second, the Inception module uses different scale convolution kernels for feature extraction. It can improve network performance and reduce the amount of network parameters at the same time. The ResNet module mitigates degradation problem due to increased depth of neural networks and achieves higher classification accuracy. The amount of information provided in the motion video in different stages of motion time is also different. Therefore, we combine the advantages of the Inception network and ResNet to extract feature information, and then we integrate the extracted features. After the extracted features are merged, the training is continued to realize parallel connection of the multi-feature neural network. In this paper, experiments are carried out on the UT dataset. Compared with the traditional activity recognition algorithm, this method can accomplish the recognition tasks of six kinds of interactive actions in a better way, and its accuracy rate reaches 88.9%.

Working memory enhancement during early childhood based on the utilization of interactive gesture game-based learning technique

<p>The use of human computer interaction is considered to be the most culturally and socially meritorious for the learning and playing activities of children. In this paper, a human interaction recognition system (HIRS) that includes gesture game-based learning is investigated for identifying its suitability and applicability in stimulation of working memory and primitive mathematical skills among the children in the early childhood period that ranges from 5 and 8 years. In the proposed human interaction recognition system, the hand gestures are facilitated by the user for the objective of controlling the computer system based on the information extracted from the user gestures.This proposed research was implemented in three phases using a quasi-experimental design that in turn incorporates pre-test and post-test for investigating the behavior of experimental and control group considered from the respondents. In the first phase, the initial evaluation of the learner’s skill is achieved. The second phase used the developed technology in order to identify diversified parameters in different dimensions that contribute towards the assessment of working memory and primitive mathematical capabilities. Finally, the third phase is responsible for actual evaluation. In the phases of evaluation, four working memory tests such as forward Corsi Blocking-Tapping test, backward Corsi Blocking-Tapping test, Forward Digit Span test and backwardDigit Span test was conducted. In addition, the evaluation was also conducted for assessing primitive mathematical skill of children using TEDI-MATH. The results confirmed that Gesture Interactive Game-Based Learning (GIGL) used by the children exhibited a predominant improvement in the working memory and primitive mathematical skills on par with their usual school activities.</p>