Intelligent Sports Video Classification Based on Deep Neural Network (DNN) Algorithm and Transfer Learning

Traditional text annotation-based video retrieval is done by manually labeling videos with text, which is inefficient and highly subjective and generally cannot accurately describe the meaning of videos. Traditional content-based video retrieval uses convolutional neural networks to extract the underlying feature information of images to build indexes and achieves similarity retrieval of video feature vectors according to certain similarity measure algorithms. In this paper, by studying the characteristics of sports videos, we propose the histogram difference method based on using transfer learning and the four-step method based on block matching for mutation detection and fading detection of video shots, respectively. By adaptive thresholding, regions with large frame difference changes are marked as candidate regions for shots, and then the shot boundaries are determined by mutation detection algorithm. Combined with the characteristics of sports video, this paper proposes a key frame extraction method based on clustering and optical flow analysis, and experimental comparison with the traditional clustering method. In addition, this paper proposes a key frame extraction algorithm based on clustering and optical flow analysis for key frame extraction of sports video. The algorithm effectively removes the redundant frames, and the extracted key frames are more representative. Through extensive experiments, the keyword fuzzy finding algorithm based on improved deep neural network and ontology semantic expansion proposed in this paper shows a more desirable retrieval performance, and it is feasible to use this method for video underlying feature extraction, annotation, and keyword finding, and one of the outstanding features of the algorithm is that it can quickly and effectively retrieve the desired video in a large number of Internet video resources, reducing the false detection rate and leakage rate while improving the fidelity, which basically meets people’s daily needs.

Research on Aerobics Training and Evaluation Method Based on Artificial Intelligence-Aided Modeling

Traditional aerobics training methods have the problems of lack of auxiliary teaching conditions and low-training efficiency. With the in-depth application of artificial intelligence and computer-aided training methods in the field of aerobics teaching and practice, this paper proposes a local space-time preserving Fisher vector (FV) coding method and monocular motion video automatic scoring technology. Firstly, the gradient direction histogram and optical flow histogram are extracted to describe the motion posture and motion characteristics of the human body in motion video. After normalization and data dimensionality reduction based on the principal component analysis, the human motion feature vector with discrimination ability is obtained. Then, the spatiotemporal pyramid method is used to embed spatiotemporal features in FV coding to improve the ability to identify the correctness and coordination of human behavior. Finally, the linear model of different action classifications is established to determine the action score. In the key frame extraction experiment of the aerobics action video, the ST-FMP model improves the recognition accuracy of uncertain human parts in the flexible hybrid joint human model by about 15 percentage points, and the key frame extraction accuracy reaches 81%, which is better than the traditional algorithm. This algorithm is not only sensitive to human motion characteristics and human posture but also suitable for sports video annotation evaluation, which has a certain reference significance for improving the level of aerobics training.

Real-Time Closed-Loop Detection Method of vSLAM Based on a Dynamic Siamese Network

As visual simultaneous localization and mapping (vSLAM) is easy disturbed by the changes of camera viewpoint and scene appearance when building a globally consistent map, the robustness and real-time performance of key frame image selections cannot meet the requirements. To solve this problem, a real-time closed-loop detection method based on a dynamic Siamese networks is proposed in this paper. First, a dynamic Siamese network-based fast conversion learning model is constructed to handle the impact of external changes on key frame judgments, and an elementwise convergence strategy is adopted to ensure the accurate positioning of key frames in the closed-loop judgment process. Second, a joint training strategy is designed to ensure the model parameters can be learned offline in parallel from tagged video sequences, which can effectively improve the speed of closed-loop detection. Finally, the proposed method is applied experimentally to three typical closed-loop detection scenario datasets and the experimental results demonstrate the effectiveness and robustness of the proposed method under the interference of complex scenes.