In recent years, with the rapid increase in the number of cars in various countries, traffic accidents have also occurred frequently. Among them, traffic accidents caused by driver fatigue driving account for a large proportion, and how to improve the safety of driver driving has become a key issue. Therefore, this article proposes a driver face recognition and fatigue driving warning method based on computer vision. This article first uses the Adaboost face detection algorithm for face detection, and uses the Dlib toolkit to label facial key points. Then, by using these key points, the eye aspect ratio, mouth aspect ratio, and Euclidean distance between the two feature points of the nose are calculated. These three parameters are used as fatigue feature values for fatigue state judgment and corresponding warning experiments are given. Tests have shown that this method can reflect the fatigue status of drivers in real time and has good detection performance.
The intrusion of foreign objects into railways poses a great threat to the reliability and safety of railway systems. In order to effectively avoid such phenomena, this paper studies a method for detecting foreign objects in railway tracks based on deep learning principles. This method mainly includes two parts: rail detection and foreign object recognition. The rail detection part adopts a deep learning method based on UNet network semantic segmentation, which optimizes the convolutional structure of the UNet network into depthwise separable convolutions and inserts a spatial pyramid structure to improve the detection speed The foreign object recognition part adopts YOLOv5's deep learning method, which improves its detection accuracy by changing the loss function to SIoU, and adds a CA attention mechanism to determine the coordinates of the target and recognize and classify foreign objects. The experimental results show that the average recognition accuracy of the algorithm proposed in this paper on the dataset of railway foreign objects reaches 93.7%, which is 5.1% higher than the traditional YOLOv5 algorithm, indicating that the algorithm effectively improves the accuracy of railway foreign object intrusion recognition.
In the process of high-speed movement of multiple unit trains, the train wireless communication delay has a very important impact on driving safety. If the delay is too long, the train will not be able to control, traction and brake normally. Therefore, a wireless delay prediction model based on Singular Spectrum Analysis (SSA)-Quantum Particle Swarm Optimization (QPSO) to optimize Least Squares Support Vector Machine (LSSVM) is proposed. Firstly, to lower the complexity of the sequence, the measured time series is broken down into components corresponding to different eigenvalues after singular value processing. During the decomposition process, the window length is selected using the Cao method. Secondly, each sub sequence is trained by QPSO-LSSVM model to determine the optimal parameters of LSSVM. Finally, each predicted subsequence is superimposed to get the final predicted results. The simulation results show that the proposed method has higher prediction accuracy and minimum prediction error compared to SSA-PSOLSSVM, EMD-QPSO-LSSVM, and QPSO-LSSSVM methods.
KEYWORDS: Video, Education and training, Feature extraction, Video compression, Deep learning, Video processing, Video acceleration, Data modeling, Databases, Neural networks
This article proposes a no reference video quality assessment method based on deep learning, aiming to simulate human perception of video quality and evaluate videos. This method evaluates the quality of videos by learning effective feature representations in the spatiotemporal domain. First, in the spatial domain, 2D-CNN is used to extract the spatial quality of video frames. Then, in the temporal domain, Recurrent neural network (RNN) and pyramid feature aggregation (PFA) module are used to model the temporal domain and aggregate the frame level feature quality. The experiment shows that the method proposed in this paper has good performance on the KoNViD-1k and CVD2014 datasets, and also indicates that the method has high generalization ability.
In this paper, a neural network time delay prediction method based on phase space reconstruction is presented. This method reconstructs one-dimensional chaotic time series in phase space according to the internal law through phase space reconstruction, and uses BP neural network algorithm to predict the time delay. Simulation experiments show that this method has good prediction performance.
A time delay prediction method of train network based on wireless transmission is proposed. EMD is used to decompose the time delay series. The decomposed components with large sample entropy are DWT to form new components, in order to reduce the complexity of prediction. The components with similar sample entropy are combined into new components to reduce the amount of model calculation. Finally, each data component is predicted by particle swarm optimization LSSVM model. The simulation results show that the proposed method has high prediction accuracy.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.