Expectations by computer vision technology to change traditional teaching model has become the research focus of many scholars, but due to lack of specific training data, and the classroom students intensive distribution, variety, easy to keep out each other, the existing multiple object detection and object tracking technique is applied to the poor performance of the teaching scene. For the above problems, in the stage of multi object detection, considering that the head can not only represent the multi-pose student object, but also is not easy to be completely blocked, this paper established a small dataset of teaching scenes with the head as the detection object to train and improve the accuracy of the Faster R-CNN detector. In the multi object tracking stage, the Kalman filter and Hungarian algorithm are used for tracking, and then the unmatched trajectory is remapped to the depth feature map based on the strong feature extraction ability of Faster R-CNN backbone neural network. Then, we correct the unmatched trajectory by fusing the depth feature information and historical trajectory position information of the object, and calculate the trajectory similarity, which improves the problems of identity switching and trajectory interruption caused by the change of object attitude and occlusion. The research of this paper is used in real teaching scenes, which can assist teachers to track students' status and the formed student object trajectory sequence, and can provide data input for subsequent classroom behavior analysis.
Facial expression recognition is a hot research topic in artificial intelligence industry and has a good research prospect in various fields. At present, facial expression recognition processes the whole face directly, but the pixel value of non-feature region may bring some interference for feature descriptor extraction. Considering that the cartoon effect of the face can directly reflect the facial expression features. In order to make the network pay more attention to the information of the facial features and their surrounding pixels, this paper proposes an expression recognition algorithm based on key point detection of Covering multi-scale Practical Landmark Detector (CM-PFLD). Under this algorithm, this paper constructs a cartoon expression data set, which only retains the key points of facial expression information, and then classifies facial expression by directly locating the key points of facial expression information. In order to verify the feasibility of the expression recognition method in this paper. The experiment uses Fer2013 and CK data sets to produce cartoon expression data sets, and trains and compares cartoon data sets and original data sets respectively under the same network. The experimental results show that the method proposed in this paper has high detection accuracy and fast speed on standardized and neat data sets. On the data set with more unfavorable factors, the training accuracy of the two methods is similar, but the processing speed of the proposed method is faster. Experimental results show that the proposed method is feasible and effective.
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.