Redirigiendo al acceso original de articulo en 23 segundos...
Inicio  /  Applied Sciences  /  Vol: 12 Par: 13 (2022)  /  Artículo
ARTÍCULO
TITULO

Classroom Behavior Detection Based on Improved YOLOv5 Algorithm Combining Multi-Scale Feature Fusion and Attention Mechanism

Longyu Tang    
Tao Xie    
Yunong Yang and Hong Wang    

Resumen

The detection of students? behaviors in classroom can provide a guideline for assessing the effectiveness of classroom teaching. This study proposes a classroom behavior detection algorithm using an improved object detection model (i.e., YOLOv5). First, the feature pyramid structure (FPN+PAN) in the neck network of the original YOLOv5 model is combined with a weighted bidirectional feature pyramid network (BiFPN). They are subsequently processed with feature fusion of different scales of the object to mine the fine-grained features of different behaviors. Second, a spatial and channel convolutional attention mechanism (CBAM) is added between the neck network and the prediction network to make the model focus on the object information to improve the detection accuracy. Finally, the original non-maximum suppression is improved using the distance-based intersection ratio (DIoU) to improve the discrimination of occluded objects. A series of experiments were conducted on our new established dataset which includes four types of behaviors: listening, looking down, lying down, and standing. The results demonstrated that the algorithm proposed in this study can accurately detect various student behaviors, and the accuracy was higher than that of the YOLOv5 model. By comparing the effects of student behavior detection in different scenarios, the improved algorithm had an average accuracy of 89.8% and a recall of 90.4%, both of which were better than the compared detection algorithms.

 Artículos similares

       
 
Yunia Ikawati, M. Udin Harun Al Rasyid, Idris Winarno     Pág. 92 - 106
Learning styles are very important to know so that students can learn effectively. By understanding the learning style, students will learn about their needs in the learning process. One of the famous learning management systems is called Moodle. Moodle ... ver más

 
Hadi Helmi Md Zuraini,Waidah Ismail,Rimuljo Hendradi,Army Justitia     Pág. 46 - 54
Background: Heartbeat playing the main roles in our life. With the heartbeat, the anxiety level can be known. Most of the heartbeat is used in the exercise. Heart rate measurement is unique and uncontrollable by any human being.Objective: This research a... ver más

 
Su Luan Wong     Pág. pp. 186 - 194
Twenty-first century learners are media-centric and heavily reliant on technology. Internet-accessible resources are always at the students? finger-tips and they learn through such resources anywhere, anytime. Unfortunately, formal education in most part... ver más

 
Daniela Acquadro Maran and Tatiana Begotti    
Workplace violence (WV) is defined as an intentional misuse of power, including threats of physical force against another person or group, which can cause physical, mental, spiritual, moral or social harm. The aim of this study was to describe the preval... ver más
Revista: Applied Sciences

 
Isabel Cristina Scafuto,Priscila Rezende,Marcos Mazzieri     Pág. 137 - 143
International Journal of Innovation - IJI completes 7 yearsInternational Journal of Innovation - IJI has now 7 years old! In this editorial comment, we not only want to talk about our evolution but get even closer to the IJI community.  It is our fi... ver más