.png){kind=icon}
.png){kind=icon}
Return
Classroom Behavior Detection Method Based on PLA-YOLO11n
.png){kind=icon}
OA
AI
DOI：10.3390/s25175386.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Accurate detection of student behavior in the classroom helps analyze students’ learning states and contributes to improving teaching effectiveness. We propose the PLA-YOLO11n classroom behavior detection model. We design a novel C3K2_PConv module that integrates partial convolution with modules from the YOLO11 network and apply it to the backbone and neck feature fusion layers. To enhance small-target feature representation, we incorporate a large-kernel self-attention (LSKA) mechanism and replace the SPPF at the end of the backbone with the attention feature integration module (AIFI). We also add a high-resolution detection head. Experimental results on the SCB2 dataset demonstrate that the improved model outperforms the original YOLO11, achieving an increase of 3.8% in mean average precision (mAP@0.5).
Keywords:
classroom behavior detection
PLA-YOLO11n
C3K2_PConv module
large-kernel self-attention
small-target detection