ENHANCED CROWD EMOTION DETECTION IN OCCLUDED ENVIRONMENTS USING YOLOV5 AND CONVOLUTIONAL NEURAL NETWORKS

Abstract

A deep learning methodology examines facial emotional identification when faces exist in partially obstructed conditions of crowds. YOLOv5-tiny functions for face detection while RepVGG handles emotion classification within this method. Training of the emotion recognition model employed FER-2013 dataset but detection enhancements came from processing WIDER FACE dataset. Experimental testing shows that YOLOv5 reaches a 91% detection success rate while RepVGG delivers an 87.5% accuracy level in emotion classification above standard CNN architectures such as ResNet and Efficient Net. The system detects emotions directly in real-time streaming video data which qualifies it for application in crowd monitoring and surveillance and behavioral analysis solutions. Future research initiatives aim to develop better methods for handling obscuration along with methods to optimize speed when applying the system to large-scale deployments.