最小边界框
行人检测
计算机科学
行人
目标检测
跳跃式监视
人工智能
特征提取
转化(遗传学)
功能(生物学)
计算机视觉
比例(比率)
模式识别(心理学)
特征(语言学)
图像(数学)
工程类
生物化学
化学
物理
语言学
哲学
量子力学
进化生物学
生物
运输工程
基因
作者
Q. Zhang,Fen Yang,Qikai Zhou,Wei Zhang,Ruizhi Li
摘要
Aiming at the problem of pedestrian targets occlusion and multi-scale error and missed detection in pedestrian detection, a lightweight pedestrian detection algorithm based on improved EA-YOLOv5n is proposed. This method introduces the ECA attention module into the backbone feature extraction network, and learns the channels of pedestrian images by learning Information, improve the accuracy of pedestrian object detection in the case of occlusion, improve the calculation method of Bounding box loss function for the disadvantages of loss function calculation, adopt EIoU Loss and introduce power transformation to obtain higher bounding box regression accuracy. The experimental results show that using the improved model to conduct experiments on the Widerperson dataset reaches 69.6% mAP, which is 2.0% higher than the original algorithm, and the detection speed reaches 65FPS.
科研通智能强力驱动
Strongly Powered by AbleSci AI