摘要
目标检测是指对图像或视频进行特征提取与分析,确定目标在图像中的位置信息,并能准确进行分类的一类算法。提出的Mobile U-Net是一种新型的无锚点的多目标检测算法,将语义分割问题转换成目标检测问题,并在分割网络U-Net网络的基础上,结合MobileNetV2,既保证了精度,又在满足了实时性。实采的视频数据上测试显示,在CPU i5-82501.8GHz硬件平台上的平均速度能达到17.38fps。
Object detection is an algorithm that extracts and analyzes the features of an image or video,determines the position information of the target in the image,and can accurately classify the target.The Mobile U-Net proposed in this paper is a new type of multi-target detection algorithm without anchor point,which transforms semantic segmentation problem into object detection problem.Based on U-Net network and MobileNetV2,it not only ensures the accuracy,but also meets the real-time requirement.Tested on live video data,the average speed on CPU i5-82501.8GHz hardware platforms is 17.38fps.
出处
《工业控制计算机》
2020年第3期81-83,共3页
Industrial Control Computer
