{"title":"面向智能建筑现场实时目标检测的YOLOv4模型推理加速研究","authors":"Jianchun Wang, Minjian Long, Yunfu Zhou, Congcong Guan","doi":"10.1117/12.2653817","DOIUrl":null,"url":null,"abstract":"In smart construction site, multi objects in real time monitoring streams are often needed to be detected at the same time. If YOLOv4 models are not accelerated, higher inference delay will be occurred, so that the purpose of real time detection can’t be achieved. The features of YOLOv4 model are firstly introduced in this paper, and then we discuss how to use YOLOv4-tiny-3l and TensorRT to accelerate the inference process of YOLOv4 model in detail. The experiments show that YOLOv4-tiny-3l models can be used to detection objects in multi real time streams smoothly, but the accuracy is pretty poor, so that the models can’t be used in practices. When adopting TensorRT toolkit to quantize YOLOv4 models with FP16 precision, the accelerated models can be used to detect objects in multi real time streams smoothly with a small loss of accuracy.","PeriodicalId":253792,"journal":{"name":"Conference on Optics and Communication Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Research on YOLOv4 model inference acceleration of real time object detection for smart construction site\",\"authors\":\"Jianchun Wang, Minjian Long, Yunfu Zhou, Congcong Guan\",\"doi\":\"10.1117/12.2653817\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In smart construction site, multi objects in real time monitoring streams are often needed to be detected at the same time. If YOLOv4 models are not accelerated, higher inference delay will be occurred, so that the purpose of real time detection can’t be achieved. The features of YOLOv4 model are firstly introduced in this paper, and then we discuss how to use YOLOv4-tiny-3l and TensorRT to accelerate the inference process of YOLOv4 model in detail. The experiments show that YOLOv4-tiny-3l models can be used to detection objects in multi real time streams smoothly, but the accuracy is pretty poor, so that the models can’t be used in practices. When adopting TensorRT toolkit to quantize YOLOv4 models with FP16 precision, the accelerated models can be used to detect objects in multi real time streams smoothly with a small loss of accuracy.\",\"PeriodicalId\":253792,\"journal\":{\"name\":\"Conference on Optics and Communication Technology\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-11-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Conference on Optics and Communication Technology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1117/12.2653817\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Conference on Optics and Communication Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1117/12.2653817","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Research on YOLOv4 model inference acceleration of real time object detection for smart construction site
In smart construction site, multi objects in real time monitoring streams are often needed to be detected at the same time. If YOLOv4 models are not accelerated, higher inference delay will be occurred, so that the purpose of real time detection can’t be achieved. The features of YOLOv4 model are firstly introduced in this paper, and then we discuss how to use YOLOv4-tiny-3l and TensorRT to accelerate the inference process of YOLOv4 model in detail. The experiments show that YOLOv4-tiny-3l models can be used to detection objects in multi real time streams smoothly, but the accuracy is pretty poor, so that the models can’t be used in practices. When adopting TensorRT toolkit to quantize YOLOv4 models with FP16 precision, the accelerated models can be used to detect objects in multi real time streams smoothly with a small loss of accuracy.