Seong-Bin Choi, Sang-Seol Lee, Jonghee Park, Sung-Joon Jang, Byung-Ho Choi
{"title":"高效的最终输出特征图处理方法，支持实时目标检测和识别","authors":"Seong-Bin Choi, Sang-Seol Lee, Jonghee Park, Sung-Joon Jang, Byung-Ho Choi","doi":"10.1109/ISOCC50952.2020.9333051","DOIUrl":null,"url":null,"abstract":"Recent advanced in CNN acceleration systems using hardware and software co-design for real-time object detection and recognition, the speedup of post processing can reduce the burden of designing the acceleration logic to meet the real-time goal. In this paper, we propose an optimization method that eliminates the operation of acquiring redundant bounding boxes without degrading performance. It is implemented on a Xilinx Zynq Ultrascale+ MPSoC ZCU106 and shows the performance improvement about 20% that of the conventional method.","PeriodicalId":270577,"journal":{"name":"2020 International SoC Design Conference (ISOCC)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Efficient final output feature map processing method supporting real-time object detection and recognition\",\"authors\":\"Seong-Bin Choi, Sang-Seol Lee, Jonghee Park, Sung-Joon Jang, Byung-Ho Choi\",\"doi\":\"10.1109/ISOCC50952.2020.9333051\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Recent advanced in CNN acceleration systems using hardware and software co-design for real-time object detection and recognition, the speedup of post processing can reduce the burden of designing the acceleration logic to meet the real-time goal. In this paper, we propose an optimization method that eliminates the operation of acquiring redundant bounding boxes without degrading performance. It is implemented on a Xilinx Zynq Ultrascale+ MPSoC ZCU106 and shows the performance improvement about 20% that of the conventional method.\",\"PeriodicalId\":270577,\"journal\":{\"name\":\"2020 International SoC Design Conference (ISOCC)\",\"volume\":\"15 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-10-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 International SoC Design Conference (ISOCC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ISOCC50952.2020.9333051\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 International SoC Design Conference (ISOCC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISOCC50952.2020.9333051","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Efficient final output feature map processing method supporting real-time object detection and recognition
Recent advanced in CNN acceleration systems using hardware and software co-design for real-time object detection and recognition, the speedup of post processing can reduce the burden of designing the acceleration logic to meet the real-time goal. In this paper, we propose an optimization method that eliminates the operation of acquiring redundant bounding boxes without degrading performance. It is implemented on a Xilinx Zynq Ultrascale+ MPSoC ZCU106 and shows the performance improvement about 20% that of the conventional method.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
