Yoshikazu Watanabe, Yuki Kobayashi, N. Nakajima, Takashi Takenaka, Hiroyoshi Miyano
{"title":"Work-in-Progress: Object Detection Acceleration Method by Improving Execution Efficiency of AI Device","authors":"Yoshikazu Watanabe, Yuki Kobayashi, N. Nakajima, Takashi Takenaka, Hiroyoshi Miyano","doi":"10.1109/CASES55004.2022.00014","DOIUrl":null,"url":null,"abstract":"In recent years, there has been a growing need to perform object detection at the edge. Since the edge environment has tight physical constraints, the efficient use of AI devices is a key challenge to execute object detection at high throughput. In this paper, we propose an object detection acceleration method which uses two types of one-stage detectors in combination. After detecting object candidates by a lightweight detector, the method generates aggregated images by combining the candidate images and executes the second more accurate detector on the aggregated images to improve execution efficiency of AI devices. Our evaluations confirmed that the proposed method can speed up object detection by up to eight times for a license plate detection task with almost no accuracy degradation. We conducted evaluations with a car detection task and a pose estimation task as well and confirmed the broad applicability of the proposed method.","PeriodicalId":331181,"journal":{"name":"2022 International Conference on Compilers, Architecture, and Synthesis for Embedded Systems (CASES)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 International Conference on Compilers, Architecture, and Synthesis for Embedded Systems (CASES)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CASES55004.2022.00014","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
In recent years, there has been a growing need to perform object detection at the edge. Since the edge environment has tight physical constraints, the efficient use of AI devices is a key challenge to execute object detection at high throughput. In this paper, we propose an object detection acceleration method which uses two types of one-stage detectors in combination. After detecting object candidates by a lightweight detector, the method generates aggregated images by combining the candidate images and executes the second more accurate detector on the aggregated images to improve execution efficiency of AI devices. Our evaluations confirmed that the proposed method can speed up object detection by up to eight times for a license plate detection task with almost no accuracy degradation. We conducted evaluations with a car detection task and a pose estimation task as well and confirmed the broad applicability of the proposed method.