跳到主要导航 跳到搜索 跳到主要内容

SlimYOLOv3: Narrower, faster and better for real-time UAV applications

  • Pengyi Zhang
  • , Yunxin Zhong
  • , Xiaoqiong Li*
  • *此作品的通讯作者
  • Beijing Institute of Technology

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

Drones or general Unmanned Aerial Vehicles (UAVs), endowed with computer vision function by on-board cameras and embedded systems, have become popular in a wide range of applications. However, real-time scene parsing through object detection running on a UAV platform is very challenging, due to limited memory and computing power of embedded devices. To deal with these challenges, in this paper we propose to learn efficient deep object detectors through channel pruning of convolutional layers. To this end, we enforce channel-level sparsity of convolutional layers by imposing L1 regularization on channel scaling factors and prune less informative feature channels to obtain 'slim' object detectors. Based on such approach, we present SlimYOLOv3 with fewer trainable parameters and floating point operations (FLOPs) in comparison of original YOLOv3 as a promising solution for real-time object detection on UAVs. We evaluate SlimYOLOv3 on VisDrone2018-Det benchmark dataset; compelling results are achieved by SlimYOLOv3 in comparison of unpruned counterpart, including ~90.8% decrease of FLOPs, ~92.0% decline of parameter size, running ~2 times faster and comparable detection accuracy as YOLOv3. Experimental results with different pruning ratios consistently verify that proposed SlimYOLOv3 with narrower structure are more efficient, faster and better than YOLOv3, and thus are more suitable for real-time object detection on UAVs. Our codes are made publicly available at https://github.com/PengyiZhang/SlimYOLOv3.

源语言英语
主期刊名Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019
出版商Institute of Electrical and Electronics Engineers Inc.
页37-45
页数9
ISBN(电子版)9781728150239
DOI
出版状态已出版 - 10月 2019
活动17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019 - Seoul, 韩国
期限: 27 10月 2019 → 28 10月 2019

丛书

姓名Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019

会议

会议17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019
国家/地区韩国
市Seoul
时期27/10/19 → 28/10/19

学术指纹

探究 'SlimYOLOv3: Narrower, faster and better for real-time UAV applications' 的科研主题。它们共同构成独一无二的学术指纹。

引用此