Computer Engineering and Applications ›› 2022, Vol. 58 ›› Issue (24): 12-28.DOI: 10.3778/j.issn.1002-8331.2206-0139

• Research Hotspots and Reviews • Previous Articles     Next Articles

Object Detection Optimization Research for Mobile Terminals

HAN Jingjing, LIU Jiangyue, GONG Weijun, WEI Hongyang, QIAN Yurong   

  1. 1.Key Laboratory of Signal Detection and Processing, Xinjiang University, Urumqi 830046, China
    2.School of Software, Xinjiang University, Urumqi 830091, China
    3.School of Information Science and Engineering, Xinjiang University, Urumqi 830046, China
    4.Training Center, Urumqi Vocational University, Urumqi 830004, China
    5.Key Laboratory of Software Engineering, Xinjiang University, Urumqi 830000, China
  • Online:2022-12-15 Published:2022-12-15

面向移动端的目标检测优化研究

韩晶晶,刘江越,公维军,魏宏杨,钱育蓉   

  1. 1.新疆大学 信号检测与处理重点实验室,乌鲁木齐 830046
    2.新疆大学 软件学院,乌鲁木齐 830091
    3.新疆大学 信息科学与工程学院,乌鲁木齐 830046
    4.乌鲁木齐职业大学 实训中心,乌鲁木齐 830004
    5.新疆大学 软件工程重点实验室,乌鲁木齐 830000

Abstract: In order to meet the demand for real-time object detection in the era of mobile intelligence, numerous solutions have been proposed for object detection optimization for mobile terminals. Optimization ideas can be classified into two categories:one is based on manual or AutoML methods, using a lightweight convolution design to build a lightweight network at the beginning of network design;the other is to use tensor decomposition, model pruning, parameter quantization or other compression methods to adjust the existing object detection model to optimize the detection performance. Then, considering that the development laws of optimization methods are different and related, different analysis angles and comparison dimensions are adopted respectively. Finally, the current situation of the mobile-oriented object detection industrial in China is analyzed from the perspective of market, and the potential problems and development directions of optimization research are discussed.

Key words: object detection, lightweight network, tensor decomposition, model pruning, parameter quantization

摘要: 为适应移动智能时代对实时目标检测的需求,人们针对面向移动端的目标检测优化问题提出了众多解决思路。其优化思路可归纳为轻量化网络设计和模型压缩两类:一类是基于手工设计或自动化机器学习(AutoML)手段,在网络设计之初就采用轻量化卷积设计构建轻量化网络;另一类是借助张量分解、模型剪枝、参数量化等压缩手段,调整现有的目标检测模型来优化检测性能。考虑到优化方法的发展规律不尽相同且彼此之间有所关联,分别采取了不同的分析角度和对比维度。从市场角度剖析了国内面向移动端的目标检测产业化现状,并对其优化研究的潜在问题和发展方向进行了总结与展望。

关键词: 目标检测, 轻量化网络, 张量分解, 模型剪枝, 参数量化