返回
Tracking more than 100 arbitrary objects at 25 FPS through deep learning
DOI:10.1016/j.patcog.2021.108205.png)
摘要
En 中文
Most video analytics applications rely on object detectors to localize objects in frames. However, when real-time is a requirement, running the detector at all the frames is usually not possible. This is somewhat circumvented by instantiating visual object trackers between detector calls, but this does not scale with the number of objects. To tackle this problem, we present SiamMT, a new deep learning multiple visual object tracking solution that applies single-object tracking principles to multiple arbitrary objects in real -time. To achieve this, SiamMT reuses feature computations, implements a novel crop-and-resize operator, and defines a new and efficient pairwise similarity operator. SiamMT naturally scales up to several dozens of targets, reaching 25 fps with 122 simultaneous objects for VGA videos, or up to 100 simultaneous objects in HD720 video. SiamMT has been validated on five large real-time benchmarks, achieving leading performance against current state-of-the-art trackers. (c) 2021 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license ( http://creativecommons.org/licenses/by-nc-nd/4.0/ )
Keyword:
Multiple visual object tracking
Motion estimation
Deep learning
Siamese networks
AI总结
对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Generation of hydroxyl radicals by urban suspended particulate air matter. The role of iron ions城市悬浮颗粒物产生羟基自由基。铁离子的作用:
Distractor-aware discrimination learning for online multiple object tracking基于分心感知的在线多目标跟踪判别学习
PATTERN RECOGNITION
IF7.6
No Blind Spots: Full-Surround Multi-Object Tracking for Autonomous Vehicles Using Cameras and LiDARs

