Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

热红外目标跟踪简介

less than 1 minute read

Published:

背景

热红外成像是一种被动式夜视技术,其通过接受物体的热辐射并将其转换成电信号而成像。热红外图像反映了物体表面的温度分布场。通常,波长为 3-8 um的中波红外与波长为 8-15 um 的长波红外被统称为热红外。近年来,随着非制冷型热红外成像技术的进步,热红外成像设备开始向小型化、高分辨率、平价化发展,越来越多的民用领域开始使用热红外成像设备。基于热红外图像的视觉智能处理技术,如目标识别、检测、跟踪等开始受到研究人员的关注。不同于可见光目标跟踪,热红外目标跟踪不受光照变化的影响。因此,其可被应用于夜间或是雨雾天气下的辅助驾驶,视频监控,海面救援等场景。 Read more

基于孪生卷积神经网络的目标跟踪方法介绍

less than 1 minute read

Published:

前言

Fully-Convolutional Siamese Networks for Object Tracking(Siamese-fc)这篇文章发表在ECCV 2016年的Workshop上, 但是文章在目标跟踪领域却产生了不小的影响。 Siamese-fc在当前大多数基于CNN的目标跟踪方法普遍较慢的情况下,实现了超实时的帧率,在处理3种尺度变换的情况下可以达到86 FPS。 跟踪的效果虽然比不上其它的state-of-the-art的方法,但也取得了较有潜力的结果,在OTB-2013上的AUC达到0.612。 Read more

视觉目标跟踪简介

less than 1 minute read

Published:

前言

视觉目标跟踪是计算机视觉中的一个重要研究方向,有着广泛的应用,如视频监控,人机交互, 无人驾驶等。过去二三十年视觉目标跟踪技术取得了长足的进步,特别是最近两年利用深度学习的目标跟踪方法取得了令人满意的效果,使目标跟踪技术获得了突破性的进展。本文旨在简要介绍目标跟踪的基本流程与框架,目标跟踪存在的挑战,目标跟踪相关方法,以及目标跟踪最新的进展等,希望通过这篇文章能让读者对视觉目标跟踪领域有一个较为全面的认识。 Read more

portfolio

publications

Multi-Task Driven Feature Models for Thermal Infrared Tracking

Published in Proceedings of the 34th AAAI Conference on Artifical Intelligence (AAAI2020), 2020

Existing deep Thermal InfraRed (TIR) trackers usually use the feature models of RGB trackers for representation. However, these feature models learned on RGB images are neither effective in representing TIR objects nor taking fine-grained TIR information into consideration. To this end, we develop a multi-task framework to learn the TIR-specific discriminative features and fine-grained correlation features for TIR object tracking. Read more

Download here

Learning Deep Multi-Level Similarity for Thermal Infrared Object Tracking

Published in IEEE Transactions on Multimedia, 2020

Existing deep Thermal InfraRed (TIR) trackers only use semantic features to represent the TIR object, which lack the sufficient discriminative capacity for handling distractors. This becomes worse when the feature extraction network is only trained on RGB images. To address this issue, we propose a multi-level similarity model under a Siamese framework for robust TIR object tracking. Read more

Download here

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post. Read more

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post. Read more