Hybrid CNN-Transformer Features for Visual Place Recognition

计算机科学 人工智能 地点 卷积神经网络 MNIST数据库 模式识别(心理学) 变压器 编码器 特征学习 计算机视觉 深度学习 量子力学 操作系统 物理 哲学 语言学 电压
作者
Yuwei Wang,Yuanying Qiu,Peitao Cheng,Junyu Zhang
出处
期刊:IEEE Transactions on Circuits and Systems for Video Technology [Institute of Electrical and Electronics Engineers]
卷期号:33 (3): 1109-1122 被引量:14
标识
DOI:10.1109/tcsvt.2022.3212434
摘要

Visual place recognition is a challenging problem in robotics and autonomous systems because the scene undergoes appearance and viewpoint changes in a changing world. Existing state-of-the-art methods heavily rely on CNN-based architectures. However, CNN cannot effectively model image spatial structure information due to the inherent locality. To address this issue, this paper proposes a novel Transformer-based place recognition method to combine local details, spatial context, and semantic information for image feature embedding. Firstly, to overcome the inherent locality of the convolutional neural network (CNN), a hybrid CNN-Transformer feature extraction network is introduced. The network utilizes the feature pyramid based on CNN to obtain the detailed visual understanding, while using the vision Transformer to model image contextual information and aggregate task-related features dynamically. Specifically, the multi-level output tokens from the Transformer are fed into a single Transformer encoder block to fuse multi-scale spatial information. Secondly, to acquire the multi-scale semantic information, a global semantic NetVLAD aggregation strategy is constructed. This strategy employs semantic enhanced NetVLAD, imposing prior knowledge on the terms of the Vector of Locally Aggregated Descriptors (VLAD), to aggregate multi-level token maps, and further concatenates the multi-level semantic features globally. Finally, to alleviate the disadvantage that the fixed margin of triplet loss leads to the suboptimal convergence, an adaptive triplet loss with dynamic margin is proposed. Extensive experiments on public datasets show that the learned features are robust to appearance and viewpoint changes and achieve promising performance compared to state-of-the-arts.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
HAG关闭了HAG文献求助
1秒前
老虎皮完成签到,获得积分10
1秒前
zhangyu应助fanglin123采纳,获得20
2秒前
2秒前
2秒前
大模型应助zwj采纳,获得10
3秒前
生动路人应助不动脑筋采纳,获得10
4秒前
4秒前
5秒前
LZAAA完成签到,获得积分10
5秒前
6秒前
11发布了新的文献求助10
7秒前
7秒前
hhhblabla应助欣喜的成败采纳,获得20
7秒前
大方谷梦完成签到 ,获得积分10
8秒前
Listen发布了新的文献求助10
8秒前
神兽下山发布了新的文献求助10
10秒前
九龙飞翔完成签到,获得积分10
10秒前
cxy完成签到,获得积分10
12秒前
Bryan应助旋律采纳,获得10
12秒前
12秒前
微笑发布了新的文献求助10
13秒前
13秒前
JeromineJade发布了新的文献求助10
13秒前
wzx发布了新的文献求助10
14秒前
HarryChan应助蝈蝈采纳,获得10
14秒前
材1完成签到 ,获得积分10
17秒前
所所应助思维隋采纳,获得10
18秒前
阿弥陀佛完成签到,获得积分10
18秒前
默默发布了新的文献求助20
19秒前
MchemG应助LWJ采纳,获得10
19秒前
神兽下山完成签到,获得积分10
19秒前
20秒前
21秒前
annzl发布了新的文献求助10
26秒前
NexusExplorer应助王大炮采纳,获得10
26秒前
Hello应助王大炮采纳,获得10
27秒前
HAG发布了新的文献求助30
27秒前
脑洞疼应助bangbangsh采纳,获得10
28秒前
28秒前
高分求助中
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
A new approach to the extrapolation of accelerated life test data 1000
Indomethacinのヒトにおける経皮吸収 400
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 370
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
Aktuelle Entwicklungen in der linguistischen Forschung 300
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3993004
求助须知:如何正确求助?哪些是违规求助? 3533801
关于积分的说明 11263775
捐赠科研通 3273597
什么是DOI,文献DOI怎么找? 1806113
邀请新用户注册赠送积分活动 882955
科研通“疑难数据库(出版商)”最低求助积分说明 809629