已入深夜,您辛苦了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!祝你早点完成任务,早点休息,好梦!

IM2HEIGHT: Height Estimation from Single Monocular Imagery via Fully Residual Convolutional-Deconvolutional Network.

计算机科学 人工智能 残余物 卷积神经网络 单眼 计算机视觉 模式识别(心理学) 深度学习
作者
Lichao Mou,Xiao Xiang Zhu
出处
期刊:arXiv: Computer Vision and Pattern Recognition 被引量:41
摘要

In this paper we tackle a very novel problem, namely height estimation from a single monocular remote sensing image, which is inherently ambiguous, and a technically ill-posed problem, with a large source of uncertainty coming from the overall scale. We propose a fully convolutional-deconvolutional network architecture being trained end-to-end, encompassing residual learning, to model the ambiguous mapping between monocular remote sensing images and height maps. Specifically, it is composed of two parts, i.e., convolutional sub-network and deconvolutional sub-network. The former corresponds to feature extractor that transforms the input remote sensing image to high-level multidimensional feature representation, whereas the latter plays the role of a height generator that produces height map from the feature extracted from the convolutional sub-network. Moreover, to preserve fine edge details of estimated height maps, we introduce a skip connection to the network, which is able to shuttle low-level visual information, e.g., object boundaries and edges, directly across the network. To demonstrate the usefulness of single-view height prediction, we show a practical example of instance segmentation of buildings using estimated height map. This paper, for the first time in the remote sensing community, attempts to estimate height from monocular vision. The proposed network is validated using a large-scale high resolution aerial image data set covered an area of Berlin. Both visual and quantitative analysis of the experimental results demonstrate the effectiveness of our approach.

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
bkagyin应助hhllhh采纳,获得10
6秒前
顾矜应助魁梧的人达采纳,获得10
7秒前
Ava应助mw采纳,获得10
9秒前
10秒前
11秒前
所所应助zephyr采纳,获得30
12秒前
负责怀莲发布了新的文献求助10
13秒前
13秒前
儒雅南风发布了新的文献求助10
14秒前
14秒前
14秒前
16秒前
hhllhh发布了新的文献求助10
17秒前
17秒前
18秒前
19秒前
奥特超曼应助123采纳,获得10
19秒前
21秒前
Iris发布了新的文献求助10
21秒前
漂亮白枫发布了新的文献求助10
22秒前
trf完成签到,获得积分10
24秒前
李健应助负责怀莲采纳,获得10
24秒前
思源应助无情的宛儿采纳,获得10
26秒前
28秒前
34秒前
yuan关注了科研通微信公众号
35秒前
隐形曼青应助hhllhh采纳,获得10
38秒前
所所应助Ray采纳,获得10
40秒前
PMoLGGYM2021发布了新的文献求助10
41秒前
调皮醉波完成签到 ,获得积分10
45秒前
章鱼哥想毕业完成签到 ,获得积分10
46秒前
月儿完成签到 ,获得积分10
48秒前
Karen331完成签到,获得积分10
48秒前
butaishao完成签到,获得积分10
49秒前
看不了一点文献应助lzm采纳,获得20
49秒前
橙子应助科研通管家采纳,获得10
50秒前
深情安青应助科研通管家采纳,获得10
50秒前
研友_VZG7GZ应助科研通管家采纳,获得10
50秒前
50秒前
情怀应助科研通管家采纳,获得10
50秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
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 350
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 3989868
求助须知:如何正确求助?哪些是违规求助? 3531994
关于积分的说明 11255752
捐赠科研通 3270793
什么是DOI,文献DOI怎么找? 1805053
邀请新用户注册赠送积分活动 882215
科研通“疑难数据库(出版商)”最低求助积分说明 809208