A Database and Evaluation Methodology for Optical Flow

光流 计算机科学 插值(计算机图形学) 基本事实 人工智能 不连续性分类 计算机视觉 算法 帧(网络) 运动(物理) 集合(抽象数据类型) 跟踪(教育) 图像(数学) 数学 教育学 心理学 数学分析 程序设计语言 电信
作者
Simon Baker,Daniel Scharstein,J. P. Lewis,Stefan Roth,Michael J. Black,Richard Szeliski
出处
期刊:International Journal of Computer Vision [Springer Science+Business Media]
卷期号:92 (1): 1-31 被引量:1791
标识
DOI:10.1007/s11263-010-0390-2
摘要

The quantitative evaluation of optical flow algorithms by Barron et al. (1994) led to significant advances in performance. The challenges for optical flow algorithms today go beyond the datasets and evaluation methods proposed in that paper. Instead, they center on problems associated with complex natural scenes, including nonrigid motion, real sensor noise, and motion discontinuities. We propose a new set of benchmarks and evaluation methods for the next generation of optical flow algorithms. To that end, we contribute four types of data to test different aspects of optical flow algorithms: (1) sequences with nonrigid motion where the ground-truth flow is determined by tracking hidden fluorescent texture, (2) realistic synthetic sequences, (3) high frame-rate video used to study interpolation error, and (4) modified stereo sequences of static scenes. In addition to the average angular error used by Barron et al., we compute the absolute flow endpoint error, measures for frame interpolation error, improved statistics, and results at motion discontinuities and in textureless regions. In October 2007, we published the performance of several well-known methods on a preliminary version of our data to establish the current state of the art. We also made the data freely available on the web at http://vision.middlebury.edu/flow/ . Subsequently a number of researchers have uploaded their results to our website and published papers using the data. A significant improvement in performance has already been achieved. In this paper we analyze the results obtained to date and draw a large number of conclusions from them.
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
研友_VZG7GZ应助hhh采纳,获得10
1秒前
1秒前
量子星尘发布了新的文献求助30
1秒前
陈少华完成签到 ,获得积分10
1秒前
美女完成签到,获得积分10
1秒前
怕孤独的如凡完成签到 ,获得积分10
1秒前
3秒前
单纯血茗发布了新的文献求助10
3秒前
芜湖完成签到,获得积分10
4秒前
心心完成签到,获得积分10
4秒前
搜集达人应助云轩采纳,获得10
4秒前
jinx123456完成签到,获得积分10
6秒前
单纯冰棍完成签到,获得积分20
6秒前
金海完成签到,获得积分10
6秒前
liqian发布了新的文献求助10
6秒前
6秒前
XIEMIN完成签到,获得积分10
7秒前
贺贺完成签到 ,获得积分20
8秒前
8秒前
悦耳荟完成签到,获得积分10
8秒前
9秒前
9秒前
joejo1124完成签到 ,获得积分10
10秒前
sl发布了新的文献求助10
11秒前
hhh发布了新的文献求助10
11秒前
爱吃藕粉凉羹的奶油完成签到,获得积分20
12秒前
动听煎饼完成签到 ,获得积分10
13秒前
明理冬瓜完成签到,获得积分10
13秒前
bkagyin应助cldg采纳,获得10
13秒前
小马甲应助不站在雾里采纳,获得10
13秒前
pp完成签到 ,获得积分0
14秒前
zhangjianzeng完成签到 ,获得积分10
14秒前
史小菜应助云轩采纳,获得20
15秒前
伏伏雅逸发布了新的文献求助10
15秒前
李健应助荒野风采纳,获得10
16秒前
Popeye应助单纯血茗采纳,获得10
16秒前
淡然冬灵发布了新的文献求助10
16秒前
Popeye应助单纯血茗采纳,获得10
16秒前
荔枝的油饼iKun完成签到,获得积分10
17秒前
Bosen完成签到,获得积分10
17秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
Research on Disturbance Rejection Control Algorithm for Aerial Operation Robots 500
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 4038446
求助须知:如何正确求助?哪些是违规求助? 3576149
关于积分的说明 11374627
捐赠科研通 3305875
什么是DOI,文献DOI怎么找? 1819354
邀请新用户注册赠送积分活动 892680
科研通“疑难数据库(出版商)”最低求助积分说明 815048