关于scene understanding场景理解概念的理解
Scene understanding 場(chǎng)景理解感覺(jué)定義并不是十分明確,找了幾個(gè)供參考。
LSUN Challenge 大規(guī)模場(chǎng)景理解比賽
INTRODUCTION
The PASCAL VOC and ImageNet ILSVRC challenges have enabled significant progress for object recognition in the past decade. Beginning with CVPR 2015, we borrowed this mechanism to speed up the progress for scene understanding via the LSUN workshop. Complementary to the object-centric ImageNet ILSVRC Challenge hosted at ICCV/ECCV every year, we propose to continue hosting this scene-centric challenge at CVPR every year. Our challenge will focus on major tasks in scene understanding, including scene object retrieval, outdoor scene segmentation, RGB-D 3D object detection and saliency prediction. Inspired by recent successes using big data, such as deep learning, we focus on providing benchmarks that are significantly bigger and more diverse than the existing ones, to support training these data-hungry algorithms. By providing a set of large-scale benchmarks in an annual challenge format, we expect significant progress to continue for scene understanding in the coming years. Given the experience of our previous workshops, we are updating all of our existing tasks and rolling out new tasks.
鏈接 http://lsun.cs.princeton.edu/2017/
從這個(gè)比賽的介紹可以看出,場(chǎng)景理解主要關(guān)注的任務(wù)有
- scene object retrieval 場(chǎng)景目標(biāo)檢索
- outdoor scene segmentation 室外場(chǎng)景分割
- RGB-D 3D object detection RGB-D 3D 目標(biāo)檢測(cè)
- saliency prediction 顯著性預(yù)測(cè)
綜述Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art
論文鏈接 https://arxiv.org/pdf/1704.05519.pdf
在這篇綜述的第10章中,對(duì)于場(chǎng)景理解是這樣描述的
One of the basic requirements of autonomous driving is to fully understand its surrounding area such as a complex traffic scene. The complex task of outdoor scene understanding involves several sub-tasks such as depth estimation, scene categorization, object detection and tracking, event categorization, and more. Each of these tasks describe particular aspect of a scene. It is beneficial to model some of these aspects jointly to exploit the relations between different elements of the scene and obtain a holistic understanding. The goal of most scene understanding
models is to obtain a rich but compact representation of the scene including all its elements e.g., layout elements, traffic participants and the relations with respect to each other. Compared to reasoning in the 2D image domain, 3D reasoning plays a significant role in solving geometric scene understanding problems and results in a more informative representation of the scene in the form of 3D object models, layout elements and occlusion relationships. One specific challenge in scene understanding is the interpretation of urban and sub-urban traffic scenarios. Compared to highways and rural roads, urban scenarios comprise many independently moving traffic participants, more variability in the geometric layout of roads and crossroads, and an increased level of difficulty due to ambiguous visual features and illumination changes.
可以看出,在這里,戶(hù)外場(chǎng)景理解(面向自動(dòng)駕駛領(lǐng)域的)包括幾個(gè)子任務(wù):
- 深度估計(jì)
- 場(chǎng)景分類(lèi)
- 目標(biāo)檢測(cè)和跟蹤
- 事件分類(lèi)
MIT 自動(dòng)駕駛公開(kāi)課
里面第三次課提到了,場(chǎng)景理解是自動(dòng)駕駛需要解決的幾大任務(wù)(定位與建圖,場(chǎng)景理解,運(yùn)動(dòng)規(guī)劃,駕駛員狀態(tài))之一。
可以直觀理解成為Where is someone else?
其中提到的例子主要有
- 關(guān)于目標(biāo)檢測(cè)的
- 關(guān)于駕駛?cè)珗?chǎng)景分割的,比如說(shuō)SegNet
- 從音頻數(shù)據(jù)得到路況信息,分析路面紋理特征等
Lecun的一個(gè)ppt
看到lecun關(guān)于深度學(xué)習(xí)和場(chǎng)景理解的一個(gè)ppt
里面大概是這樣理解場(chǎng)景理解
- 目標(biāo)檢測(cè)
- 語(yǔ)義分割
- 場(chǎng)景解析和標(biāo)注 Scene Parsing and Labelling
國(guó)內(nèi)論文
自動(dòng)化學(xué)報(bào)上的
目前視覺(jué)場(chǎng)景理解還沒(méi)有嚴(yán)格統(tǒng)一的定義.參考麻省理工、卡耐基梅隆、斯坦福等大學(xué)的國(guó)際著名科研團(tuán)隊(duì)的研究工作[2?4],視覺(jué)場(chǎng)景理解可表述為在環(huán)境數(shù)據(jù)感知的基礎(chǔ)上,結(jié)合視覺(jué)分析與圖像處理識(shí)別等技術(shù)手段,從計(jì)算統(tǒng)計(jì)、行為認(rèn)知以及語(yǔ)義等不同角度挖掘視覺(jué)數(shù)據(jù)中的特征與模式,從而實(shí)現(xiàn)場(chǎng)景有效分析、認(rèn)知與表達(dá).近年來(lái)結(jié)合數(shù)據(jù)學(xué)習(xí)與挖掘、生物認(rèn)知特征和統(tǒng)計(jì)建模方法構(gòu)建的視覺(jué)場(chǎng)景認(rèn)知理解系統(tǒng)。
讀都沒(méi)讀順……
總結(jié)
以上是生活随笔為你收集整理的关于scene understanding场景理解概念的理解的全部?jī)?nèi)容,希望文章能夠幫你解決所遇到的問(wèn)題。
- 上一篇: 虚拟机教程(一) 启用win10自带虚拟
- 下一篇: 销售和程序员哪个好_适合服装店的服装销售