Scene understanding 場景理解感覺定義并不是十分明確，找了幾個供參考。

LSUN Challenge 大規模場景理解比賽

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/
從這個比賽的介紹可以看出，場景理解主要關注的任務有

• scene object retrieval 場景目標檢索
• outdoor scene segmentation 室外場景分割
• RGB-D 3D object detection RGB-D 3D 目標檢測
• saliency prediction 顯著性預測

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，對于場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，戶外場景理解（面向自動駕駛領域的）包括幾個子任務：

• 深度估計
• 場景分類
• 目標檢測和跟蹤
• 事件分類

MIT 自動駕駛公開課

里面第三次課提到了，場景理解是自動駕駛需要解決的幾大任務（定位與建圖，場景理解，運動規劃，駕駛員狀態）之一。
可以直觀理解成為Where is someone else?
其中提到的例子主要有
- 關于目標檢測的
- 關于駕駛全場景分割的，比如說SegNet
- 從音頻數據得到路況信息，分析路面紋理特征等

Lecun的一個ppt

看到lecun關于深度學習和場景理解的一個ppt
里面大概是這樣理解場景理解

• 目標檢測
• 語義分割
• 場景解析和標注 Scene Parsing and Labelling

國內論文

自動化學報上的
目前視覺場景理解還沒有嚴格統一的定義.參考麻省理工、卡耐基梅隆、斯坦福等大學的國際著名科研團隊的研究工作[2?4],視覺場景理解可表述為在環境數據感知的基礎上,結合視覺分析與圖像處理識別等技術手段,從計算統計、行為認知以及語義等不同角度挖掘視覺數據中的特征與模式,從而實現場景有效分析、認知與表達.近年來結合數據學習與挖掘、生物認知特征和統計建模方法構建的視覺場景認知理解系統。

讀都沒讀順……

總結

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內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。