Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top
Published in:
Design of a Simulation System for Cross-Eye Dynamic Jamming Read chapter Read first chapter

2018 | OriginalPaper | Chapter

Scene Parsing with Deep Features and Per-Exemplar Detectors

Authors : Xiaofei Cui, Hanbing Qu, Xi Chen, Ziliang Qi, Liang Dong

Published in: Proceedings of 2017 Chinese Intelligent Automation Conference

Publisher: Springer Singapore

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Scene parsing is the task of labeling every pixel in an image with its semantic category. This paper presents an approach that combines the convolution neural network with per-exemplar detectors for scene parsing. We use a convolution neural network to learn the image global features. Compared to most standard feature extraction approaches, the convolution neural network features can describe images better. Our system has the following steps. First, we use the global features to find the retrieval set which is similar to query images from training dataset. Then, we use local features to compute the likelihood scores of superpixels in the query image, which combined the per-exemplar detectors and Support Vector Machine (SVM) for classification. Finally, our system integrates multiple cues into a Markov Random Field (MRF) framework. We evaluate our system on two challenging datasets. The experimental results show that our method can achieve good performance.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

inform now
previous chapter Feature-Based Monocular Real-Time Localization for UAVs in Indoor Environment
next chapter Design of a Temperature and Humidity Monitoring System for Plant Growth Cabinets Based on Data Fusion
Literature
1.
Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110CrossRef
2.
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: 2005 IEEE computer society conference on computer vision and pattern recognition. CVPR 2005, vol 1. IEEE, pp 886–893
3.
Oliva A, Torralba A (2001) Modeling the shape of the scene: a holistic representation of the spatial envelope. Int J Comput Vis 42(3):145–175CrossRefMATH
4.
Bay H, Ess A, Tuytelaars T, Van Gool L (2008) Speeded-up robust features (SURF). Comput Vis Image Underst 110(3):346–359CrossRef
5.
Farabet C, Couprie C, Najman L, LeCun Y (2012) Scene parsing with multiscale feature learning, purity trees, and optimal covers. arXiv preprint arXiv:​1202.​2160
6.
Bu S, Han P, Liu Z, Han J (2016) Scene parsing using inference embedded deep networks. Pattern Recogn 59:188–198CrossRef
7.
Pinheiro P, Collobert R (2014) Recurrent convolutional neural networks for scene labeling. In: International conference on machine learning, pp 82–90
8.
9.
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105
10.
Liu C, Yuen J, Torralba A (2009) Nonparametric scene parsing: label transfer via dense scene alignment. In: 2009 IEEE conference on computer vision and pattern recognition. CVPR 2009. IEEE, pp 1972–1979
11.
Tighe J, Lazebnik S (2010) Superparsing: scalable nonparametric image parsing with superpixels. Comput Vis ECCV 352–365
12.
Eigen D, Fergus R (2012) Nonparametric image parsing using adaptive neighbor sets. In: 2012 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 2799–2806
13.
Tighe J, Lazebnik S (2013) Finding things: image parsing with regions and per-exemplar detectors. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3001–3008
14.
Yang J, Price B, Cohen S, Yang MH (2014) Context driven scene parsing with attention to rare classes. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3294–3301
15.
Malisiewicz T, Gupta A, Efros AA (2011) Ensemble of exemplar-svms for object detection and beyond. In: 2011 IEEE international conference on computer vision (ICCV). IEEE, pp 89–96
16.
17.
Liu X, Zhao Y, Zhu SC (2017) Single-view 3D scene reconstruction and parsing by attribute grammar. IEEE Trans Pattern Anal Mach Intell (99):1–1
18.
Singh G, Kosecka J (2013) Nonparametric scene parsing with adaptive feature relevance and semantic context. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3151–3157
19.
George M (2015) Image parsing with a wide range of classes and scene-level context. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3622–3630
20.
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D et al. (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1–9)
21.
Felzenszwalb PF, Huttenlocher DP (2004) Efficient graph-based image segmentation. Int J Comput Vis 59(2):167–181CrossRef
22.
Tung F, Little JJ (2016) Scene parsing by nonparametric label transfer of content-adaptive windows. Comput Vis Image Underst 143:191–200CrossRef
23.
Kolmogorov V, Zabin R (2004) What energy functions can be minimized via graph cuts? IEEE Trans Pattern Anal Mach Intell 26(2):147–159CrossRef
24.
Shuai B, Zuo Z, Wang G, Wang B (2016) Scene parsing with integration of parametric and non-parametric models. IEEE Trans Image Process 25(5):2379–2391CrossRefMathSciNet
Metadata
Title
Scene Parsing with Deep Features and Per-Exemplar Detectors
Authors
Xiaofei Cui
Hanbing Qu
Xi Chen
Ziliang Qi
Liang Dong
Copyright Year
2018
Publisher
Springer Singapore
Book
Proceedings of 2017 Chinese Intelligent Automation Conference

Print ISBN: 978-981-10-6444-9

Electronic ISBN: 978-981-10-6445-6

Copyright Year: 2018

DOI
https://doi.org/10.1007/978-981-10-6445-6_40