Salient Region Detection Methods with Application to Traffic Sign Recognition from Street View Images
Doktorsavhandling, 2016

In the computer vision community, saliency detection refers to modeling the selective mechanism in human visual attentions. Outputs of saliency detection algorithms are called saliency maps, which represent conspicuousness levels of different scene areas. Since saliency detection is an effective way to estimate regions of interest that may be attractive to human eyes, numerous applications range from object recognition, image compression, to content-based image editing and image retrieval. This thesis focuses on salient region detection, which aims at detecting and segmenting holistic salient objects from natural images. Despite of many existing models/algorithms and rapid progress in this field over the past decade, improving the detection performance in complex and unconstrained scenarios remains challenging. This thesis proposes five innovative methods for salient region detection. Each method is designed to solve some issues in the existing models. The main contributions of this thesis include: 1) A novel method that induces saliency maps through eigenvectors of the normalized graph cut for better visual clustering of objects and background. It leads to more accurate saliency estimation. 2) A novel data-driven method for salient region detection based on continuous conditional random field (C-CRF). It provides an optimal way to integrate various unary saliency features with pairwise cues. 3) A robust graph-based diffusion method, referred to as manifold-preserving diffusion (MPD). Based on two assumptions on manifold---smoothness and local reconstruction, the method preserves the manifold used in the saliency diffusion. 4) A superpixel-based method that effectively computes color contrast and color distribution attributes of images in a unified manner. 5) A new geodesic propagation method that is used to optimize coarse salient regions for rendering visual coherence. In addition, driven by applications, this thesis also addresses traffic sign recognition (TSR) problem from street view images. As a new application linking between saliency detection and TSR, salient region detection of traffic signs is investigated in order to enhance the sign classification performance.

normalized cut

traffic sign recognition

saliency propagation

color distribution

continuous conditional random field

manifold

Salient region detection

adaptive graph edge weights

color contrast

geodesics

Room EC-salen, Hörsalsvägen 11, EDIT building, 5th floor, Chalmers University of Technology
Opponent: Volker Krüger, Department of Mechanical and Production Engineering, Aalborg University, Denmark

Författare

Keren Fu

Signaler och system, Signalbehandling och medicinsk teknik, Signalbehandling

Geodesic Distance Transform-based Salient Region Segmentation for Automatic Traffic Sign Recognition

Proceedings - 2016 IEEE Intelligent Vehicles Symposium, IV 2016, Gotenburg, Sweden, 19-22 June 2016,; (2016)p. 948-953

Paper i proceeding

Geodesic Saliency Propagation for Image Salient Region Detection

IEEE Int'l conf. on Image Processing (ICIP 2013), Sept.15-18, Melbourne, Australia,; (2013)p. 3278-3282

Paper i proceeding

Superpixel based Color Contrast and Color Distribution Driven Salient Object Detection

Signal Processing: Image Communication,; Vol. 28(2013)p. 1448-1463

Artikel i vetenskaplig tidskrift

Normalized Cut-based Saliency Detection by Adaptive Multi-Level Region Merging

IEEE Transactions on Image Processing,; Vol. 24(2015)p. 5671-5683

Artikel i vetenskaplig tidskrift

Robust manifold-preserving diffusion-based saliency detection by adaptive weight construction

Neurocomputing,; Vol. 175(2016)p. 336-347

Artikel i vetenskaplig tidskrift

Traffic Sign Recognition using Salient Region Features: A Novel Learning-based Coarse-to-Fine Scheme

IEEE Intelligent Vehicles Symposium, June 28-July 1, 2015, Seoul, Korea,; (2015)p. 443-448

Paper i proceeding

Keren Fu, Irene Yu-Hua Gu, Jie Yang. "Saliency Detection by Fully Learning A Continuous Conditional Random Field"

Styrkeområden

Informations- och kommunikationsteknik

Ämneskategorier

Signalbehandling

Datorseende och robotik (autonoma system)

Medicinsk bildbehandling

ISBN

978-91-7597-493-4

Doktorsavhandlingar vid Chalmers tekniska högskola. Ny serie: 4174

Utgivare

Chalmers tekniska högskola

Room EC-salen, Hörsalsvägen 11, EDIT building, 5th floor, Chalmers University of Technology

Opponent: Volker Krüger, Department of Mechanical and Production Engineering, Aalborg University, Denmark