Yet Another Survey on Image Segmentation: Region and Boundary Information Integration

Freixenet, Jordi; Muñoz, Xavier O'Callaghan; Raba, David; Martı́, Joan; Cufí, Xavier

doi:10.1007/3-540-47977-5_27

Cited by 385 publications

(228 citation statements)

References 25 publications

Supporting

Mentioning

227

Contrasting

Unclassified

Order By: Relevance

“…For comparisons, we use the same metrics as in [15], namely the Boundary Displacement Error [9] (BDE) and the Jaccardindex (i.e., intersection over union, IOU) [21] (J). Fig.…”

Section: Saliency-based Evaluationmentioning

confidence: 99%

Lightweight Monocular Obstacle Avoidance by Salient Feature Fusion

Manno-Kovacs

Kovács

2017

2017 IEEE International Conference on Computer Vision Workshops (ICCVW)

View full text Add to dashboard Cite

We present a monocular obstacle avoidance method based on a novel image feature map built by fusing robust saliency features, to be used in embedded systems on lightweight autonomous vehicles. The fused salient features are a textural-directional Harris based feature map and a relative focus feature map. We present the generation of the fused salient map, along with its application for obstacle avoidance. Evaluations are performed from a saliency point of view, and for the assessment of the method's applicability for obstacle avoidance in simulated environments. The presented results support the usability of the method in embedded systems on lightweight unmanned vehicles.

show abstract

“…For comparisons, we use the same metrics as in [15], namely the Boundary Displacement Error [9] (BDE) and the Jaccardindex (i.e., intersection over union, IOU) [21] (J). Fig.…”

Section: Saliency-based Evaluationmentioning

confidence: 99%

Lightweight Monocular Obstacle Avoidance by Salient Feature Fusion

Manno-Kovacs

Kovács

2017

2017 IEEE International Conference on Computer Vision Workshops (ICCVW)

View full text Add to dashboard Cite

show abstract

“…There are two types of algorithms that belong to this category. The first type of algorithms carries out region and boundary segmentations sequentially [18] [19] [20], where one segmentation method is employed as the preprocessing or initialization step of another. The second type performs segmentation by considering region and boundary information simultaneously [21] [22].…”

Section: Boundary (Edge) Informationmentioning

confidence: 99%

A human visual system-driven image segmentation algorithm

Peng¹,

Varshney²

2015

Journal of Visual Communication and Image Representation

View full text Add to dashboard Cite

This paper presents a novel image segmentation algorithm driven by human visual system (HVS) properties. Quality metrics for evaluating the segmentation result, from both region-based and boundary-based perspectives, are integrated into an objective function. The objective function encodes the HVS properties into a Markov random fields (MRF) framework, where the just-noticeable difference (JND) model is employed when calculating the difference between the image contents. Experiments are carried out to compare the performances of three variations of the presented algorithm and several representative segmentation algorithms available in the literature. Results are very encouraging and show that the presented algorithms outperform the state-of-the-art image segmentation algorithms. Index Terms-Image segmentation, human visual system, Markov random fields, just-noticeable difference KEYWORDS: Abstract-This EDICS-ARS-RBS

show abstract

“…There exists a tremendous quantity of image segmentation approaches [11,21]. Our goal in this paper is not to propose a new segmentation algorithm, but to study the influence of the segmentation as a preprocessing step in the object detection and recognition pipeline.…”

Section: Image Segmentationmentioning

confidence: 99%

Segmentation-based multi-class semantic object detection

Vieux

Benois-Pineau

Domenger

et al. 2010

Multimed Tools Appl

View full text Add to dashboard Cite

In this paper we study the problem of the detection of semantic objects from known categories in images. Unlike existing techniques which operate at the pixel or at a patch level for recognition, we propose to rely on the categorization of image segments. Recent work has highlighted that image segments provide a sound support for visual object class recognition. In this work, we use image segments as primitives to extract robust features and train detection models for a predefined set of categories. Several segmentation algorithms are benchmarked and their performances for segment recognition are compared. We then propose two methods for enhancing the segments classification, one based on the fusion of the classification results obtained with the different segmentations, the other one based on the optimization of the global labelling by correcting local ambiguities between neighbor segments. We use as a benchmark the Microsoft MSRC-21 image database and show that our method competes with the current state-of-the-art.

show abstract

Yet Another Survey on Image Segmentation: Region and Boundary Information Integration

Cited by 385 publications

References 25 publications

Lightweight Monocular Obstacle Avoidance by Salient Feature Fusion

Lightweight Monocular Obstacle Avoidance by Salient Feature Fusion

A human visual system-driven image segmentation algorithm

Segmentation-based multi-class semantic object detection

Contact Info

Product

Resources

About