多级分割下的判别式区域特征融合显著对象检测

需积分: 9 57 浏览量更新于2024-09-13 收藏 964KB PDF 举报

"显著性检测：判别式区域特征融合方法（Salient Object Detection: A Discriminative Regional Feature Integration Approach）是2013年在计算机视觉与模式识别（CVPR）会议上发表的一篇论文。作者华如竹、王景东、袁泽健、吴扬、郑南宁和李诗鹏在西安交通大学和微软亚洲研究院、京都大学的研究团队合作，提出了一个新颖的显著对象检测算法。论文的核心观点是将显著性检测视为回归问题，通过多层次图像分割技术，采用监督学习方法，将每个区域的特征向量转化为对应的显著性分数。这种方法的关键在于它结合了三个关键概念：区域对比度（representing the difference between a region and its surrounding context）、区域属性（describing the unique characteristics of an object）以及区域背景度（measuring how well a region stands out from its background）。这些元素被整合在一起形成所谓的“主显著性地图”，能够生成比现有许多基于不同特征类型（如颜色、纹理、边缘等）的启发式显著性图谱更为优越的结果。该方法的优势在于其系统性和精确性。通过多级融合，不仅考虑了局部特征的丰富性，还考虑了全局上下文信息，这使得它在处理复杂场景中的显著性检测任务时更具优势。此外，通过监督学习，算法能够学习到更深层次的特征关联，提高了对真实显著对象的识别能力。这篇论文提出了一种新颖的显著性检测框架，通过深度学习和特征融合，显著提升了显著对象检测的性能，并为后续研究者提供了新的思路，即如何利用高级别的特征表示和学习来改进显著性检测算法。这对于图像理解、计算机视觉和机器智能等领域都有着重要的实践价值。"

Salient Object Detection: A Discriminative Regional Feature

Integration Approach

Huaizu Jiang

†

Jingdong Wang

‡

Zejian Yuan

†

Yang Wu

Nanning Zheng

†

Shipeng Li

‡

†

Xi’an Jiaotong University

‡

Microsoft Research Asia

Kyoto University

https://sites.google.com/site/jianghz88/saliency_drfi

Abstract

Salient object detection has been attracting a lot of

interest, and recently various heuristic computational

models have been designed. In this paper, we regard

saliency map computation as a regression problem. Our

method, which is based on multi-level image segmenta-

tion, uses the supervised learning approach to map the

regional feature vector to a saliency score, and ﬁnally

fuses the saliency scores across multiple levels, yielding

the saliency map. The contributions lie in two-fold.

One is that we show our approach, which integrates

the regional contrast, regional property and regional

backgroundness descriptors together to form the master

saliency map, is able to produce superior saliency maps

to existing algorithms most of which combine saliency

maps heuristically computed from diﬀerent types of fea-

tures. The other is that we introduce a new regional fea-

ture vector, backgroundness, to characterize the back-

ground, which can be regarded as a counterpart of the

objectness descriptor [2]. The performance evaluation

on several popular benchmark data sets validates that

our approach outperforms existing state-of-the-arts.

1. Introduction

Visual saliency has been a fundamental problem in

neuroscience, psychology, neural systems, and com-

puter vision for a long time. It is originally a task of

predicting the eye-ﬁxations on images, and recently has

been extended to identifying a region containing the

salient object, which is the focus of this paper. There

are various applications for salient object detection, in-

cluding object detection and recognition [25, 46], im-

age compression [21], image cropping [35], photo col-

lage [17, 47], dominant color detection [51, 52] and so

on.

The study on human visual systems suggests that

the saliency is related to uniqueness, rarity and sur-

prise of a scene, characterized by primitive features

like color, texture, shape, etc. Recently a lot of eﬀorts

have been made to design various heuristic algorithms

to compute the saliency [1, 6, 11, 15, 18, 27, 31, 34, 38].

In this paper, we regard saliency estimation as a

regression problem, and learn a regressor that directly

maps the regional feature vector to a saliency score.

Our approach consists of three main steps. The ﬁrst

one is multi-level segmentation, which decomposes the

image to multiple segmentations from a ﬁne level to

a coarse one. Second, we conduct a region saliency

computation step with a random forest regressor that

maps the regional features to a saliency score. Last, a

saliency map is computed by fusing the saliency maps

across multiple levels of segmentations.

The key contributions lie in the second step, region

saliency computation. Unlike most existing algorithms

that compute saliency maps heuristically from various

features and combine them to get the saliency map,

which we call saliency integration, we learn a random

forest regressor that directly maps the feature vector

of each region to a saliency score, which we call dis-

criminative regional feature integration (DRFI). This

is a principle way in image classiﬁcation [19], but rarely

studied in salient object detection. It turns out that the

learnt regressor is able to automatically pick discrimi-

native features rather than heuristically hand-crafting

special features for saliency. On the other hand, we

also introduce a new descriptor, called backgroundness,

to discriminate the background from the object, which

can be considered as a counterpart of the objectness

descriptor [2].

1.1. Related work

The following gives a review of salient object detec-

tion (segmentation) algorithms that are related to our

approach. A comprehensive survey of salient object

detection can be found from [9]. The review on visual

attention modeling [7] also includes some analysis on

salient object detection.

2013 IEEE Conference on Computer Vision and Pattern Recognition

DOI 10.1109/CVPR.2013.271

2081

2013 IEEE Conference on Computer Vision and Pattern Recognition

DOI 10.1109/CVPR.2013.271

2081

2013 IEEE Conference on Computer Vision and Pattern Recognition

DOI 10.1109/CVPR.2013.271

2083

下载后可阅读完整内容，剩余7页未读，立即下载

keltloja

粉丝: 0
资源: 5

多级分割下的判别式区域特征融合显著对象检测

Face Detection and Recognition on Mobile Devices

Real-time multiple vehicle detection and tracking from a moving vehicle.pdf

Real-Time BCI System Design

Salient Object Detection

RGBD Salient Object Detection A Benchmark and Algorithms

20200894_RGB-D Salient Object Detection A Survey.pdf

SALIENT OBJECT DETECTION VIA BACKGROUND CONTRAST

Robust salient object detection for RGB images

SALIENT OBJECT DETECTION VIA OBJECTNESS MEASURE.pdf

MATLAB implementation of the paper Salient Object Detection

最新资源