一种基于颜色属性的通用目标检测方法

赵起超; 任明武

Chinese

您当前的位置：

首页 >

文章列表页 >

一种基于颜色属性的通用目标检测方法

更新时间：2026-09-04

- 一种基于颜色属性的通用目标检测方法
- A Method of Generic Object Detection Based on Image Color Names
- 微电子学与计算机 2017年34卷第2期页码：128-131
- 作者机构：
  
  南京理工大学计算机科学与工程学院,江苏,南京,210094
- 作者简介：
- 基金信息：
- DOI：
  中图分类号：
- 纸质出版：2017
- 稿件说明：
移动端阅览
赵起超, 任明武. 一种基于颜色属性的通用目标检测方法[J]. 微电子学与计算机, 2017, 34(2): 128-131.

ZHAO Qi-chao, REN Ming-wu. A Method of Generic Object Detection Based on Image Color Names[J]. 2017, 34(2): 128-131.
赵起超, 任明武. 一种基于颜色属性的通用目标检测方法[J]. 微电子学与计算机, 2017, 34(2): 128-131. DOI：

ZHAO Qi-chao, REN Ming-wu. A Method of Generic Object Detection Based on Image Color Names[J]. 2017, 34(2): 128-131. DOI：

摘要

通用目标检测是视频分析技术中目标定位、检测和跟踪的关键技术.针对数字图像分析中的通用目标检测问题

提出了一种基于颜色属性的通用目标检测算法

用以提取图像中有可能包含目标的子区域并以外接矩形的形式输出.该算法首先利用输入图像的颜色属性对其进行区域分割并计算划分后的区域相似度

接着根据相邻区域间的相似度进行区域合并

最后结合选择性搜索策略

实现了通用目标的检测.实验表明此算法检测出的候选框的精度可以满足通用目标检测的要求.

Abstract

Generic object detection is the key to object localization

detection and tracking in video analyzing. In this paper

we propose a algorithm of generic object detection based on image color names

by which we can obtain sub-regions containing objects in the form of rectangle. In the beginning

an input image is segmented by using color names and the similarity of different regions is computed. Next

we merge the regions based on the similarity between the adjacent ones. Last but not least

selective search strategy is adopted to realize generic object detection in the images. The Experiments show that the candidate boxes detected by this method can meet the accuracy requirements of generic object detection.

关键词

Keywords

references

Hosang J, Benenson J, Dollar R. What makes for effective detection proposals[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2015, 99: 1. DOI: 1

Felzenszwalb P F, Huttenlocher D P. Efficient graph-based image degmentation[J]. International Journal of Computer Vision, 2004, 59: 167-181. DOI: 167

Joost van de Weijer, Cordelia Schmid, Jakob Verbeek. Learning Color Names from Real-World Images[C]//IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis: IEEE, 2007: 1-8.

Fahad Shahbaz Khan, Rao Muhammad Anwer, Joost van de Weijeer. Color Attributes for Object Detection[C]//Proceedings CVPR 2012. CVPR, 2012.

Xu Dan, Tang Zhenmin, Xu Wei. Combining color names with spatial information for salient object detection[J]. Journal of Image and Graphics, 2014, 19(4): 541-548. DOI: 541

闯跃龙, 张石清, 郭文平, 等. 基于感知哈希和自适应搜索的通用对象检测[J]. 光电子·激光, 2016, 27(2): 231-238. DOI: 231

Koen E A van de Sande, Jsaper R R Uijlings, Theo Gevers, et al. Segmentation as selective search for object recognition[R]. ICCV, 2011: 1879-1886.

Uijlings J R R, K E A. van de Sande, Gevers T, et al. Selective Search for object Recognition[J]. International Journal of Computer Vision, 2013, 104: 154-171. DOI: 154

Hosang J, Benenson R, Schiele B. How good arre detection proposals, really?[C]//Proceedings British Machine Vision Conference 2014. Nottingham, 2014.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向处理器分支预测单元的Spectre攻击轻量化防御方法

V型沟槽SiC中子探测器的蒙特卡洛分析

基于反向体偏置的高增益稳定性高温运放设计

基于MSS-YOLO-MPHands融合架构的装配手部动作识别研究

超低功耗实时时钟电路的设计