本文介绍了什么是最适合的方法使用Android设备检测图像无标记检测?的处理方法,对大家解决问题具有一定的参考价值,需要的朋友们下面随着小编来一起学习吧!

问题描述



我试图创建一个Android应用程序,使用openCV从相机检测对象,我读取openCV参考,发现有很多方法的图像检测,我的目的是创建一个应用程序



1)应用程序可以检测来自数据库中的任何对象(可以检测的对象的集合)处理/检测很重要)



2)对象映像的数据库将不时更新(数据库最好在外部服务器上) - 这是否意味着我不能使用级联分类器,HOG或任何机器学习方法?



3)相机框架有时可能有两个或更多的对象在数据库中都可以检测到这种情况?



我尝试了一个简单的功能检测与ORB检测和描述和强力匹配,但几乎任何对象或甚至墙检测 - 假阳性检测(使用SIFT或SURF

  FeatureDetector检测器= FeatureDetector.create(FeatureDetector.ORB) 
DescriptorExtractor extractor = DescriptorExtractor.create(DescriptorExtractor.ORB);
DescriptorMatcher matcher = DescriptorMatcher.create(DescriptorMatcher.BRUTEFORCE);

我不需要任何单应性或透视,因为我不打算投射任何东西只是一个鲁棒的方法检测对象的存在。

解决方案

2)你可以,但如果你想添加对象数据库。



3)是,如果您在框架上应用多个检测器。



可以使用latentsvm对象检测来检测部件的实现,但训练新模型有点棘手。



其他那样,你可以使用Viola& Jones或许多对象检测方案中的一个(例如,HOG + SVM或BOW + SVM)。


I'm trying to create an android application for detecting objects from camera using openCV, I read the openCV reference and found there are many methods for image detection,

my purpose is to create an application

1) App can detect the any object from database(set of objects that can be detected) on real time camera frame.(Speed of processing/detection is important)

2) The database of object images will be updated from time to time.(database preferably on an external server) - Does this mean I cannot use cascade classifier, HOG or any machine learing methods?

3) The camera frame may sometimes have two or more objects that are in database can both be detected in this case?

I tried a simple feature detection with ORB detection and description and bruteforce matching but gives detection for almost any object or even a wall - false positive detection.(using SIFT or SURF for testing even throws error)

FeatureDetector detector = FeatureDetector.create(FeatureDetector.ORB);
DescriptorExtractor extractor = DescriptorExtractor.create(DescriptorExtractor.ORB);
DescriptorMatcher matcher = DescriptorMatcher.create(DescriptorMatcher.BRUTEFORCE);

I dont need any homography or perspective since I'm not going to project anything just a robust method to detect presence of object.

解决方案

2) You can, but you would have to train new detectors if you want to add objects to the database.

3)Yes, if you would apply more then one detector on the frame.

You can use latentsvm object detection for detection by parts implementation, but it's a bit tricky to train new models.

Other then that, you can use Viola & Jones or one of many object detection schemes (for example, HOG + SVM or BOW+SVM).

这篇关于什么是最适合的方法使用Android设备检测图像无标记检测?的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持!

07-22 16:31
查看更多