icsfy / pedestrian_detection Goto Github PK
View Code? Open in Web Editor NEW通过HOG+SVM训练进行行人检测,行人数据库使用INRIAPerson,程序基于OpenCV实现
通过HOG+SVM训练进行行人检测,行人数据库使用INRIAPerson,程序基于OpenCV实现
I am sincerely consult for the The steps to detect pedestrian in video? thanks you @icsfy
自己训练得到SVM_HOG.xml文件,使用SVM_HOG.xml文件,svm.predict()测试结果完全正确,但是使用HOG.detectMultiScale()进行检测的时候,一直没有rect结果。感觉跟这个有点相似https://stackoverflow.com/questions/31706560/svm-hog-found-object-is-always-null
计算-(alphaMat * supportVectorMat)为什么要乘-1?
g++ -o SvmTrainUseHog main.cpp $(pkg-config opencv --cflags --libs)
这行命令的时候出了错误
https://www.douban.com/note/638487822/
从错误提示来看,问题应该都出在class MySVM上,应该是定义不完全,希望能够解答
For usage in raspberry pi, is this program fast enough?
Is this detector faster than yolo?
Thanks!
video_detection.cpp中读取视频一直失败,返回的一直是0
@icsfy 楼主你好,可执行文件并不能达到裁剪图片的作用。
你好!谢谢您开源了这部分代码,但是我最近碰到了一个很困惑的问题,就是我训练出来的.xml文件中支撑向量的个数只有1个,不管如何调整参数和训练样本的个数,都是一个,看到您上传的SVM_HOG.xml文件里也只有一个支撑向量,所以想问下这个是正常的吗?因为直接拿这个文件去检测行人效果非常不好,所以觉得是这里有问题,希望可以得到您的回复,再次感谢!
大神吖,我就换了数据库,别的都没变,已经能读取了图片,也训练完了,但是在替换的时候报了错,怎么就两个分类器的大小不一致了尼?
报错如下:
开始训练SVM分类器
训练完成
支持向量个数:1
检测子维数:94501
OpenCV Error: Assertion failed (checkDetectorSize()) in setSVMDetector, file /build/buildd/opencv-2.4.8+dfsg1/modules/objdetect/src/hog.cpp, line 89
terminate called after throwing an instance of 'cv::Exception'
what(): /build/buildd/opencv-2.4.8+dfsg1/modules/objdetect/src/hog.cpp:89: error: (-215) checkDetectorSize() in function setSVMDetector
跪求解答。。。
你好,main.cpp里的hot.compute里面报错,是什么原因呢
在执行./SvmTrainUseHog时会出现问题
libpng error: IDAT: invalid distance too far back
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.