[英]Feature detection for embedded platform OpenCV
I'm trying to do object recognition in an embedded environment, and for this I'm using Raspberry Pi (Specifically version 2). 我正在尝试在嵌入式环境中进行对象识别,为此我正在使用Raspberry Pi(特别是版本2)。
I'm using OpenCV Library and as of now I'm using feature detection algorithms contained in OpenCV. 我正在使用OpenCV库,截至目前我正在使用OpenCV中包含的特征检测算法。
So far I've tried different approaches: 到目前为止,我尝试过不同的方法:
I now am to the point where I get the best results time permitting using ORB for keypoint extraction and SURF for description. 我现在已经达到了最佳结果时间,允许使用ORB进行关键点提取和SURF进行描述。 But it is still really slow.
但它仍然很慢。
So do you have any suggestions or new ideas to obtain better results? 那么您有什么建议或新想法可以获得更好的结果吗? Am I missing something?
我错过了什么吗?
As additional information, I'm using Python 3.5 with OpenCV 3.1 作为附加信息,我正在使用Python 3.5和OpenCV 3.1
I have done similar project in my Masters Degree. 我在硕士学位上做过类似的项目。
I had used Raspberry Pi 3 because it is faster than Pi 2 and has more resources for image processing. 我曾经使用过Raspberry Pi 3,因为它比Pi 2更快,并且拥有更多的图像处理资源。
I had used KNN algorithm in OpenCV for Number Detection. 我在OpenCV中使用KNN算法进行数字检测。 It was fast and had good efficiency.
它速度快,效率高。
The main advantage of KNN algorithm is it is very light weight. KNN算法的主要优点是重量很轻。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.