I want to recognise an image and also to extract information from the image. Like while pointing the camera on vehicle dashboard it should detect all the led lights and should show an Augmented reality information for each led lights and what is the meaning if the led is blinking.
我想识别图像并从图像中提取信息。就像将相机指向车辆仪表板一样，它应该检测所有LED灯，并且应该显示每个LED灯的增强现实信息以及LED指示灯闪烁的含义。
I tried with Wikitude, Craft AR and other libraries that they are focusing on recognising one single image.
我尝试使用Wikitude，Craft AR和其他图书馆，他们专注于识别单个图像。
For me I want to recognise an image and within that image I want to detect all the led lights and display information in augmented reality way on the camera display.
对我来说，我想要识别一个图像，在该图像中我想要检测所有的LED灯并在相机显示器上以增强现实的方式显示信息。
1 个解决方案
#1
1
I think you are probably looking for a computer vision segmentation/detecion problem. For that I would suggest to use openCV to process the images and detect the information of the leds that you need. Depending on what you want to do with that then you could need some of those AR libraries or not, but without more information I would suggest you to try to do some experiments on openCV to achieve your goals.
我想你可能正在寻找计算机视觉分割/检测问题。为此，我建议使用openCV处理图像并检测您需要的LED的信息。根据你想要做什么，你可能需要一些AR库，但没有更多的信息，我建议你尝试在openCV上做一些实验，以实现你的目标。
#1
1
I think you are probably looking for a computer vision segmentation/detecion problem. For that I would suggest to use openCV to process the images and detect the information of the leds that you need. Depending on what you want to do with that then you could need some of those AR libraries or not, but without more information I would suggest you to try to do some experiments on openCV to achieve your goals.
我想你可能正在寻找计算机视觉分割/检测问题。为此，我建议使用openCV处理图像并检测您需要的LED的信息。根据你想要做什么，你可能需要一些AR库，但没有更多的信息，我建议你尝试在openCV上做一些实验，以实现你的目标。