[英]Finetuning a tensorflow object detection pretrained model
I'm working on a real-time object detector with tensorflow and opencv. 我正在使用tensorflow和opencv进行实时对象检测。
I've used different SSD and Faster-RCNN based frozen inference graphs and they almost never fail. 我使用了不同的SSD和基于Faster-RCNN的冻结推理图,它们几乎永远不会失败。
The video stream comes from a IR camera fixed to a wall that has a background that almost never changes. 视频流来自固定在墙壁上的红外摄像机,该墙壁的背景几乎没有变化。 There are some misdetections at particular hours of the day (eg when the light changes in the afternoon) that occur in the background area or on small objects too close to the camera.
在一天中的特定时间(例如,下午的光线变化),在背景区域或太靠近相机的小物体上会发生一些误检测。
So to fix this little mistakes i wanted to finetune the model with images from the same background. 因此,为了解决这个小错误,我想使用来自相同背景的图像对模型进行微调。
Being the background always the same, how do i approach the retraining of the model having 1000 misdetections pics that are all almost the same? 在背景始终相同的情况下,我该如何对具有1000个几乎完全相同的误检测图片的模型进行重新训练?
In case of variations in the background lighting, it might be possible to use Background Subtraction 如果背景照明发生变化,则可以使用背景减法
https://docs.opencv.org/3.4.1/d1/dc5/tutorial_background_subtraction.html ,while dynmically updating it as shown here: https://docs.opencv.org/3.4.1/d1/dc5/tutorial_background_subtraction.html ,同时动态更新它,如下所示:
https://www.pyimagesearch.com/2015/06/01/home-surveillance-and-motion-detection-with-the-raspberry-pi-python-and-opencv/ https://www.pyimagesearch.com/2015/06/01/home-surveillance-and-motion-detection-with-the-raspberry-pi-python-and-opencv/
Thank you. 谢谢。
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.