如何在路线检测中使用Python进行深度学习（Keras / Tensorflow）创建自己的数据集

Question

I am given the task to find road lines on an image for a class project.

I want to start writing Convolutional Neural Network to do the task, but I am not sure how to create a dataset.

Let's say I have to find lines on this image (originally I have been given arround 1000 images of traffic where road lines could be detected):

To be able to do that I have to create a dataset. What to do? Should I take some random images and cut regions where I can see the road lines? What size should the training images be? How would I label the line to stand out from the background?

Also, I presume cutting lines from an image is an okay way when the line is segmented, but I cannot do that for a full line, can I?

Answer 1

It depends a lot on the assignment details. What does "find road lines on an image" mean?

Depending on the answer to the above question, you could divide the image in a 4x4 or 5x5 grid and try to find the cells on that grid that contain road lines.

To accomplish that you could manually label some of the cells (you might want to create a small GUI to facilitate this part) and train your CNN with the labeled data.