Would this algorithm work if we add an output to detect other types of parking spaces?

[BranisGh]

Hello, I am interested in working with this algorithm, however, the parking spaces I want to detect do not correspond to either the L or T type. In fact, the parking spaces I want to detect are rather straight lines that do not have significant intersections. I would like to know why this case has not been considered in your algorithm. If I add an output to the network to classify this new type of parking space, taking into account annotation and inference, do you think it could work?

[Teoge]

Hi,

Thank you for your interest in our algorithm. The reason why the case of straight line parking spaces has not been considered in our algorithm is because our experiments were primarily conducted in China, where the majority of parking-slots are composed of T-shape and L-shape marking-points.

However, I believe that our approach can still be adapted to work with straight line parking spaces if you manage to collect sufficient data of this new type of parking space and retrain the model accordingly. By adding an output to the network to classify this new type of parking space, and considering annotation and inference, it is possible to enhance the algorithm's capability to detect these straight line parking spaces.

I would also like to mention that a similar issue was raised in #1, where you can find more information and potential insights related to your question. If you have any further questions, please let me know. I'll be glad to help you.