pandas-team / autonomous-vehicle-environment-perception Goto Github PK

Good day!
Beautiful project, I'm trying to run in сolab on my video and get unsatisfactory results, I guess because of the low quality of the picture + bad road markings, isn't it?
What does the green area on the picture mean?

How to improve the frame rate of the output video, my output display interface is only about 2 frames

Hi, may I know how to get the actual distance of vehicle as done on the BD-100K dataset.

Hello :D

I want to know why I can't get the video output from my own video input. But the program works really well. It just cant save the results, the results don't have any size.

When I try the program using input from your drive, it can save the results. I'm just wondering why because there's no error or warning,

This is the output when I try the program with your video

and this is the output when I try the program with my own video, the size is unknown and a corrupt video

By the way, I'm using a video with 17 seconds duration, 1019 frames, and .mp4 format type. I wonder if there's any specific input video format. Thank you so much for your help!

A nice work!
When I read your paper, I found the performances of CLRNet and CondlaneNet are quite bad on both datasets. So have you finetuned them on these datasets? Or you used the pretrained model to evaluate to see the generalization. If so, which model did you choose? CULane or Tusimple?
Thanks for your time.