Clear Filters
Clear Filters

How to use NGSIM I80 dataset for lane changing detection application in Matlab?

6 views (last 30 days)
I would like to use deep learning techniques to detect lane changing scenario present in NGSIM I80 dataset. I have downoaded processed video and ground truth (csv) file also.
But i don't know how exactly to proceed further in detecting the lane change of vehicle.
  1 Comment
idris on 4 Jun 2024 at 16:23
Edited: idris on 4 Jun 2024 at 16:24
You will need to use the following guide:
credit (Dr Omveer)
After extracting the data for US-101 (assuming using US-101), follow these steps:
1. Filter Vehicles on Lanes 1-5:
- Consider only the vehicles present on lanes 1 to 5.
2. Identify Target Vehicles on Lanes 2-4:
- Find the target vehicles that are present on lanes 2 to 4.
3. Extract Trajectory Data:
- Extract the trajectory data along with the frame number, vehicle ID, lane number, time, and position for the target vehicles.
4. Frame-by-Frame Analysis for Each Target Vehicle:
- For each target vehicle, process the data frame by frame.
4.1 Identify Vehicles in Each Frame:
- For each frame, identify the target vehicle and the surrounding vehicle IDs.
4.2 Determine Positions:
- Find the positions of the identified vehicles.
5. Save Variables:
- Save all variables for the target vehicle.
6. Repeat for Next Target Vehicle:
- Repeat steps 3 to 5 for the next target vehicle.

Sign in to comment.

Answers (0)




Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!