Temporal analysis on the IDD temporal dataset

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

Description

I want to perform temporal analysis on the Indian Driving Dataset (IDD) temporal dataset. I want to be able to predict the future path of the moving vehicle for autonomous driving. I have the dataset ready. How do I approach this task?

Environment

GPU Type: NVIDIA Corporation GP106 [GeForce GTX 1060 6GB]
Nvidia Driver Version: NVIDIA-SMI 535.129.03
CUDA Version: 12.2
Operating System + Version: Ubuntu 22.04.3

Relevant Files

Dataset details: INSAAN | Datasets
The IDD temporal dataset consists of the temporally nearby frames (± 15 frames) from the IDD Segmentation and Detection Datasets. The 30 nearby frames for many of the frames in the IDD Segmentation dataset, is provided in the correspondingly named subfolders in the IDD temporal dataset.

2

Do I have to start with obect detection first then move on to this. Please give an elaborate answer, Thanks :)