Skip to content

Example scripts for the detection of lanes using the ultra fast lane detection model in Tensorflow Lite.

License

Notifications You must be signed in to change notification settings

Sendeky/TfLite-Ultra-Fast-Lane-Detection-Inference

 
 

Repository files navigation

TFlite Ultra Fast Lane Detection Inference

Example scripts for the detection of lanes using the ultra fast lane detection model in Tensorflow Lite.

!Ultra fast lane detection Source: https://www.flickr.com/photos/32413914@N00/1475776461/

Requirements

  • OpenCV, scipy and tensorflow/tflite_runtime. pafy and youtube-dl are required for youtube video inference.

Installation

pip install -r requirements.txt
pip install pafy youtube-dl

For the tflite runtime, you can either use tensorflow pip install tensorflow or the TensorFlow Runtime

tflite model

The original model was converted to different formats (including .tflite) by PINTO0309, download the models from his repository and save it into the models folder.

Original Pytorch model

The Pytorch pretrained model from the original repository.

Ultra fast lane detection - TuSimple(link)

  • Input: RGB image of size 800 x 200 pixels.
  • Output: Keypoints for a maximum of 4 lanes (left-most lane, left lane, right lane, and right-most lane).

Examples

  • Image inference:
python imageLaneDetection.py 
  • Webcam inference:
python webcamLaneDetection.py
  • Video inference:
python videoLaneDetection.py

Pytorch inference

For performing the inference in Pytorch, check my other repository Ultrafast Lane Detection Inference Pytorch.

ONNX inference

For performing the inference in ONNX, check my other repository ONNX Ultra Fast Lane Detection Inference.

!Ultrafast lane detection on video

Original video: https://youtu.be/2CIxM7x-Clc (by Yunfei Guo)

About

Example scripts for the detection of lanes using the ultra fast lane detection model in Tensorflow Lite.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%