traffic-light-detection-module

⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️

IMPORTANT UPDATE

This repo is deprecated. For a newer and improved model, implemented in PyTorch, please refer to this repo.

⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️⚠️

About

Module for detecting traffic lights in the CARLA autonomous driving simulator (version: 0.8.4).
Built upon and inspired by https://github.com/experiencor/keras-yolo2.
Instructions and more traffic light detection examples can be found below.

• This module is used along several other modules to implement our version of imitation learning in the CARLA simulator. Results of the core module can be found on this repository

• Model for objection detection is based on tiny yolov2

• Training started with yolov2 coco pretrained weights

• It was first trained on the LISA traffic light detection dataset (~5800 images), and after that on the dataset collected from the CARLA simulator by myself (~1800 images).

CARLA dataset and model

• Dataset collected by myself in the CARLA simulator can be found here, annotations can be found here.

• Important note - several images in the dataset are left out of annotations because bounding boxes are too small (too far away). I also filtered (left out) all images that have xmax < 15 when loading the dataset. There is around 70-80 out of ~1800 images that are left out, so it isn't that problematic.

• Pretrained model can be found here.

Instructions

• To train:

  • In the config file set training -> enabled to true
  • Put your annotations file in the dataset folder
  • In the config file set training -> annot_file_name to the name of your annotations file
  • Put your images in the dataset/images folder
  • If necessary, adjust parameters in config according to your problem/dataset
  • run main.py with -c config.json

• To evaluate:

  • In the config file set training -> enabled to false
  • Put your annotations file in the evaluation folder
  • In the config file set training -> annot_file_name to to the name of your annotations file containing images for evaluation
  • Put your images in the evaluation/images folder
  • If necessary, adjust parameters in config according to your problem/dataset
  • run main.py with -c config.json

• To generate anchors:

  • run generate_anchors.py with -c config.json

• Soon to be added:

  • Real time traffic light detecting gifs

Examples

• Several examples of predictions, more can be found in the out folder