DL & CV-based indicator toolset for the vehicle drivers via live dash-cam footage.

Overview

Vehicle Indicator Toolset

Deep Learning and Computer Vision based indicator toolset for vehicle drivers using live dash-cam footages.

Tracking of vehicles
The tracking of the vehicles with a track ID can be seen below.

|


Detection of the lanes.
Whenever the driver gets out of the lane, he will be displayed a warning to stay inside the lane.

|


Tail light detection
Detect all the tail lights of the vehicles applying brakes at night.

|


Traffic signal recognition
Warning is shown when to stop and resume again using traffic lights.

|



Vehicle collision estimation
Incase, a collision is estimated, driver is warned.

|



Pedestrian stepping
Whenever, pedestrian comes in our view, a warning is displayed.

|


Dependencies required:

  • Python 3.0
  • TensorFlow 2.0
  • openCV

Project Structure:

  • lanes:This folder contains files related to lane detection only.
  • tf-color: This folder contains files related to traffic light detection and detect the colour and accordingly give instructions to the driver.
  • tracked: This folder contains detection and tracking algorithm for the vehicles.
  • untracked: Detection and visualization only
  • utils: contains various functions that are used continuously again and again for different frames.
  • estimations: Detect pedestrians and vehicles too close to us that may cause collision.
  • cropping: Cropping frames using drag and drop or clicking points.
  • display: All the gifs shown above are stored here.

Requisities:

Download the tensorflow model from here.

  • Provide the path to the labels txt file using variable named PATH_TO_LABELS.
  • Provide the path to the tensorflow model using variable named model_name.
  • Make sure all the files are imported properly from the utils folder. If you get an error, add the location of the utils folder using sys module.
  • Tensorflow version 2.0 is must or else you may come across various error.

Working:

Run python integrate3.py or python intyolo.py after following the above mentioned requisities.
Now select the dash area for the car by clicking on multiple points as shown below. This is done to
remove detection of our own vehicle in some cases which may generate false results.

In the second step, select the area where searching of the lanes should be made. This may differ due to
the placement of dash-cams in the vehicle. The area above the horizon where road ends should not be selected.

Now, you can visualize the working and see the warnings/suggestions displayed to the driver.
All the works that are implemented individually are present in their respective folders, which are integrated together.
Old models may have some bugs now, as many files inside utils are changed.
Visit honors branch of models repository forked from tf/models to see more work on this project,
that I have done in google colab.

Drawbacks:

  • At night, searching for tail light should be made in the dark. If sufficient light is present, false cases can get introduced.
  • Tracking works good for bigger objects, while smaller may loose their track ID at places.
  • Threshold values used in lane detection needs to be altered depending on the roads and the quality of the videos.
  • Object detection needs to work properly for better results throughout. The model with higher accuracy should be downloaded from the link given above.
Owner
Alex Xu
Alex Xu
Nodule Generation Algorithm Baseline and template code for node21 generation track

Nodule Generation Algorithm This codebase implements a simple baseline model, by following the main steps in the paper published by Litjens et al. for

node21challenge 10 Apr 21, 2022
Shape-aware Semi-supervised 3D Semantic Segmentation for Medical Images

SASSnet Code for paper: Shape-aware Semi-supervised 3D Semantic Segmentation for Medical Images(MICCAI 2020) Our code is origin from UA-MT You can fin

klein 125 Jan 03, 2023
PyTorch implementation of adversarial patch

adversarial-patch PyTorch implementation of adversarial patch This is an implementation of the Adversarial Patch paper. Not official and likely to hav

Jamie Hayes 172 Nov 29, 2022
Neural Magic Eye: Learning to See and Understand the Scene Behind an Autostereogram, arXiv:2012.15692.

Neural Magic Eye Preprint | Project Page | Colab Runtime Official PyTorch implementation of the preprint paper "NeuralMagicEye: Learning to See and Un

Zhengxia Zou 56 Jul 15, 2022
Audio Domain Adaptation for Acoustic Scene Classification using Disentanglement Learning

Audio Domain Adaptation for Acoustic Scene Classification using Disentanglement Learning Reference Abeßer, J. & Müller, M. Towards Audio Domain Adapt

Jakob Abeßer 2 Jul 06, 2022
Neural networks applied in recognizing guitar chords using python, AutoML.NET with C# and .NET Core

Chord Recognition Demo application The demo application is written in C# with .NETCore. As of July 9, 2020, the only version available is for windows

Andres Mauricio Rondon Patiño 24 Oct 22, 2022
Official project website for the CVPR 2021 paper "Exploring intermediate representation for monocular vehicle pose estimation"

EgoNet Official project website for the CVPR 2021 paper "Exploring intermediate representation for monocular vehicle pose estimation". This repo inclu

Shichao Li 138 Dec 09, 2022
Tensorforce: a TensorFlow library for applied reinforcement learning

Tensorforce: a TensorFlow library for applied reinforcement learning Introduction Tensorforce is an open-source deep reinforcement learning framework,

Tensorforce 3.2k Jan 02, 2023
Code for our paper 'Generalized Category Discovery'

Generalized Category Discovery This repo is a placeholder for code for our paper: Generalized Category Discovery Abstract: In this paper, we consider

107 Dec 28, 2022
This is the official repository of Music Playlist Title Generation: A Machine-Translation Approach.

PlyTitle_Generation This is the official repository of Music Playlist Title Generation: A Machine-Translation Approach. The paper has been accepted by

SeungHeonDoh 6 Jan 03, 2022
An unofficial styleguide and best practices summary for PyTorch

A PyTorch Tools, best practices & Styleguide This is not an official style guide for PyTorch. This document summarizes best practices from more than a

IgorSusmelj 1.5k Jan 05, 2023
Pyramid Scene Parsing Network, CVPR2017.

Pyramid Scene Parsing Network by Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang, Jiaya Jia, details are in project page. Introduction This

Hengshuang Zhao 1.5k Jan 05, 2023
The code release of paper 'Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization' NIPS 2020.

Domain Generalization for Medical Imaging Classification with Linear Dependency Regularization The code release of paper 'Domain Generalization for Me

Yufei Wang 56 Dec 28, 2022
A python library for time-series smoothing and outlier detection in a vectorized way.

tsmoothie A python library for time-series smoothing and outlier detection in a vectorized way. Overview tsmoothie computes, in a fast and efficient w

Marco Cerliani 517 Dec 28, 2022
Pytorch implementation of RED-SDS (NeurIPS 2021).

Recurrent Explicit Duration Switching Dynamical Systems (RED-SDS) This repository contains a reference implementation of RED-SDS, a non-linear state s

Abdul Fatir 10 Dec 02, 2022
Autonomous Perception: 3D Object Detection with Complex-YOLO

Autonomous Perception: 3D Object Detection with Complex-YOLO LiDAR object detect

Thomas Dunlap 2 Feb 18, 2022
The world's largest toxicity dataset.

The Toxicity Dataset by Surge AI Saving the internet is fun. Combing through thousands of online comments to build a toxicity dataset isn't. That's wh

Surge AI 134 Dec 19, 2022
Advanced yabai wooting scripts

Yabai Wooting scripts Installation requirements Both https://github.com/xiamaz/python-yabai-client and https://github.com/xiamaz/python-wooting-rgb ne

Max Zhao 3 Dec 31, 2021
DeepVoxels is an object-specific, persistent 3D feature embedding.

DeepVoxels is an object-specific, persistent 3D feature embedding. It is found by globally optimizing over all available 2D observations of

Vincent Sitzmann 196 Dec 25, 2022
Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"

Mask2Former: Masked-attention Mask Transformer for Universal Image Segmentation Bowen Cheng, Ishan Misra, Alexander G. Schwing, Alexander Kirillov, Ro

Meta Research 1.2k Jan 02, 2023