Potholes are formed on roads due to wear and tear or weathering of roads. They cause discomforts to commuters and deaths due to vehicle accidents. There are numerous use cases to detect a pothole. Cameras installed on vehicles can see potholes on roads in real-time and help drivers to avoid them. The steps for building a pothole detection system are as follows: 1. Data acquisition and preparation 2. Model training and evaluation 3. Model deployment for real-time detection Some of the libraries can help you create applications to reduce accidents and discomforts by detecting potholes.
Data acquisition and preparation
VoTTby microsoft
Visual Object Tagging Tool: An electron app for building end to end Object Detection Models from Images and Videos.
VoTTby microsoft
TypeScript
4041
Version:v2.2.0
License: Permissive (MIT)
detectron2by facebookresearch
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
detectron2by facebookresearch
Python
25211
Version:v0.6
License: Permissive (Apache-2.0)
maskrcnn-benchmarkby facebookresearch
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
maskrcnn-benchmarkby facebookresearch
Python
9110
Version:v0.1
License: Permissive (MIT)
detrby facebookresearch
End-to-End Object Detection with Transformers
detrby facebookresearch
Python
11172
Version:v0.2
License: Permissive (Apache-2.0)
CenterNetby xingyizhou
Object detection, 3D detection, and pose estimation using center point detection:
CenterNetby xingyizhou
Python
6889
Version:Current
License: Permissive (MIT)
myvisionby OvidijusParsiunas
Computer vision based ML training data generation tool :rocket:
myvisionby OvidijusParsiunas
JavaScript
537
Version:1.0.0
License: Strong Copyleft (GPL-3.0)
OpenLabelingby Cartucho
Label images and video for Computer Vision applications
OpenLabelingby Cartucho
Python
862
Version:v1.3
License: Permissive (Apache-2.0)
Model deployment for realtime detection
servingby tensorflow
A flexible, high-performance serving system for machine learning models
servingby tensorflow
C++
5877
Version:2.12.1
License: Permissive (Apache-2.0)
tensorfxby TensorLab
TensorFlow framework for training and serving machine learning models
tensorfxby TensorLab
Python
189
Version:Current
License: Permissive (Apache-2.0)
modelsby IntelAI
Model Zoo for Intel® Architecture: contains Intel optimizations for running deep learning workloads on Intel® Xeon® Scalable processors
modelsby IntelAI
Python
561
Version:v2.11.0
License: Permissive (Apache-2.0)
nnfusionby microsoft
A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.
nnfusionby microsoft
C++
807
Version:v0.4
License: Permissive (MIT)
pamelaby dollabs
Probabalistic Advanced Modeling and Execution Learning Architecture
pamelaby dollabs
HTML
237
Version:Current
License: Permissive (Apache-2.0)
InnerEye-DeepLearningby microsoft
Medical Imaging Deep Learning library to train and deploy 3D segmentation models on Azure Machine Learning
InnerEye-DeepLearningby microsoft
Python
494
Version:v0.8
License: Permissive (MIT)
Model training and evaluation
How to train a TensorFlow Object Detection Classifier for multiple object detection on Windows
TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10by EdjeElectronics
Python
2859
Version:Current
License: Permissive (Apache-2.0)
nniby microsoft
An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
nniby microsoft
Python
12981
Version:v3.0rc1
License: Permissive (MIT)
autogluonby awslabs
AutoGluon: AutoML for Image, Text, and Tabular Data
autogluonby awslabs
Python
4341
Version:v0.4.0
License: Permissive (Apache-2.0)
spacy-transformersby explosion
🛸 Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy
spacy-transformersby explosion
Python
1243
Version:v1.2.3
License: Permissive (MIT)
TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Piby EdjeElectronics
A tutorial showing how to train, convert, and run TensorFlow Lite object detection models on Android devices, the Raspberry Pi, and more!
TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Piby EdjeElectronics
Jupyter Notebook
1342
Version:Current
License: Permissive (Apache-2.0)
dist-kerasby cerndb
Distributed Deep Learning, with a focus on distributed training, using Keras and Apache Spark.
dist-kerasby cerndb
Python
615
Version:0.2.1
License: Strong Copyleft (GPL-3.0)
mindinsightby mindspore-ai
A visual dashboard for model tuning.
mindinsightby mindspore-ai
Python
96
Version:Current
License: Permissive (Apache-2.0)