Tuesday, April 13, 2021
  • Setup menu at Appearance » Menus and assign menu to Top Bar Navigation
Advertisement
  • AI Development
    • Artificial Intelligence
    • Machine Learning
    • Neural Networks
    • Learn to Code
  • Data
    • Blockchain
    • Big Data
    • Data Science
  • IT Security
    • Internet Privacy
    • Internet Security
  • Marketing
    • Digital Marketing
    • Marketing Technology
  • Technology Companies
  • Crypto News
No Result
View All Result
NikolaNews
  • AI Development
    • Artificial Intelligence
    • Machine Learning
    • Neural Networks
    • Learn to Code
  • Data
    • Blockchain
    • Big Data
    • Data Science
  • IT Security
    • Internet Privacy
    • Internet Security
  • Marketing
    • Digital Marketing
    • Marketing Technology
  • Technology Companies
  • Crypto News
No Result
View All Result
NikolaNews
No Result
View All Result
Home Data Science

Deep Learning for Autonomous Driving: A Breakthrough in Urban Navigation

April 6, 2021
in Data Science
Deep Learning for Autonomous Driving: A Breakthrough in Urban Navigation
585
SHARES
3.3k
VIEWS
Share on FacebookShare on Twitter

‘

Autonomous vehicle’ is a buzzword that’s been circulating in recent decades. However, the development of such a vehicle has posed a significant challenge for automotive manufacturers. This article describes how deep learning autonomous driving and navigation can help to turn the concept into a long-awaited reality.

You might also like

Trends in custom software development in 2021

Epoch and Map of the Energy Transition through the Consensus Validator

NetSuite ERP ushering a digital era for SMEs

The low-touch economy in a post-pandemic world is driving the introduction of autonomous technologies that can satisfy our need for contactless interactions. Whether it’s self-driving vehicles delivering groceries or medicines or robo-taxis driving us to our desired destinations, there’s never been a bigger demand for autonomy.

Self-driving vehicles have six different levels of autonomy, from drivers being in full control to full automation. According to Statista, the market for autonomous vehicles in levels 4 and 5 will reach $60 billion by 2030. The same research indicates that 73% of the total number of cars on our roads will have at least some level of autonomy before fully autonomous vehicles are introduced.

Countries and automobile companies around the world are working on bringing a higher level of unmanned driving to a wider audience. South Korea has recently announced it is to invest around $1 billion in autonomous vehicle technologies and introduce a level 4 car by 2027.

Machine learning and deep learning are among other technologies that enable more sophisticated autonomous vehicles. Applications of deep learning techniques in self-driving cars include:

  • Scene classification
  • Path planning
  • Scene understanding
  • Lane and traffic sign recognition
  • Obstacle and pedestrian detection
  • Motion control

Deep learning for autonomous navigation

Deep learning methods can help to address the challenges of perception and navigation in autonomous vehicle manufacturing. When a driver navigates between two locations, they drive using their knowledge of the road, how streets look like and traffic lights, etc. It is a simple task for a human driver, but quite a challenge for an autonomous vehicle.

Here at ELEKS, we’ve created a demo model that can help vehicles to navigate the environment as humans already do – using eyesight and previous knowledge. We came up with a solution that offers autonomous navigation without GPS and vehicle telemetry by using modern deep learning methods and other data science possibilities.

We used only an on-dash camera and street view dataset of the city of Lviv, Ukraine; we used no GPS or sensors. Below is an overview of the techniques applied and our key findings.

1. Image segmentation task

We used a Cityscapes dataset with 19 classes, which focuses on buildings, road, signs, etc., and an already trained model from DeepLab. The model we used is based on Xception inference. Other models with different maps/IoUs are also available.

Final layers were the semantic probabilities — mostly dim ~ classes*output_image_dims (without channels), so they could be filtered and become the inference to similarity model. It is recommended to transform them into the embedding layer or find a more suitable layer before the outputs. However, even after transformation objects position (higher or lower) on the frame and distance to it, may have influenced the embedding robustness.

Deep Learning for Autonomous Driving

Deep Learning for Autonomous Driving

2. Gathering additional data and labelling

We then downloaded raw photos from the web of the streets, road names and locations (coordinates, etc.), and we also got the Street View API key for download. We added labels in semi-automated ways based on the names and locations and verified them manually. We created pairs of images for similarity model training.

Deep Learning for Autonomous Driving

Finally, we used the image augmentation (also adding photos of different times of day and seasons) and image labelling using model (for example, additional negative samples, which the model recognizes as similar, but they are not located on the one street (GPS, street names, etc.)). As a result, we created a dataset containing approximately 8-12K augmented images.

Deep Learning for Autonomous Driving

3. Similarity models ideation and validation

We tested a few streets view comparison approaches from classical descriptor and template matching to modern SOTA DL algorithms like QATM. The most accurate was the inference model with representation for each segmented image in a pair, like VGG, ResNet or efficientNet and binary classifier (xgb or rf). Validated accuracy equals to approximately 82.5% (whether the right street was found or not), taking into account Lviv’s most known streets between 2011 and 2019 and with augmentation (changing image shapes, lightning, etc).

Similarity models ideation and validation

Deep Learning for Autonomous Driving

Deep Learning for Autonomous Driving

4. Outcome and performance features

We segmented every tenth frame, which was helpful for near real-time calculation, and because there would not be any huge changes in the environment in the space of 10 frames (1/3 s). Then, DeepLab models have shown >70 mIoU (Cityscapes, third semantic mat – buildings), time for prediction – CPU 15s-more than 10m based on Xception, GPU ~ <1s.

The similarity prediction was equal to 1min per 100 pairs (inference on GPU (4Gb VRAM) + classifier on 6 CPU cores). It can be optimised, after the first estimated positions, by limiting search only to closer street views, because the vehicle can’t appear more than 1 km in 10-50 frames.

Not all of the city’s streets were covered, so we found videos with a drive around the city centre. For the map positioning, we used wiki maps; however, other maps can be used if needed. We got the vehicle coordinates from street image metadata (lat/long, street name).

Some streets segments are available in a few different versions — the same location in 2011, 2015 or 2019 and photos from different sources, etc., so the classifier can find any of them. We used mostly weak affine transformations for the street’s augmentation with no flipping or strong colour and shape changes.

Some of the estimations may be inaccurate for the following reasons:

  • Street and road estimation – the static object area is low, street noise is quite high (vehicles, pedestrians) or seasonality changes (trees, snow, rain, etc.)
  • Vehicle position and speed errors – the same street position and different street step or Euclidean distance for curved streets can be viewed with a different focus (distance to an object), etc.

You can check out a video sample of prerecorded navigation with post-processing here.

Want to learn more about our demo? We will be happy to answer your questions!

Originally published at ELEKS Labs blog. 


Credit: Data Science Central By: Olha Zhydik

Previous Post

Why machine learning, not artificial intelligence, is the right way forward for data science

Next Post

Self-Learning, Self-Evolving Smart Quantum Technologies for Secure Communication

Related Posts

Trends in custom software development in 2021
Data Science

Trends in custom software development in 2021

April 13, 2021
Epoch and Map of the Energy Transition through the Consensus Validator
Data Science

Epoch and Map of the Energy Transition through the Consensus Validator

April 13, 2021
NetSuite ERP ushering a digital era for SMEs
Data Science

NetSuite ERP ushering a digital era for SMEs

April 12, 2021
Orphaned Analytics: The Great Destroyers of Economic Value
Data Science

Orphaned Analytics: The Great Destroyers of Economic Value

April 12, 2021
An overview of Augmented reality applications and their future impact on AI
Data Science

An overview of Augmented reality applications and their future impact on AI

April 12, 2021
Next Post
Self-Learning, Self-Evolving Smart Quantum Technologies for Secure Communication

Self-Learning, Self-Evolving Smart Quantum Technologies for Secure Communication

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Recommended

Plasticity in Deep Learning: Dynamic Adaptations for AI Self-Driving Cars

Plasticity in Deep Learning: Dynamic Adaptations for AI Self-Driving Cars

January 6, 2019
Microsoft, Google Use Artificial Intelligence to Fight Hackers

Microsoft, Google Use Artificial Intelligence to Fight Hackers

January 6, 2019

Categories

  • Artificial Intelligence
  • Big Data
  • Blockchain
  • Crypto News
  • Data Science
  • Digital Marketing
  • Internet Privacy
  • Internet Security
  • Learn to Code
  • Machine Learning
  • Marketing Technology
  • Neural Networks
  • Technology Companies

Don't miss it

Trends in custom software development in 2021
Data Science

Trends in custom software development in 2021

April 13, 2021
A.I. For Raspberry Pi Pico: Uctronics TinyML Learning Kit Review
Machine Learning

A.I. For Raspberry Pi Pico: Uctronics TinyML Learning Kit Review

April 13, 2021
BERT Transformers — How Do They Work? | by James Montantes | Apr, 2021
Neural Networks

BERT Transformers — How Do They Work? | by James Montantes | Apr, 2021

April 13, 2021
Bug bounties: More hackers are spotting vulnerabilities across web, mobile and IoT
Internet Security

Critical security alert: If you haven’t patched this old VPN vulnerability, assume your network is compromised

April 13, 2021
Epoch and Map of the Energy Transition through the Consensus Validator
Data Science

Epoch and Map of the Energy Transition through the Consensus Validator

April 13, 2021
Bitcoin mining in China could threaten climate policies, new study shows
Blockchain

Bitcoin mining in China could threaten climate policies, new study shows

April 13, 2021
NikolaNews

NikolaNews.com is an online News Portal which aims to share news about blockchain, AI, Big Data, and Data Privacy and more!

What’s New Here?

  • Trends in custom software development in 2021 April 13, 2021
  • A.I. For Raspberry Pi Pico: Uctronics TinyML Learning Kit Review April 13, 2021
  • BERT Transformers — How Do They Work? | by James Montantes | Apr, 2021 April 13, 2021
  • Critical security alert: If you haven’t patched this old VPN vulnerability, assume your network is compromised April 13, 2021

Subscribe to get more!

© 2019 NikolaNews.com - Global Tech Updates

No Result
View All Result
  • AI Development
    • Artificial Intelligence
    • Machine Learning
    • Neural Networks
    • Learn to Code
  • Data
    • Blockchain
    • Big Data
    • Data Science
  • IT Security
    • Internet Privacy
    • Internet Security
  • Marketing
    • Digital Marketing
    • Marketing Technology
  • Technology Companies
  • Crypto News

© 2019 NikolaNews.com - Global Tech Updates