Part 2: Detecting Truck Parking Lots on Satellite Images

This post describes a student group project developed within the Data Science Lab undergraduate course of the Vienna University of Economics and Business, co-supervised by Trustbit.

Student project team: Michael Fixl, Josef Hinterleitner, Felix Krause and Adrian Seiß

Supervisors:  Prof. Dr. Axel Polleres (WU Vienna), Dr. Vadim Savenkov (Trustbit)

Introduction

In the previous blog post (which you can find here), we created an already pretty powerful image segmentation model in order to detect the shape of truck parking lots on satellite images. However, we will now try to run the code on new hardware and get even better as well as more robust results.

New hardware and out-of-sample data

Up to now we trained all semantic segmentation models on Google Colab, which is advantageous as this assures everyone can reproduce the project easily but unfortunately the platform partly uses old package versions. In order to check out if the model training can simply be repeated on different hardware, we train the promising semantic segmentation models once again but with the newest package versions and on a high-end computer with an RTX 3090 graphics card. Hereby we can see that there can in fact be some randomness in the results depending on the hardware and packages used.

Let’s also check how robust our model is against more varied data, e.g. coming in different scales or from sources other than OpenStreetMap. Therefore, we made some experiments with unseen truck parking lots from Google Earth with various parking lot positions and sizes. Checking those images with the optimized PSPNet model from the last blog post shows that generalizability is not yet convincing, as you can see below.

Further testing and optimization

To counter the above mentioned issues, we should implement some fixes to reduce the risk of overfitting and check generalizability of the other models. Interestingly, further testing and optimization now shows that the LinkNet architecture turns out to be very precise and much more generalizable than PSPNet. It reaches a mIoU of up to 75% in the test set while also achieving high precision on completely new data with different structure than the train data.

You can find some predictions of this model on unseen parking lots from Google Earth below. Also this model of course fails under certain conditions and does not predict anything or predicts falsely as you can see in the right sample image. If you are interested in more detailed results, you might check out the comparison of the model performance before and after the previously mentioned changes in the table at the end of the blog post. There you can also find the training process of the final LinkNet model.

Conclusion

Overall, in this narrowly defined task the optimized LinkNet model shows decent accuracy and generalizability. Instead of sending expensive workers on site to measure coordinates of unrecorded truck parking lots, this model could be used to get a sometimes rough but at the same time very cheap estimation of the shapes of parking areas. Knowing these, the current activity of a truck can be derived based on GPS signals. This information could then be used to optimize transport operations.

Finally, a small app concludes the project, which is visible in the screenshot above. It simply takes coordinates as input and outputs a prediction mask using the optimized LinkNet model from before.

Additional material

Testing results

*new hardware, code optimization and changes (overfitting fix, newest package versions, etc.)

Training process of final LinkNet model

Contact

Christoph Hasenzagl
TIMETOACT GROUP Österreich GmbHContact
Felix KrauseBlog
Blog

Part 1: Detecting Truck Parking Lots on Satellite Images

Real-time truck tracking is crucial in logistics: to enable accurate planning and provide reliable estimation of delivery times, operators build detailed profiles of loading stations, providing expected durations of truck loading and unloading, as well as resting times. Yet, how to derive an exact truck status based on mere GPS signals?

Rinat AbdullinRinat AbdullinBlog
Blog

Part 1: TIMETOACT Logistics Hackathon - Behind the Scenes

A look behind the scenes of our Hackathon on Sustainable Logistic Simulation in May 2022. This was a hybrid event, running on-site in Vienna and remotely. Participants from 12 countries developed smart agents to control cargo delivery truck fleets in a simulated Europe.

Felix KrauseBlog
Blog

Creating a Cross-Domain Capable ML Pipeline

As classifying images into categories is a ubiquitous task occurring in various domains, a need for a machine learning pipeline which can accommodate for new categories is easy to justify. In particular, common general requirements are to filter out low-quality (blurred, low contrast etc.) images, and to speed up the learning of new categories if image quality is sufficient. In this blog post we compare several image classification models from the transfer learning perspective.

Rinat AbdullinRinat AbdullinBlog
Blog

State of Fast Feedback in Data Science Projects

DSML projects can be quite different from the software projects: a lot of R&D in a rapidly evolving landscape, working with data, distributions and probabilities instead of code. However, there is one thing in common: iterative development process matters a lot.

Felix KrauseBlog
Blog

Boosting speed of scikit-learn regression algorithms

The purpose of this blog post is to investigate the performance and prediction speed behavior of popular regression algorithms, i.e. models that predict numerical values based on a set of input variables.

Referenz
Referenz

Automated Planning of Transport Routes

Efficient transport route planning through automation and seamless integration.

Rinat AbdullinRinat AbdullinBlog
Blog

Machine Learning Pipelines

In this first part, we explain the basics of machine learning pipelines and showcase what they could look like in simple form. Learn about the differences between software development and machine learning as well as which common problems you can tackle with them.

Felix KrauseBlog
Blog

License Plate Detection for Precise Car Distance Estimation

When it comes to advanced driver-assistance systems or self-driving cars, one needs to find a way of estimating the distance to other vehicles on the road.

Rinat AbdullinRinat AbdullinBlog
Blog

Strategic Impact of Large Language Models

This blog discusses the rapid advancements in large language models, particularly highlighting the impact of OpenAI's GPT models.

TIMETOACT
Technologie
Headerbild zu IBM DB2
Technologie

IBM Db2

The IBM Db2database has been established on the market for many years as the leading data warehouse database in addition to its classic use in operations.

TIMETOACT
Referenz
Referenz

Standardized data management creates basis for reporting

TIMETOACT implements a higher-level data model in a data warehouse for TRUMPF Photonic Components and provides the necessary data integration connection with Talend. With this standardized data management, TRUMPF will receive reports based on reliable data in the future and can also transfer the model to other departments.

TIMETOACT
Technologie
Headerbild zu Talend Real-Time Big Data Platform
Technologie

Talend Real-Time Big Data Platform

Talend Big Data Platform simplifies complex integrations so you can successfully use Big Data with Apache Spark, Databricks, AWS, IBM Watson, Microsoft Azure, Snowflake, Google Cloud Platform and NoSQL.

TIMETOACT
Service
Navigationsbild zu Data Science
Service

Data Science, Artificial Intelligence and Machine Learning

For some time, Data Science has been considered the supreme discipline in the recognition of valuable information in large amounts of data. It promises to extract hidden, valuable information from data of any structure.

TIMETOACT
Technologie
Headerbild zu IBM Decision Optimization
Technologie

Decision Optimization

Mathematical algorithms enable fast and efficient improvement of partially contradictory specifications. As an integral part of the IBM Data Science platform "Cloud Pak for Data" or "IBM Watson Studio", decision optimisation has been decisively expanded and embedded in the Data Science process.

TIMETOACT
Technologie
Headerbild Talend Application Integration
Technologie

Talend Application Integration / ESB

With Talend Application Integration, you create a service-oriented architecture and connect, broker & manage your services and APIs in real time.

TIMETOACT
Technologie
Headerbild für IBM SPSS
Technologie

IBM SPSS Modeler

IBM SPSS Modeler is a tool that can be used to model and execute tasks, for example in the field of Data Science and Data Mining, via a graphical user interface.

TIMETOACT
Technologie
Headerbild zu IBM Watson Studio
Technologie

IBM Watson Studio

IBM Watson Studio is an integrated solution for implementing a data science landscape. It helps companies to structure and simplify the process from exploratory analysis to the implementation and operationalisation of the analysis processes.

TIMETOACT
Technologie
Headerbild IBM Cloud Pak for Data
Technologie

IBM Cloud Pak for Data

The Cloud Pak for Data acts as a central, modular platform for analytical use cases. It integrates functions for the physical and virtual integration of data into a central data pool - a data lake or a data warehouse, a comprehensive data catalogue and numerous possibilities for (AI) analysis up to the operational use of the same.

TIMETOACT
Service
Headerbild zu Operationalisierung von Data Science (MLOps)
Service

Operationalization of Data Science (MLOps)

Data and Artificial Intelligence (AI) can support almost any business process based on facts. Many companies are in the phase of professional assessment of the algorithms and technical testing of the respective technologies.

TIMETOACT
Service
Headerbild zu Dashboards und Reports
Service

Dashboards & Reports

The discipline of Business Intelligence provides the necessary means for accessing data. In addition, various methods have developed that help to transport information to the end user through various technologies.

TIMETOACT
Service
Headerbild zu Digitale Planung, Forecasting und Optimierung
Service

Demand Planning, Forecasting and Optimization

After the data has been prepared and visualized via dashboards and reports, the task is now to use the data obtained accordingly. Digital planning, forecasting and optimization describes all the capabilities of an IT-supported solution in the company to support users in digital analysis and planning.

Daniel WellerBlog
Blog

Revolutionizing the Logistics Industry

As the logistics industry becomes increasingly complex, businesses need innovative solutions to manage the challenges of supply chain management, trucking, and delivery. With competitors investing in cutting-edge research and development, it is vital for companies to stay ahead of the curve and embrace the latest technologies to remain competitive. That is why we introduce the TIMETOACT Logistics Simulator Framework, a revolutionary tool for creating a digital twin of your logistics operation.

Sebastian BelczykBlog
Blog

Building and Publishing Design Systems | Part 2

Learn how to build and publish design systems effectively. Discover best practices for creating reusable components and enhancing UI consistency.

Ian RussellIan RussellBlog
Blog

So, I wrote a book

Join me as I share the story of writing a book on F#. Discover the challenges, insights, and triumphs along the way.

TIMETOACT
Technologie
Headerbild zu IBM DataStage
Technologie

IBM InfoSphere Information Server

IBM Information Server is a central platform for enterprise-wide information integration. With IBM Information Server, business information can be extracted, consolidated and merged from a wide variety of sources.

TIMETOACT
Technologie
Headerbild zu IBM Netezza Performance Server
Technologie

IBM Netezza Performance Server

IBM offers Database technology for specific purposes in the form of appliance solutions. In the Data Warehouse environment, the Netezza technology, later marketed under the name "IBM PureData for Analytics", is particularly well known.

TIMETOACT
Technologie
Headerbild zu IBM Watson® Knowledge Catalog
Technologie

IBM Watson® Knowledge Catalog/Information Governance Catalog

Today, "IGC" is a proprietary enterprise cataloging and metadata management solution that is the foundation of all an organization's efforts to comply with rules and regulations or document analytical assets.

TIMETOACT
Technologie
Headerbild zu IBM Cloud Pak for Automation
Technologie

IBM Cloud Pak for Automation

The IBM Cloud Pak for Automation helps you automate manual steps on a uniform platform with standardised interfaces. With the Cloud Pak for Business Automation, the entire life cycle of a document or process can be mapped in the company.

TIMETOACT
Technologie
Haderbild zu IBM Cloud Pak for Application
Technologie

IBM Cloud Pak for Application

The IBM Cloud Pak for Application provides a solid foundation for developing, deploying and modernising cloud-native applications. Since agile working is essential for a faster release cycle, ready-made DevOps processes are used, among other things.

TIMETOACT
Technologie
Headerbild zu Talend Data Fabric
Technologie

Talend Data Fabric

The ultimate solution for your data needs – Talend Data Fabric includes everything your (Data Integration) heart desires and serves all integration needs relating to applications, systems and data.

TIMETOACT
Technologie
Headerbild Talend Data Integration
Technologie

Talend Data Integration

Talend Data Integration offers a highly scalable architecture for almost any application and any data source - with well over 900 connectors from cloud solutions like Salesforce to classic on-premises systems.

TIMETOACT
Service
Navigationsbild zu Business Intelligence
Service

Business Intelligence

Business Intelligence (BI) is a technology-driven process for analyzing data and presenting usable information. On this basis, sound decisions can be made.

TIMETOACT
Service
Header Konnzeption individueller Business Intelligence Lösungen
Service

Conception of individual Analytics and Big Data solutions

We determine the best approach to develop an individual solution from the professional, role-specific requirements – suitable for the respective situation!

Rinat AbdullinRinat AbdullinBlog
Blog

Let's build an Enterprise AI Assistant

In the previous blog post we have talked about basic principles of building AI assistants. Let’s take them for a spin with a product case that we’ve worked on: using AI to support enterprise sales pipelines.

Aqeel AlazreeBlog
Blog

Part 1: Data Analysis with ChatGPT

In this new blog series we will give you an overview of how to analyze and visualize data, create code manually and how to make ChatGPT work effectively. Part 1 deals with the following: In the data-driven era, businesses and organizations are constantly seeking ways to extract meaningful insights from their data. One powerful tool that can facilitate this process is ChatGPT, a state-of-the-art natural language processing model developed by OpenAI. In Part 1 pf this blog, we'll explore the proper usage of data analysis with ChatGPT and how it can help you make the most of your data.

Nina DemuthBlog
Blog

They promised it would be the next big thing!

Haven’t we all been there? We have all been promised by teachers, colleagues or public speakers that this or that was about to be the next big thing in tech that would change the world as we know it.

Rinat AbdullinRinat AbdullinBlog
Blog

Innovation Incubator Round 1

Team experiments with new technologies and collaborative problem-solving: This was our first round of the Innovation Incubator.

Felix KrauseBlog
Blog

AIM Hackathon 2024: Sustainability Meets LLMs

Focusing on impactful AI applications, participants addressed key issues like greenwashing detection, ESG report relevance mapping, and compliance with the European Green Deal.

Ian RussellIan RussellBlog
Blog

Introduction to Functional Programming in F# – Part 2

Explore functions, types, and modules in F#. Enhance your skills with practical examples and insights in this detailed guide.

Laura GaetanoBlog
Blog

5 lessons from running a (remote) design systems book club

Last year I gifted a design systems book I had been reading to a friend and she suggested starting a mini book club so that she’d have some accountability to finish reading the book. I took her up on the offer and so in late spring, our design systems book club was born. But how can you make the meetings fun and engaging even though you're physically separated? Here are a couple of things I learned from running my very first remote book club with my friend!

Rinat AbdullinRinat AbdullinBlog
Blog

Inbox helps to clear the mind

I hate distractions. They can easily ruin my day when I'm in the middle of working on a cool project. They do that by overloading my mind, buzzing around inside me, and just making me tired. Even though we can think about several things at once, we can only do one thing at a time.

Aqeel AlazreeBlog
Blog

Part 4: Save Time and Analyze the Database File

ChatGPT-4 enables you to analyze database contents with just two simple steps (copy and paste), facilitating well-informed decision-making.

Ian RussellIan RussellBlog
Blog

Introduction to Web Programming in F# with Giraffe – Part 2

In this series we are investigating web programming with Giraffe and the Giraffe View Engine plus a few other useful F# libraries.

Rinat AbdullinRinat AbdullinBlog
Blog

LLM Performance Series: Batching

Beginning with the September Trustbit LLM Benchmarks, we are now giving particular focus to a range of enterprise workloads. These encompass the kinds of tasks associated with Large Language Models that are frequently encountered in the context of large-scale business digitalization.

Rinat AbdullinRinat AbdullinBlog
Blog

So You are Building an AI Assistant?

So you are building an AI assistant for the business? This is a popular topic in the companies these days. Everybody seems to be doing that. While running AI Research in the last months, I have discovered that many companies in the USA and Europe are building some sort of AI assistant these days, mostly around enterprise workflow automation and knowledge bases. There are common patterns in how such projects work most of the time. So let me tell you a story...

Aqeel AlazreeBlog
Blog

Part 3: How to Analyze a Database File with GPT-3.5

In this blog, we'll explore the proper usage of data analysis with ChatGPT and how you can analyze and visualize data from a SQLite database to help you make the most of your data.

Christian FolieBlog
Blog

The Power of Event Sourcing

This is how we used Event Sourcing to maintain flexibility, handle changes, and ensure efficient error resolution in application development.

Daniel PuchnerBlog
Blog

How we discover and organise domains in an existing product

Software companies and consultants like to flex their Domain Driven Design (DDD) muscles by throwing around terms like Domain, Subdomain and Bounded Context. But what lies behind these buzzwords, and how these apply to customers' diverse environments and needs, are often not as clear. As it turns out it takes a collaborative effort between stakeholders and development team(s) over a longer period of time on a regular basis to get them right.

Christian FolieBlog
Blog

Running Hybrid Workshops

When modernizing or building systems, one major challenge is finding out what to build. In Pre-Covid times on-site workshops were a main source to get an idea about ‘the right thing’. But during Covid everybody got used to working remotely, so now the question can be raised: Is it still worth having on-site, physical workshops?

Christian FolieBlog
Blog

Designing and Running a Workshop series: An outline

Learn how to design and execute impactful workshops. Discover tips, strategies, and a step-by-step outline for a successful workshop series.

Ian RussellIan RussellBlog
Blog

Introduction to Functional Programming in F# – Part 3

Dive into F# data structures and pattern matching. Simplify code and enhance functionality with these powerful features.

Daniel PuchnerBlog
Blog

How to gather data from Miro

Learn how to gather data from Miro boards with this step-by-step guide. Streamline your data collection for deeper insights.

Christian FolieBlog
Blog

Designing and Running a Workshop series: The board

In this part, we discuss the basic design of the Miro board, which will aid in conducting the workshops.

Nina DemuthBlog
Blog

7 Positive effects of visualizing the interests of your team

Interests maps unleash hidden potentials and interests, but they also make it clear which topics are not of interest to your colleagues.

Rinat AbdullinRinat AbdullinBlog
Blog

Innovation Incubator at TIMETOACT GROUP Austria

Discover how our Innovation Incubator empowers teams to innovate with collaborative, week-long experiments, driving company-wide creativity and progress.

Chrystal LantnikBlog
Blog

CSS :has() & Responsive Design

In my journey to tackle a responsive layout problem, I stumbled upon the remarkable benefits of the :has() pseudo-class. Initially, I attempted various other methods to resolve the issue, but ultimately, embracing the power of :has() proved to be the optimal solution. This blog explores my experience and highlights the advantages of utilizing the :has() pseudo-class in achieving flexible layouts.

Aqeel AlazreeBlog
Blog

Part 2: Data Analysis with powerful Python

Analyzing and visualizing data from a SQLite database in Python can be a powerful way to gain insights and present your findings. In Part 2 of this blog series, we will walk you through the steps to retrieve data from a SQLite database file named gold.db and display it in the form of a chart using Python. We'll use some essential tools and libraries for this task.

Rinat AbdullinRinat AbdullinBlog
Blog

Using NLP libraries for post-processing

Learn how to analyse sticky notes in miro from event stormings and how this analysis can be carried out with the help of the spaCy library.

Ian RussellIan RussellBlog
Blog

Introduction to Functional Programming in F# – Part 8

Discover Units of Measure and Type Providers in F#. Enhance data management and type safety in your applications with these powerful tools.

Laura GaetanoBlog
Blog

My Weekly Shutdown Routine

Discover my weekly shutdown routine to enhance productivity and start each week fresh. Learn effective techniques for reflection and organization.

Ian RussellIan RussellBlog
Blog

Introduction to Functional Programming in F# – Part 6

Learn error handling in F# with option types. Improve code reliability using F#'s powerful error-handling techniques.

Ian RussellIan RussellBlog
Blog

Introduction to Functional Programming in F# – Part 5

Master F# asynchronous workflows and parallelism. Enhance application performance with advanced functional programming techniques.

Rinat AbdullinRinat AbdullinBlog
Blog

Consistency and Aggregates in Event Sourcing

Learn how we ensures data consistency in event sourcing with effective use of aggregates, enhancing system reliability and performance.

Matus ZilinskyBlog
Blog

Creating a Social Media Posts Generator Website with ChatGPT

Using the GPT-3-turbo and DALL-E models in Node.js to create a social post generator for a fictional product can be really helpful. The author uses ChatGPT to create an API that utilizes the openai library for Node.js., a Vue component with an input for the title and message of the post. This article provides step-by-step instructions for setting up the project and includes links to the code repository.

Rinat AbdullinRinat AbdullinBlog
Blog

Learning + Sharing at TIMETOACT GROUP Austria

Discover how we fosters continuous learning and sharing among employees, encouraging growth and collaboration through dedicated time for skill development.

Sebastian BelczykBlog
Blog

Building a micro frontend consuming a design system | Part 3

In this blopgpost, you will learn how to create a react application that consumes a design system.

Nina DemuthBlog
Blog

From the idea to the product: The genesis of Skwill

We strongly believe in the benefits of continuous learning at work; this has led us to developing products that we also enjoy using ourselves. Meet Skwill.

Rinat AbdullinRinat AbdullinBlog
Blog

The Intersection of AI and Voice Manipulation

The advent of Artificial Intelligence (AI) in text-to-speech (TTS) technologies has revolutionized the way we interact with written content. Natural Readers, standing at the forefront of this innovation, offers a comprehensive suite of features designed to cater to a broad spectrum of needs, from personal leisure to educational support and commercial use. As we delve into the capabilities of Natural Readers, it's crucial to explore both the advantages it brings to the table and the ethical considerations surrounding voice manipulation in TTS technologies.

Blog
Blog

SAM Wins First Prize at AIM Hackathon

The winning team of the AIM Hackathon, nexus. Group AI, developed SAM, an AI-powered ESG reporting platform designed to help companies streamline their sustainability compliance.

Aqeel AlazreeBlog
Blog

Database Analysis Report

This report comprehensively analyzes the auto parts sales database. The primary focus is understanding sales trends, identifying high-performing products, Analyzing the most profitable products for the upcoming quarter, and evaluating inventory management efficiency.

Sebastian BelczykBlog
Blog

Composite UI with Design System and Micro Frontends

Discover how to create scalable composite UIs using design systems and micro-frontends. Enhance consistency and agility in your development process.

Laura GaetanoBlog
Blog

Using a Skill/Will matrix for personal career development

Discover how a Skill/Will Matrix helps employees identify strengths and areas for growth, boosting personal and professional development.

Blog
Blog

Second Place - AIM Hackathon 2024: Trustpilot for ESG

The NightWalkers designed a scalable tool that assigns trustworthiness scores based on various types of greenwashing indicators, including unsupported claims and inaccurate data.

Ian RussellIan RussellBlog
Blog

Introduction to Web Programming in F# with Giraffe – Part 1

In this series we are investigating web programming with Giraffe and the Giraffe View Engine plus a few other useful F# libraries.

Daniel PuchnerBlog
Blog

Make Your Value Stream Visible Through Structured Logging

Boost your value stream visibility with structured logging. Improve traceability and streamline processes in your software development lifecycle.

Rinat AbdullinRinat AbdullinBlog
Blog

5 Inconvenient Questions when hiring an AI company

This article discusses five questions you should ask when buying an AI. These questions are inconvenient for providers of AI products, but they are necessary to ensure that you are getting the best product for your needs. The article also discusses the importance of testing the AI system on your own data to see how it performs.

Blog
Blog

Third Place - AIM Hackathon 2024: The Venturers

ESG reports are often filled with vague statements, obscuring key facts investors need. This team created an AI prototype that analyzes these reports sentence-by-sentence, categorizing content to produce a "relevance map".

Jonathan ChannonBlog
Blog

Tracing IO in .NET Core

Learn how we leverage OpenTelemetry for efficient tracing of IO operations in .NET Core applications, enhancing performance and monitoring.

Rinat AbdullinRinat AbdullinBlog
Blog

Announcing Domain-Driven Design Exercises

Interested in Domain Driven Design? Then this DDD exercise is perfect for you!

Rinat AbdullinRinat AbdullinBlog
Blog

Event Sourcing with Apache Kafka

For a long time, there was a consensus that Kafka and Event Sourcing are not compatible with each other. So it might look like there is no way of working with Event Sourcing. But there is if certain requirements are met.

Blog
Blog

My Workflows During the Quarantine

The current situation has deeply affected our daily lives. However, in retrospect, it had a surprisingly small impact on how we get work done at TIMETOACT GROUP Austria.

Jörg EgretzbergerJörg EgretzbergerBlog
Blog

8 tips for developing AI assistants

AI assistants for businesses are hype, and many teams were already eagerly and enthusiastically working on their implementation. Unfortunately, however, we have seen that many teams we have observed in Europe and the US have failed at the task. Read about our 8 most valuable tips, so that you will succeed.