CUSTOM SOFTWARE DEVELOPMENT

Benefit from our experience and skills within Artificial Intelligence and Machine Learning domain

VIDEO & AUDIO ANALYTICS ON THE EDGE

We build and manage AI solutions running on the edge devices like cameras of different vendors

AI ON THE EDGE

Video & Audio Analytics solutions

Safety & Compliance
Keep people safe and compliant with on‑device video and audio analytics. Detect missing PPE, anonymise recordings for GDPR, and react to incidents in seconds.

Retail & Logistics
Understand movement of carts, goods and people directly from your cameras. Improve store flow, reduce shrinkage and digitise tracking with on‑camera QR/DMX reading and pallet tracking.

Quality & Manufacturing
Spot micro‑defects, measure and classify products in real time — right on the line. Retrain models on your own samples and keep quality consistent without extra hardware.

Mobility & Public Space
From parking utilisation to passenger counting — get reliable, privacy‑friendly analytics directly on cameras. Trigger actions to improve traffic flow and operations.

Applications



PPE Detection



Shopping cart tracker



QR & Barcode Scanner



Sound analyzer



Parking application



Anonymization application

OUR TECHNOLOGY EXPERTISE

Take advantage of our technological expertise and extensive pool of skilled IT professionals equipped with the latest programming languages, tools and frameworks.

Intelligent automation

End-to-end business process automation Artificial Intelligence and Robotic Process Automation (RPA) Complex data AI analytics

Machine Learning & AI

Neural Networks and Deep Learning Machine Learning Algorithms Real-time visual data processing

Data analytics

Big Data analytics Real-time video analytics Predictive analytics

Cloud Solutions

Cloud applications development Microservices Architecture Cloud solutions for Big Data

CASE STUDIES

Advanced video & audio analytics on the edge

Development and implementation of advanced custom AI analytics on AXIS cameras

Advanced video & audio analytics on the edge

We help our partners create and implement embedded software for non-standard object detection, classification, tracking, and behavioral analysis on edge devices – such as static or vehicle-mounted cameras. For more demanding analyses, we use additional embedded computers to offload part of the tasks. A few examples of objects whose behavior we helped to analyze are airplanes at small airports, trash cans in cities, airport trolleys, cyclists, livestock…

Detecting surface anomalies in industry

Using special illumination and Neural Networks to detect the smallest anomalies

Detecting surface anomalies in industry

An automotive industry client wanted to automate the process of detecting even the smallest defects in the paint coating on car parts. We developed a unique combination of custom made illumination and camera modules with in-house trained convolution neural networks. The whole solution is prepared for on-premises and cloud deployment with the industry standard in mind. We detect and classify several types of surface defects less than 0.1 mm in size with more than 95% accuracy.

Traffic video analytics for SmartCity

Real-time analytics, pattern recognition and anomaly detection

Traffic video analytics for SmartCity

A renowned European system integrator was looking for a software solution for its SmartCity project with special requirements for real-time traffic video data analytics. We were able to customize our software modules and meet all the specific requirements within a short time. We used our extensive expertise to provide specific and precise output traffic data for further use in the customer’s SmartCity platform.

Web platform visual search

Neural network model, microservices and platform integration

Web platform visual search

A furniture aggregator platform was looking to extend their search services with visual search, which allows customers to find similar products just by uploading a photo they have taken or downloaded. We prepared the whole service as a separate microservice for the customer’s Kubernetes infrastructure. The team consisted of two ML experts and two Senior Developers, who completely designed and developed the whole service including the communication model with other already existing services. We worked with the latest architecture designs such as detector, feature vector extractor, approximate nearest neighbor and other services.

NLP document classifier

Analyzing thousands of documents a day, classifying and storing them in a database

NLP document classifier

Our in-house Natural Language Processing (NLP) solution can analyse thousands of documents a day. It determines the type of content in the documents (while respecting their privacy) and can store them in a database according to predefined content types. For example, if you had 10,000 unlabelled documents in one folder, you could use the PDF classifier to sort them into four different folders automatically, without having to open a single PDF.

Voice recognition mobile application

High-precision audio recognition for Android

Voice recognition mobile application

A client was looking for a development partner for an audio recognition project. We were approached to undertake the whole process of mobile application delivery, which included graphical design, development, testing, backend data collection and processing. The application (optimised for Android) utilised TensorFlow Lite proprietary model for audio recognition, which ensured high precision and low latency.

DNN optimization for Facial recognition

High performance inference on NVIDIA GPUs

DNN optimization for Facial recognition

A client specialising in Facial Recognition approached us with a project on optimization of Deep Neural Network (DNN) models for TensorRT to enable high performance inference on NVIDIA GPUs. One of our tasks was finding a balance between computation load and precision for DNN quantization processes. We prepared AI video analytics pipelines with features such as object detection, classification and recognition. These pipelines can be extended by additional DNN approaches (e.g., tracking) and are based on DeepStream SDK with custom GStreamer plugins built by our company.

Sound analyzer for predictive maintenance

An app that can diagnose the problem of a car by analyzing the underlying sounds

Sound analyzer for predictive maintenance

We created an ML engine that analyzes unusual sounds emanating from cars and provides a predictive diagnosis of the issue. It is based on unique classification technology utilizing a custom Densely Connected Convolutional Network, delivering 98% accuracy after training on extremely small data sets of only a few sound samples for each class. The entire solution operates and employs the latest ML services from the Microsoft Azure cloud.

World‘s first diamond selection tool

An automated process of selecting diamonds based on visual appeal and price

World‘s first diamond selection tool

Our solution analyses the visual purity and overall quality of premium diamond stones. To achieve outstanding results we employ hundreds of images for each stone and a spatio-temporal prediction model based on cutting-edge Convolutional Neural Network architectures. The product is a web app virtual assistant that outperforms most of the world’s diamond experts and helps a buyer to select the right balance of quality, visual appeal and price.

Identifying dental problems using a smartphone

Automatic monitoring of patient’s teeth based on a series of photographs

Identifying dental problems using a smartphone

Our client, the owner of a private dental clinic, approached us with a request to automate patient tracking based on a series of photographs of the patient’s face and projections of their jaws taken with a smartphone. The algorithms we developed allowed us to identify some of the most important key elements used in dental diagnostics. The knowledge obtained from each photograph is combined into a single data point, and based on this our system will make a comprehensive diagnosis and offer a treatment plan. The patient can now perform these examinations remotely by himself/herself and send the results to his or her doctor.

AI video analytics for retail

Real-time object detection, tracking and behavioral analysis

AI video analytics for retail

A customer with a long term experience in AI/ML was looking for highly qualified Machine Learning developers experienced in real-time object detection and tracking, as well as behavioral analysis of objects in video feeds from a retail environment. We created an expert team comprising an ML specialist with experience of real-time object detection pipeline, two senior developers with experience in using Nvidia DeepStream SDK principles, and one annotator with experience of preparing ground truth data for ML models. Our team has substantially helped improve current customer solution in terms of performance, reliability and speed of processing.

Process automation

Integration of third party APIs into the customer platform

Process automation

A powerful process automation platform provider was trying to enlarge their development team. Peoly provided them with a managed nearshore development team with experience of integration, RESTful API and JavaScript as well as knowledge of front-end development. After an evaluation period, we were able to qualify as an exclusive partner for the project. The assignment was to integrate 3rd party APIs into the customer platform. Within a couple of months we had expanded a dedicated team of 5 to 15 people with a specific developer profile tailored to the customer needs. Currently, the customer makes use of a wide scope of our services and enjoys access to a team extended on on-demand basis.

Interested in a more detailed description?

REFERENCES

We thank our clients for the trust they place in us. A long-term sincere partnership is what we value the most.

It went much faster than we thought

„Working with peoly helped us to consolidate our internal systems for managing thousands of candidates for recruiting processes for almost 200 of our industrial clients. The partnership allowed us to migrate our systems to one Applicant Tracking System, which peoly designed according to our specific needs in a shorter time than planned.“ M.Sc. Marketa Dlabolova, COO, PolySearch LLC.

Effective Cooperation

“Our cooperation with peoly is very effective. They are capable of delivering the developers we need quite quickly, which is important for us. They are also capable of quickly solving any issues, proving that they are a partner we can rely on.” Ondrej Gazda – Integromat Co-founder & CEO

Strategic importance

“The technology developed by peoly solutions, former GoodAI Solutions, is of strategic importance for us, it is unique in the market and it will allow us to grow our e-commerce business” Rudolf Jániš, CEO @ Sanitino, s.r.o.

High degree of professionalism

“The peoly solutions, former GoodAI Solutions team showed a high degree of professionalism and knowledge since the beginning and guided us in this challenging project delivering a solution to our full satisfaction. Their proactive approach and ideas, mixed with their knowledge of cutting edge technologies, resulted in a solution that allows us to classify each message in 30 seconds instead of minutes, with an estimated savings of 6,000 hours per year. I highly recommend their services and I am looking forward to continuing to work together in the future.” Michael Fried, Co-Founder @The Diamond Pro Ltd.

Innovative proof of concept

“Peoly solutions, former GoodAI Solutions, developed a solution which resulted in sizable savings for GasNet. They succeeded in designing an innovative proof of concept, and then building a production-ready system for automating document processing.“ Radek Starý, Director of Operational Asset Management @ GasNet Czech Republic

Flexibility, adaptability and client centric

“I have had a very positive experience working with Guillermo and Jiri at former GoodAI Solutions, now peoly solutions. They have been adaptive to our needs and worked closely with us to ensure that as the project scope evolved, their ideas did as well. Their flexibility, adaptability and client centric approach is refreshing and I can say that we will continue to work with them in the future because of this. “ Alan White, CEO @ Arriello

Latest News

peoly becomes Technology Integration Partner of Axis Communications

peoly acquires innovative Czech AI company in a strategic merger

Joining the NVIDIA Metropolis Partner program

GO TO ALL NEWS

ABOUT US

We are a Prague-headquartered software company building dedicated development teams, augmenting existing development teams, and providing end-to-end software engineering services. We were able to create local ecosystems of experienced professionals, developers and universities in both countries, which in combination with our own local recruitment company allows us to grow every year. Our team of experienced data analysts, machine learning experts and programmers is always up for a challenge and dedicated to help clients grow and prosper. We partner with: