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.

A customer with a long term experience in AI/ML (bylo ML/AI) 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 (detection model, transfer learning, tracking, behavioral analysis), two senior developers with experience of real-time object detection pipeline and 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.

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.

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.

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.

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.

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.

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.

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.

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. 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 plane. The patient can perform these examinations remotely by himself and send the results to his doctor.

Our client wanted to be able to retrieve various data from video cameras on pig farms. How often they go out to drink/eat, how active they are and conversely how often they rest, how much they weigh and how much they should weigh or even whether they are moving odd, potentialy because they might be sick – to separate it from the others and prevent the spread of a possible disease. In order for us to determine those things correcctly, the system must be able to distinguish individual pigs from each other, whether they are standing or lying down, whether they are feeding or just staying near the trough, whether they are sleeping or just resting etc.

A client form automotive industry wanted to automate the process of detecting even the smallest defects in 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-prem 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.