Illustration
Results
1.5K users per mounth
65 games
AI for image recognition
Project
Project

Partner's Profile

Background
The customer (NDA protected) organized cycling and hiking photo quests all over the world. The creation of each quest was preceded by a long labor-intensive preparation of paper cards with tasks. The organizers developed their own AI image recognition model and needed a contractor to implement this model into the application and digitize the games.

Goal
To develop a mobile app for players of the sports and entertainment game — photo quests. The app should help players to pass photo tasks from the quest due to the built-in image recognition algorithm.

Solution

Our team and the partner's developers implemented a user-friendly mobile application for Android. It allows players to quickly complete photo quest tasks along various routes. Being in the desired location during the game, according to the photo task, the player points the camera of his smartphone at the desired object. If the app recognizes the object, the task is successfully completed.

This mobile app also greatly simplified the game creation process.

Location Map

The application provides a detailed map with the game locations. The games can take place not only in the streets of the city but also on rough terrain, in remote villages.

Image recognition algorithm

Thanks to the real-time image recognition system, players are able to quickly perform photo quests in just a few seconds.

Player Profile

All of a player's achievements — in current and past games — are collected in his profile. Player ratings are compiled based on these data.

Ability to create teams

The player can send an invitation to a particular game to his friends in the application, create a team and pass the quests together.

Different types of quests

Walking and cycling quests are available by default.

List of routes

The player can choose the most attractive routes, for which he gets points by completing photo tasks.

Technologies

Backend

Java, Android SDK

Frontend

JavaScript, jQuery, HTML5

Integrations

PostgreSQL, Celery

Project

Projects

AIMCP

AI Avatar Videos and MCP Server for Astrology Media

Horoscope Reels voiced by three AI personas, plus an MCP server that gives LLM agents exact astrological calculations.

58 finished Reels produced by the pipeline
~20 min from date and signs to a ready Reel, hands-off
0 code changes to launch a new AI persona

APISaaS

API-First Platform for Delivering Music Releases to Streaming Stores

Delivery core for record labels with exactly-once submission and tenant isolation; the first real release went live in 21 of 21 stores.

21/21 stores received the first real release
<8 wks from kickoff to the first live release
2 delivery providers behind one adapter contract

AIVideo Localization

AI Video Localization into 17 Languages Without Re-Rendering

Language variants for AI-generated short story videos: translated, re-voiced and fitted to the existing visuals.

17 languages from one finished video
4–20× cheaper than a dubbing API, by the team’s estimate
1 click to generate every language variant

SMPL3D

Virtual Try-On Room with SMPL Anthropometry

fit clothing onto SMPL models.

ML enabled solution
3D models are based on skinning and shape blending

SaaSDigital Transformation

SaaS for Gyms — Gymistration

for the ultimate sports business management.

5 months to launch
$90K monthly fees paid

MVPAPI

MVP of Astrology App — Starmantic

for personalized horoscope from astrology enthusiasts

4 months to MVP launch
1.9K active users
$6.6Kincome monthly

Need a project estimate?

Drop us a line, and we provide you with a qualified consultation.

x

Partnership That Works for You

Your Trusted Agency for Digital Transformation and Custom Software Innovation.

Start typing to search...