CCTV AI application for tracking objects in real-time
Role
Full-stack developer
Description of Project
The application actively monitors large networks of cameras and tracks objects in real time throughout the scenes. Advanced trackers and AI detectors are used to maintain a track of every individual, vehicle or object to generate rich and accurate metadata unique to each object in the scene. Live-streamed cameras have certain rules which triggered events. The tracked object's shape, class, appearance, colours, speed and trajectory on a geomap (time and location) are some of the information collected. This information can be used to provide statistical information and support post-event analytics and forensic investigations.
Responsibilities
Backend development
Frontend development
Bug fixing and testing
Code refactoring
Completed tasks:
Improved the low-light facial recognition solution by integrating compatibility with IP cameras. Such a system has proven its effectiveness in crowded environments. In examination mode, the system can be configured to capture and store faces.
Created flexible searches in an existing system based on predefined parameters and images, increased productivity, opened up the potential for new applications and offering a higher degree of personalization.
Pushed logs to Kibana via rabbitMQ
Technology Stack
Java 17, Spring boot, Elasticsearch, Kibana, RabbitMQ, Docker, Jenkins, Spring Security, Websocket, Angular, JUnit5, TestNg
Period
11.2022 —
until now
(1 year 11 months)