Vid.Supervisor

Client: Global Online Survey and Insights Pure Play Company

Technology

Azure, Linux, Java SEE Runtime, Spring & Hibernate, Apache Tomcat, JavaScript/Angular.js, Quartz, Apache HTTP Client, JUnit, Jenkins and Apache Maven, Azure IoT Hub, Events Hub, Cosmos DB, Kubernetes, Docker, AWS, Edge Computing, Custom Protocol Gateways.

Solution

Video retail events recognition with local processing and cloud storage

Challenges

Supervising activity without breach of confidentiality

Solution

Vid.Supervisor is a machine-learning model that runs over a video to identify and tag behaviors. Rinf.tech and its partners are working together to develop a solution rooted in the latest Machine Learning and video analytics trends. The main purpose is to vastly decrease the amount of time necessary for codifying a video, while improving the overall accuracy of the process. For a visual map of reaching the end objective, we can take as example the next journey:
  1. System setup, user management, project definition
  2. Uploading videos into the System and defining codebook tags: actions/quantities/locations
  3. Streaming the videos for manual tagging
  4. Generating codebook excels
  5. System proposing values for tags
  6. User confirming/correcting tags
  7. Automated identification of patterns & behavior insight (human review is needed for 100% accuracy)

Key Features
  • Person Detection
  • People Recognition
  • Sewing Videos by: Person, Tag, Location etc.

Methodology

Agile iteration

Results

  • 98% reduction of unrelevant content – cramming 10000 hours of surveilance in 2 hours of relevant footage.
  • high accuracy in task recognition increasing relevance of performance analysis bonus policies.
0 K
Lines of code written
0
Hours of work
0
Team members
(1 Dev, 1 Designer, 1 PM)

Other Similar Projects

Want to work together?

Let’s talk.