Computer Vision - Internship

Selected intern's day-to-day responsibilities include:

1\. Model development: Researching, training, and fine-tuning deep learning

models for object detection (players, sports equipment), tracking, and action

recognition using frameworks like PyTorch or TensorFlow.

2\. Video analytics: Working on algorithms for automated event detection

(e.g., goals, boundaries, wickets) to facilitate auto-highlight generation.

3\. OCR & data extraction: Implementing Optical Character Recognition (OCR) to

read scoreboards and game clocks from video feeds.

4\. Optimization: Optimizing computer vision pipelines for real-time

performance on cloud and edge devices.

5\. Data management: Assisting in collecting, cleaning, and annotating sports

datasets to improve model accuracy.

6\. Collaboration: Working closely with the backend and product teams to

integrate CV models into the SportVot Cloud Studio and OTT platforms.