# What is Volleyball AI?

Meet VOLL-E

<figure><img src="/files/9THKSATbrZQJUIlXHxfy" alt="" width="250"><figcaption><p>VOLL-E</p></figcaption></figure>

VOLL-E is our AI robot who is in charge of breaking down video, tagging actions and athletes, and helping the Balltime Family one video at a time! VOLL-E was meticulously trained on a vast collection of volleyball footage, covering both beach and indoor variations across all skill levels. This diverse training regimen has equipped VOLL-E with the ability to accurately interpret and analyze the complex dynamics of volleyball games. The exciting part is that VOLL-E continues to evolve, becoming even smarter with each new video it processes!

{% embed url="<https://www.youtube.com/watch?t=1s&v=SMCFIvtXAEk>" %}

Below is a comprehensive list of all the things Voll-E is doing when the magic is happening:

1. Downtime removal
   * The average downtime in a volleyball match is about 67% for indoor, and 65% for beach. We want to make it faster and easier than ever to watch film
2. Actions ID
   * Once the downtime is removed, VOLL-E focuses on identifying the different actions of the game (serve, pass, set, attack, block, dig)
3. Team ID
   * VOLL-E also is identifying what players belong to what team&#x20;
4. Player ID
   * VOLL-E needs to identify all of the individual players on the court in order to use all of the filtering and statistical analysis available on Balltime.

<figure><img src="https://lh7-us.googleusercontent.com/zUdTJSQExJ79yehBocOXzu_fbrkALu_cUs71_j7eqSonsN0JlcH5CdgK6t-pXbCvZ-TR_-j-GE2TybPJZZzzWWnLZYhqrgrW7Xclt9RvSZhGgchXrl95XUfX4qHVRrlomtcius0PNO28EVxL7Ts2a5tsKw=s2048" alt="" width="375"><figcaption></figcaption></figure>

1. Ball Tracking
   * VOLL-E's work on tracking the ball is vital to being able to create Vertical Reels, Trajectories (serve, pass, set, and dig), and capturing speeds of certain actions.

<div align="center"><figure><img src="https://lh7-us.googleusercontent.com/_aNlcJyNR_xhTszSomVgRcrOp_dr1Oz6tAMvb2yh9_d_Frg1D0Ns6sHXFw2DALn-CRpciA0nkTaSjzewSQl4qQUJKJoHpsjsl4MIWECOLI0-oHefxKJnypt3RuYmKC_NudKdbz5z9kNWEXuhN8X_VQquMA=s2048" alt="" width="375"><figcaption></figcaption></figure></div>

6. Ball & player positioning
   * In order to see tendencies and positional data, VOLL-E needs to track where the ball and the players are on the court at all times!

<figure><img src="https://lh7-us.googleusercontent.com/0keldJ-IDCGoQgYrj9uGlfVTzzinvrnsJkrZGsv5Z7LnKOaJacuQcyRAhWF9cFZoU5MK9YmMrCS6Jz_BG2ZDHrDyfT2F4BCVtMMfAqXdI9q86NWTeV2qjVf82GRB_D6CeyDDynoShJWXdUn65WrAk3sMdA=s2048" alt="" width="563"><figcaption></figcaption></figure>

<figure><img src="https://lh7-us.googleusercontent.com/htWKfbyuEb4vdbBfZDUeAz6Lf6A-DeuLI-jc4XlcZK2Ek5knfP9_1EDE1aAzOCyZV-PELL2WQlXoukDjKP7oNxrbu1GOS4zI5hy0KCrnvB1ffaT6AiyT9z7eJx7VtAIsR-e3a-VZp-mWH_3umNoV7PXmaQ=s2048" alt="" width="188"><figcaption><p>DIG TENDENCIES</p></figcaption></figure>

<figure><img src="https://lh7-us.googleusercontent.com/o08adYpi9bF_yjP-JpiZxuEk1mtiwtswbX0uUO8F31vF0ftKmwpK39KYd2Uekr2Vs3P7ZwuyYbec3FEhpsOR7Odg9Uu2UWWqfDPfWcaNYAdUsfwIviCgoCOh-o-5MMM0qSUt3RWn0Nf3nqQTmgZDtdR5qA=s2048" alt="" width="188"><figcaption><p>ATTACK TENDENCIES</p></figcaption></figure>

<figure><img src="https://lh7-us.googleusercontent.com/MsFbqVO9j13cRYMUXZZX4sscnAsrSVjxHJaCO2xHISvLz0KcwQuiLwR-wZwSzDnI6dfK_MQenWd8jLPdsx_lHDVPCzavr70vqJ2IsBZzJDaPT-j9dutGtlDXg2lvDcz8yqg-OOHIwIhDEM7VdNqsgFYP3A=s2048" alt="" width="188"><figcaption><p>ROTATION CHARTS</p></figcaption></figure>

You can learn more about Balltime and what is behind the magic here:

<https://vimeo.com/913736817/d8bfa100c2?share=copy>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://academy.balltime.com/getting-started/what-is-volleyball-ai.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.