Have something to say?

Tell PB Vision how they could make the product more useful to you.

Completed

Additional Stat- Targeting/Icing- How many balls were hit to each player?

I would like to see stats showing how many times each player hits to each player or player area across the net. This would be helpful. I get annoyed when the other team accuses our team of targeting OR icing out a particular player. In rec play we should be more generous/forgiving. In tournament/league play we should absolutely go to the optimal shot placement regardless of who that player is. Most times, when accused, I really dont feel like targeting/icing was happening. IF it actually happened, it was completely subconscious. My subconscious mind just sees the court/players and suggests the better shot. The “right shot” just happened to be to a player that was out of position or just more vulnerable, regardless of who the player actually was. Conversely, am I the player being iced out or targeted? How can I support a player being targeted? How can I get more involved if I am being iced out? How can I ask my partner for support if I am being targeted? What are the partner strategies?

Jeremy Stout 6 days ago

3

Shot quality should be based on results

Many power users now agree that PBV shot quality puts too much value on power, to the ultimate detriment of their games. Shot quality should be judged by results, not speed. PBV has resisted results-based shot quality on the argument that you can appear to be improving (getting better results) simply by playing against weaker players. Objective criteria normalize the competition. While true in theory, the reality is every shot is context-dependent. The hardest slam or serve is not always the best. A mishit volley is indistinguishable from a drop volley. The difference is that the latter is a winner. PBV matches are self-leveling. There’s no reason to upload your 11-1 match. You won’t learn anything from it. A better approach would be only to process matches 11-6 or closer. Once you know the match is competitive, then judging shot quality by results becomes a much better metric. Did my serve result in weaker-than-average returns for my opponent? Did my 3rd let us move up? Am I winning firefights? Did my setup lead to my partner’s putaway? These are much more salient questions than “did my drive speed reach the PBV 80th percentile?” In our experience, that doesn’t correlate to more Ws.

Alden 25 days ago

2

shot editing v.next

Latest iteration of shot editing. Data quality has come a long way, but it’s not reflected in the app. The JSON schema now has a reliable way of distinguishing a knockback from a serve. A one-shot rally with the winner flag unset indicates a knockback. It allows them to be easily filtered from the results. Furthermore, any rally without the winner flag set is suspicious. In my testing, about 50% of these rallies should be excluded (interrupted by a ball-on, for example), and there may be around 2 per game. There are occasional misattributions, concentrated in stack unwinds. Ball tracking errors are almost exclusively on outdoor recordings, but many of these are also caught in that same suspicious rally filter. If these filters are reliable and already in the data, they should be exposed in the app. Filter out the knockbacks and don’t include them in the stats. For suspicious rallies, simply throw up a pop-up the first time it’s viewed: “This rally looks suspicious. Should we include it in your stats?” Simple yes/no. No fancy shot editing.

Alden 25 days ago

Completed

Brand New Skill Ratings

Six data-backed skills, predictive stats, and drill-down tools that explain your rating and how to improve it. Kitchen Game · Ball Control · Defense V2 · Offense V2 · Court IQ · Targeting After analyzing performance signals across hundreds of thousands of videos, we found that they form more useful groups that better reflect how you play and how you can improve. They also create the foundation for the deeper rating breakdowns we’ve been promising. The useful parts of today’s ratings aren’t disappearing. Serve and return signals will feed Ball Control and Targeting, agility and movement will become part of Kitchen Game, and consistency will be reflected through execution and errors across the new components. The new ratings will arrive first. We’ll then be incrementally adding supporting "drill-down" charts and trend views over time as we validate the signal and build the UI components. More in this section here: https://help.pb.vision/en/help/articles/8216806-pb-vision-skill-ratings#e7wwxmyb5dw

PB Vision Team about 1 month ago

Ability to create folder via API

It would be very helpful for partners with API access to have an API to organize the games within our partner account without having to manually create a folder for each use case. Thought process: Our user uploads a video through our application, which is sent to our PBV partner account. If no folder exists for said user within our PBV partner account, we can create one via an API call, then upload said video to that folder. If a folder does exist for said user already within our PBV partner account, then we just upload that video to that folder. I know when someone uploads them, they can link them to their existing PBV account using their email, but since videos get stored in our partner library, I just want an easy way to organize them all. That way, if we ever need to look through them, we could easily dig down through the folders based on the users within our app.

Chasing Fivezero 3 months ago

1