Computer Vision.
Markerless capture, pose estimation and the error bars vendors leave out.
Articles
0
Quick Takes
0
Videos
0Soon
Podcasts
0Soon
Clarity Index
—Soon
Followers
—Soon
Markerless capture promises lab-grade measurement from ordinary cameras. It is improving fast, and the error bars are still large enough that pretending otherwise would be an error of its own.
What this field actually measures
- Keypoint error
Distance between estimated and true joint position.
ReferenceReported in millimetres against marker-based reference systems; degrades with occlusion.
- Occlusion robustness
Accuracy when a limb or player is hidden.
ReferenceThe dominant failure mode in crowded team-sport footage.
- Frame rate
Capture speed of the source video.
ReferenceBroadcast rates are often too low to resolve fast joint kinematics reliably.
Evidence & metrics
The published work behind the numbers above, and the public datasets you can open to check us. If a claim can’t be traced here, we don’t print it.
Citations
ImageNet large scale visual recognition challenge
Russakovsky et al. — International Journal of Computer Vision · 2015
Documents the benchmark and the human error baseline against which vision models are compared.
OpenPose / markerless pose estimation validation
Cao et al. — CVPR; plus sports-science validation studies · 2017–2021
Markerless pose estimation is usable for gross kinematics but still trails marker-based capture on joint-angle precision.
Datasets
COCO Consortium · free
Annotated human keypoints across 200k+ labelled images.
Human3.6M / open pose benchmarks
Academic consortia · registration
Ground-truth 3D motion capture paired with video for accuracy testing.
Still open
- When does markerless capture reach clinical-grade reliability?
- How should automated tracking errors be disclosed in public analysis?
- What consent framework should govern automated athlete measurement?
What we won’t say
We will not treat a pose-estimation overlay as a measurement without its error range.
- VO-1Evidence before wit
- VO-2Punch at claims, never at people
- VO-3Say the uncertainty out loud
Everything published on this topic.
No articles have been published for Computer Vision yet. New long-form pieces will land here.
Everything published on Computer Vision.
The permanent record of every piece we publish under this topic — grouped by year, oldest kept as history.
Short reactions, polls, and open questions.
Faster than the long form. Same standard.
No quick takes match this filter yet.
Evidence, counterpoints, patterns, and the standard.
Every entry links back to its source article. Nothing duplicated.
Framework entries appear here as articles publish.
Open questions and measurable predictions.
We log the question, the confidence, and the review date. When the evidence moves, so does our position.
No active predictions are currently being tracked for this topic.
Coverage on screen.
Long-form, shorts, and playlists connected back to the source articles.
Video coverage is coming soon.
Coming SoonWe haven't published video on Computer Vision yet. Playlists, chapters, and shorts will surface here as they roll out.
Long-form conversations.
No podcast episodes yet.
Coming SoonWhen we publish podcast episodes on Computer Vision, each will link back to its source article.
Connected hubs.
Where this topic overlaps with the rest of the 2CS knowledge graph.
Explore Computer Vision
Every surface connected to this topic.
One permanent home per topic — the whole 2CS library on Computer Vision, indexed for readers and search engines alike.
- All Computer Vision articlesLong-form analysis and film breakdowns tagged Computer Vision.
- Computer Vision quick takesShort reactions, polls, and open questions on the record.
- Computer Vision in the 2CS Analysis FrameworkEvidence, counterpoints, patterns, and the standard.
- Computer Vision Future WatchPredictions we're tracking with confidence and review dates.
- Video coverageLong-form, shorts, and playlists — filter for Computer Vision coverage.
- Podcast episodesLong-form conversations that reference Computer Vision.
- Community investigationsReader-led inquiries connected to Computer Vision.
- Claims & evidence lockerEvery claim we've logged, with the evidence behind it.
- Computer Vision in the Knowledge GraphHow this topic connects to people, teams, and events.
Related topics
Where Computer Vision overlaps.
Full index
Browse every topic.
Every permanent home in one place — grouped by league, discipline, and idea.
All topicsThe conversation, on the record.
Community discussion is coming soon.
Coming SoonA dedicated space for readers to discuss this topic will live here — moderated to the same standard as the editorial.
Follow Computer Vision.
One weekly dispatch. Signal over noise. No spam.
No spam. Unsubscribe anytime.