𝕏X采集材料
用 ViTPose+ 识别俯卧撑动作
10-27 06:53 · 北京时间
待归类
应用场景不明确
代码仓库演示线索
原文与观测指标
1 个来源𝕏X
查看原文 用 ViTPose+ 识别俯卧撑动作
Jeremy Park, PhD点赞191采集时的累计值
每小时增长+10.7赞 / 小时 · 观测区间平均值
观测增量+22两次有效记录之间的变化
发布时间：2026-10-27 06:53 · 北京时间
指标采集：10-28 02:05
对比区间：10-28 00:02 至 10-28 02:05 · 2.06 小时 · 净增量 +22
摘要
作者用 ViTPose+ Large 进行姿态估计，通过肩部垂直位移判断俯卧撑是否达到完整动作，并用踝、髋、肩连线与直背参考线比较姿势偏差。代码已开源。
摘要由 AI 生成，请以原文为准。观测历史 · 最近 6 条 展开 / 收起
缺失不计为零；增长只比较同一指标来源的有效记录，按实际间隔折算每小时。上游缓存可能延迟数值更新。
| 采集时间 · 北京时间 | 指标 | 数值 | 来源 | 状态 |
|---|---|---|---|---|
| 10-28 02:05:49 | 点赞 | 191 | 工业质检与设备应用 | 已取得 |
| 10-28 00:02:16 | 点赞 | 169 | 工业质检与设备应用 | 已取得 |
| 10-27 22:02:13 | 点赞 | 146 | 工业质检与设备应用 | 已取得 |
| 10-27 20:02:13 | 点赞 | 129 | 工业质检与设备应用 | 已取得 |
| 10-27 16:02:04 | 点赞 | 73 | 工业质检与设备应用 | 已取得 |
| 10-27 15:45:44 | 点赞 | 72 | 工业质检与设备应用 | 已取得 |
采集原文 展开 / 收起
I made a computer vision demo for push ups! Working with @movewithmigs on strength training, and I did a push ups test to see how many I could d...
I made a computer vision demo for push ups! Working with @movewithmigs on strength training, and I did a push ups test to see how many I could do. I thought I did 25, but computer vision counted 24 🤣 keeping me honest lol I'm using ViTPose+ Large through the @vlmrun Gateway for pose estimation. I'm using the vertical displacement of the shoulder to detect full range of motion, and using the ankle-hip-shoulder line to compare against a straight back reference. You can see a plot of how much my back deviates from the straight line reference. In the last two reps, you can see that I am deviating a bit. Since everyone’s push ups look different, we can tune the thresholds accordingly if needed. Let me know what you think! The code is open-source on GitHub: https://github.com/jeremyipark/vision-demos