{"id":265,"date":"2026-04-13T23:56:49","date_gmt":"2026-04-14T03:56:49","guid":{"rendered":"https:\/\/wp.stgeorges.bc.ca\/michaelh\/?p=265"},"modified":"2026-04-16T02:22:11","modified_gmt":"2026-04-16T06:22:11","slug":"personal-project-update-2","status":"publish","type":"post","link":"https:\/\/wp.stgeorges.bc.ca\/michaelh\/uncategorized\/personal-project-update-2\/","title":{"rendered":"Personal Project Update #2"},"content":{"rendered":"\n

Back in my first update<\/a>, I talked about the problem I’m solving: athletes don’t have an accessible, data-driven way to analyze their technique. You either hire an expensive biomechanics lab, or you film yourself and guess. I’m building Motion X<\/strong> to fix that. It is an AI-powered biomechanics platform that gives you the kind of precise, frame-by-frame feedback that used to require a sports science degree.<\/p>\n\n\n\n

Since the last post, Motion X went from an idea with some early research to a functional web application. In this blog post, I will walk you through what it can do now in general.<\/p>\n\n\n\n

\n\n\n\n

The Core: Video Analysis<\/h2>\n\n\n\n

The flagship feature of MOTION X is dual video comparison<\/strong>. The user can upload two videos, a reference (maybe your coach, a pro athlete, or now you can even select and import directly from a youtube video) and your current attempt. The system then breaks down exactly where your form differs, joint by joint, frame by frame.<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

Video Analysis Page<\/p>\n\n\n\n

Here’s what happens when you hit “Analyze”:<\/p>\n\n\n\n

    \n
  1. Pose Detection<\/strong> \u2014 Every frame of both videos gets processed through joint identification, which detects 33 anatomical landmarks on the body. This includes shoulders, elbows, wrists, hips, knees, ankles, the full skeleton. The system tracks all 33 points but focuses scoring on 8 key joint angles: both elbows, both shoulders, both hips, and both knees. These are the joints that matter most for athletic form across almost every sport.<\/li>\n\n\n\n
  2. Angle Calculation<\/strong> \u2014 For each of those 8 joints, the system calculates the precise angle using vector math (specifically atan2<\/code>-based angle computation between three connected landmarks). So instead of “your arm looks a bit off,” you get “your right elbow is at 142\u00b0 when the reference is at 158\u00b0 \u2014 that’s a 16\u00b0 deviation.”<\/li>\n\n\n\n
  3. Temporal Alignment (STCF-DTW)<\/strong> \u2014 This is where it gets interesting. Two people never perform a movement at exactly the same speed. A squat might take you 3 seconds but the reference only 2. Naive frame-to-frame comparison would be completely wrong. So I implemented Spatiotemporal Coupling Feature Dynamic Time Warping<\/strong>. This is a modified DTW algorithm that uses a 32-dimensional feature vector per frame (8 angles + 8 angular velocities + 8 accelerations + 8 coupling ratios between adjacent joints) to intelligently align both videos by movement phase, not by time. This means the system knows that your frame 47 corresponds to the reference’s frame 32 because you’re both at the bottom of the squat, even if you got there at different speeds.<\/li>\n\n\n\n
  4. Scoring<\/strong> \u2014 Each joint gets a score from 0\u2013100 based on angle deviation from the reference. Under 5\u00b0 difference gives a perfect score of a hundred. Under 10\u00b0 gives a score ranging from 80-90. The further off you are, the lower the score. You get per-joint scores, per-frame scores, and an overall score for the entire movement.<\/li>\n\n\n\n
  5. <\/li>\n<\/ol>\n\n\n\n

    Interactive Joint Inspector<\/h3>\n\n\n\n

    On top of the video, you can toggle the Joint Inspector. This allows the user to click on any joint in the skeleton overlay, and a popup would appear showing the exact angle, the reference angle, the difference, and a score. <\/p>\n\n\n\n

    \n