PRE2024 3 Group4

max van aken

Bram van der pas

Jarno peters

Simon B. Wessel

Javier Basterreche Blasco

Matei Manaila

Start of project

Problem statement and objective

The problem this group wants to tacke is that many swimmers have flaws in their swimming technique, while the quality and quantity of trainers is declining in many amateur clubs. To solve the problem we want to create a swimsuit with sensors that track the position and orientation of the limbs of swimmers. The suit should then be able to give feedback based on the data the sensors aqcuire.

The users

people who swim for sport (as amateurs, professionals generally have a lot of good coaches) and wish to improve their technique (pretty much all of them).

Requirements

The suit should not be too heavy or inhibit motion too much, as the swimmers should be able to swim as normal while the suit is measuring. It should also be a one size fits all solution, as this means swimming clubs have to purchase less suits. The suits should also be as affordable as possible, as the end users are amateur clubs, which are usually not super rich.

Approach

Preferrably we would like to do this using sensors on the suit, as this means that all of the technology would be on the suit, meaning no external infrastructure is required in the swimming pool. The sensors would be placed on top of or near joints in the body, such as the shoulder, elbow and wrist for arms, and the hips, knees and ankles for legs. Distances between joints would be determined using supersonic sensors and orientation would be determined by having gyrosensors at each joint location. With this approach, reference sensors would be required at the base of each arm or leg so the relative position data from the joints can be converted into more absolute data that is more useful.

If the sensor idea turns out to be impossible to implement during this course, the alternative would be the principles of a motion capture suit, where bright white balls are placed on a black suit and their position is determined using 2 cameras. One camera would view from the side in this case, while another would view from above. Based on this data, the same feedback can be constructed as with the sensor principle, but this would require 2 cameras on rails to be installed in the swimming pool, and these cameras would need to follow the suit around. This would possibly make the suit more expensive, as these rails would need to be either 25 or 50 meters long, depending on the swimming pool. This would also be less practical to implement for amateur clubs, as the pools they use would need to agree with installing said rails.

Milestones and deliverables

Due to the time frame and the scope of the course, a full body suit is likely not feasible. To be able to have something to show at the end of the course, a prototype will be built for one arm. There are also multiple ways of swimming, for this project the focus will be on the front crawl.

The milestones for the construction of the arm suit would be as follows:

1. Build a functional prototype with either onboard sensors or external cameras, that can send position data for each joint to a computer.
2. Convert the raw position data to usable coordinates, likely with angles and distances between joints.
3. Construct a program that can differentiate between correct and wrong technique. Some technique errors may be distinguished manually, others might require some simple implementations of AI. One method for this would be gathering a bunch of data for wrong and correct arm motion, gathering simple features from the data, like minimal and maximal angle of the elbow joint, and training a simple decision tree.
4. (bonus) if there is some time left, it may be possible to also write a program for a different way of swimming, like backstroke or the butterfly.

Literature study

Wearable motion capture suit with full-body tactile sensors

This article discusses a suit with not only motion sensors, but also tactile sensors. These sensors detect whether a part of the suit is touching something or not. The motion sensors consist of an accelerometer, several gyroscopes, and multiple magnetometers. The data from these sensors is processed in a local cpu and subsequently sent to a central computer, to decrease processing time and ensure real-time calculations. The goal of the suit is to give researchers in the field of sports and rehabilitation more insight in human motion and behavior, as before this, no real motion capture suit with both motion sensors and tactile sensors had been implemented.

Motion tracking: no silver bullet, but a respectable arsenal

https://ieeexplore.ieee.org/abstract/document/1046626