TurboTouchPredictor 0.1.5

TurboTouch predictor

TurboTouch predictor Python version

Provides a Python implementation for the TurboTouch predictor.

Install

pip install TurboTouchPredictor --upgrade

Minimal example

from TurboTouchPredictor import TurboTouchPredictor

ttpPredictor = TurboTouchPredictor();

// Amount of prediction in ms. Allowed values: 0, 16, 32, 48, 64
ttpPredictor.setAmountOfCompensation(32);

predictedPoint = ttpPredictor.predict(0, 0, 0, "Interacting") # x, y, t, state

Doc

TurboTouchPredictor package

_class _TurboTouchPredictor.TurboTouchPredictor

Bases: object

Filter:

OneEuroVectorProcessor

LatencyCompensated:

int

Update1euroInternalFreq:

bool

__init__() → None

Initializes the TurboTouchPredictor

predict(_x: float_, _y: float_, _timestamp: float_, _state: str_) → tuple[float, float]

Predicts a point from the current lagging one

Parameters:

• x – x coordinate in pixels

• y – y coordinate in pixels

• timestamp – timestamp in nanoseconds

• state – “Interacting” or “NotInteracting”

Returns:

return the predicted point p, p[0]: x coordinate, p[1]: y coordinate

Return type:

tuple[float, float]

reset()

Resets the internal state of the processor

setAmountOfCompensation(_comp: int_) → None

Sets the parameters of the predictor for the given amount of compensation

Parameters:

comp (int) – Compensation amount in ms. Allowed values: 0, 16, 32, 48, 64

_class _OneEuroVectorProcessor.OneEuroVectorProcessor(_freq: float_, _mincutoff: float_, _beta: float_)>

Bases: object

NormFilter:

OneEuroFilter

FilterX:

OneEuroFilter

FilterY:

OneEuroFilter

__init__(_freq: float, mincutoff: float, beta: float) → None

Initializes the OneEuroVectorProcessor with three OneEuroFilter

Parameters:

• freq (float) – An estimate of the frequency in Hz of the signal (> 0).

• mincutoff (float) – Min cutoff frequency in Hz (> 0).

• beta (float) – Parameter to reduce latency (> 0).

process(prediction: tuple[float, float, float], lag: tuple[float, float]) → tuple[float, float]

Parameters:

• prediction (tuple[float, float, float]) – (x, y, t)

• lag (tuple[float, float]) – (x, y)

Returns:

the processed position

Return type:

tuple[float, float]

reset() → None

Resets the internal state of the processor

setParameters(freq: float, mincutoff: float, beta: float) → None

Parameters:

• freq (float) – An estimate of the frequency in Hz of the signal (> 0).

• mincutoff (float) – Min cutoff frequency in Hz (> 0).

• beta (float) – Parameter to reduce latency (> 0).

Related publication

@inproceedings{10.1145/3242587.3242646,
    author = {Nancel, Mathieu and Aranovskiy, Stanislav and Ushirobira, Rosane and Efimov, Denis and Poulmane, Sebastien and Roussel, Nicolas and Casiez, G\'{e}ry},
    title = {Next-Point Prediction for Direct Touch Using Finite-Time Derivative Estimation},
    year = {2018},
    isbn = {9781450359481},
    publisher = {Association for Computing Machinery},
    address = {New York, NY, USA},
    url = {https://doi.org/10.1145/3242587.3242646},
    doi = {10.1145/3242587.3242646},
    abstract = {End-to-end latency in interactive systems is detrimental to performance and usability, and comes from a combination of hardware and software delays. While these delays are steadily addressed by hardware and software improvements, it is at a decelerating pace. In parallel, short-term input prediction has shown promising results in recent years, in both research and industry, as an addition to these efforts. We describe a new prediction algorithm for direct touch devices based on (i) a state-of-the-art finite-time derivative estimator, (ii) a smoothing mechanism based on input speed, and (iii) a post-filtering of the prediction in two steps. Using both a pre-existing dataset of touch input as benchmark, and subjective data from a new user study, we show that this new predictor outperforms the predictors currently available in the literature and industry, based on metrics that model user-defined negative side-effects caused by input prediction. In particular, we show that our predictor can predict up to 2 or 3 times further than existing techniques with minimal negative side-effects.},
    booktitle = {Proceedings of the 31st Annual ACM Symposium on User Interface Software and Technology},
    pages = {793–807},
    numpages = {15},
    keywords = {touch input, latency, lag, prediction technique},
    location = {Berlin, Germany},
    series = {UIST '18}
}