The algorithm for predictive tracking considers the timestamp when a read is recorded respectively generated. The timestamp when Racemap receives the detection is not used for the prediction.
Possible reasons for a significant difference between the recorded timestamp and the received timestamp of the same read:
There is a delay in forwarding the reads from the timing system to Racemap. Minimize the delay to improve the quality of the prediction.
Settings that impact the timestamps such as date, start time, and time offsets of your event in the timing system do not fit the NOW time.
Predictive tracking with any timing system
The set-up guide checks your settings for predictive tracking. For RACE|RESULT timekeeping system Racemap additionally checks the forwarding of detections with emulated track pings. If the forwarding is configured in RACE|RESULT then the emulated pings are sent back to Racemap.
Intuitive setup guides to correct settings for predictive live tracking
We recommend testing to gain experience with the prediction. We support your test events.
Strategically place hardware along the race course.
1st & 2nd read approx 0.5 & 1 km behind the start.
Place readers along the race course to detect each transponder every 20 min.
Transition area: t_in, t_out with decoders, track boxes too inaccurate.
Algorithm for predictive tracking
For predictive tracking our system needs to know:
transponder ID of each participant you want to display
exact race course as .gpx or .kml ("shadowtrack")
locations of the timing hardware
readers with a GPS module eg. track boxes send their locations to Racemap
readers without own locations: define the location of the reader in Racemap
With AI-based features, you flexibly apply predictive tracking.
Auto-Mapping to shadowtrack within 30 m distance:
If reader is placed in laps the reader will be mapped on each lap automatically.
If reader is located > 30 m from the shadowtrack the prediction ignores its reads.
Moving reader: Variable locations of reader during the race, e.g. place track boxes on cars or boats. The prediction considers the current location of every detection for live and replay.
Multiple contests detection: One reader can detect several contests (shadowtracks), simultaneously. Racemap assigns reads to the correct shadowtrack, corresponding to transponder ID and contest.
High performance: prediction calculates location & speed for > 50,000 participants simultaneously, e.g. München Marathon
predictive live tracking at München Marathon, decoder reads forwarded from RACE|RESULT
Different visualization of live and replay
The replay is calculated with each finish detection for separate participants. The recalculation considers reads sent with a delay or even after the event.
Live
Replay
Appearance of markers
With 2nd read, eg. prediction receives detection from start without delay and markers will show from 1st reader behind
From start detection
Movement of markers
Speed extrapolation until detection from next reader's location;
speed correction depending on difference between marker in visualization from detection of real participant;
As readers (especially track box) might miss detections, marker moves on over location of following reader.
Average speed between detections
Speed filters to check the plausibility of reads: You can set splits with expected speed values eg. swimming, transition, and cycling for triathlon.
filter_max: ignore reads with two times faster speed than expected speed
filter_min: ignore reads with 0.1 x speed than expected speed