🏇 Japan Develops AI That Detects Horse Racing Whip Use Through Sound

Currently, race stewards manually review video footage to count whip strikes—a time-consuming process prone to oversight. Researchers at the University of Tsukuba have developed an AI system that detects whip use by analyzing sound. Achieving approximately 70% accuracy with potential for real-time detection, this technology could transform how racing authorities ensure fair competition while protecting horse welfare.

Background: Why Automated Whip Detection Matters

The whip is a standard tool in horse racing, used by jockeys to encourage speed and maintain a horse's focus. However, excessive whip use can cause pain and distress to horses, making it a significant animal welfare concern that has prompted regulatory action worldwide.

Japan's Racing Association (JRA) tightened its rules in 2024, limiting consecutive whip strikes to five (down from ten). Violations result in penalties ranging from warnings to fines and riding suspensions. Similar strict regulations exist internationally—Germany limits consecutive strikes to three, while the UK caps flat race whipping at seven strikes.

The current enforcement method relies on stewards manually reviewing race footage after each event. This process is labor-intensive, time-consuming, and carries inherent risks of human error. The racing industry has long needed an objective, efficient method for monitoring whip use—and that's exactly what this new technology provides.

The Research Approach: Focusing on High-Frequency Sound

The research team, led by Associate Professor Keiichi Zempo from the University of Tsukuba's Faculty of Engineering, Information and Systems, took an innovative approach by focusing on the distinctive sound produced when a whip is cracked.

After collecting and analyzing sound data from various whip types used by trainers in stables, the team made a surprising discovery: whip sounds contain frequencies exceeding 22 kilohertz—beyond the range of human hearing (approximately 20 Hz to 20 kHz). Standard recording equipment cannot accurately capture these high-frequency sounds, so the researchers employed specialized recording at 192 kHz sampling rate.

Building the AI Detection System

The team utilized deep learning technology called "Convolutional Recurrent Neural Networks" (CRNN), which can capture both the acoustic characteristics and temporal changes in sound patterns simultaneously.

Training data came from 24 races held in Japan, incorporating 620 instances of whip use. The best-performing model achieved approximately 70% accuracy in automatically detecting whip strikes. Crucially, the use of high-fidelity audio data containing high-frequency components improved detection accuracy, scientifically demonstrating for the first time that whip sounds contain these ultrasonic elements.

Real-World Testing and Real-Time Potential

The research team conducted field tests at racecourses in Japan's Kanto region and at France's ParisLongchamp Racecourse. Racing venues present significant acoustic challenges—crowd noise can reach 70 to 126 decibels, comparable to standing near a jet engine.

The team found that data collection was most effective in areas with fewer spectators, such as near track corners. Importantly, processing speeds in most configurations were faster than real-time audio playback, suggesting the system could potentially detect whip use during live races—a significant advancement over post-race video review.

Implications for Animal Welfare and Racing Integrity

If implemented practically, this technology would enable more accurate, objective monitoring of whip use, enhancing race integrity while helping ensure horses are treated humanely. Professor Zempo expressed his hope that the technology would help reduce stress on horses.

The research was funded by NEXION Corporation (Shinjuku, Tokyo) and was published in the International Federation of Automatic Control's journal "Engineering Applications of Artificial Intelligence" in November 2025.

The Global Context: Growing Focus on Animal Welfare

The debate over whip use in horse racing continues worldwide. Australia's harness racing industry banned whips entirely in 2016, and Norway has prohibited whip use in most races since 1982. Meanwhile, animal welfare organizations like the RSPCA argue that whipping fatigued horses in the final stages of races offers no performance benefit and should be eliminated entirely.

However, many jockeys maintain that the whip serves primarily as a safety tool and directional cue rather than a device for inflicting pain. Legendary jockey Yutaka Take has noted that the whip helps maintain safety and correct a horse's course. This technology could help bridge the gap between these perspectives by providing objective data on whip use patterns.

Looking Ahead

This Japan-developed technology represents a meaningful step toward balancing sporting integrity with animal welfare—two values that need not be in conflict. The research team plans to continue collecting data and refining the system to work reliably even in noisy conditions, with practical implementation as the ultimate goal.

In Japan, AI technology is being developed to promote fairness in horse racing while improving animal welfare. What discussions are happening in your country about how animals are treated in horse racing or other sports? We'd love to hear your perspective.

References