The organizing committee of the ICSV31 hosts an AI Challenge focusing on diagnosing machine anomalies using acoustic signals.

Participants will train AI models on drone sound signals and identify anomalies from a provided dataset. A grand prize of 1,500 USD will be awarded to the winning team.

For detailed instructions to participate in the ICSV31 AI Challenge, please visit https://icsv31aichallenge.github.io/ICSV31-AI-Challenge/ 


 Key Dates 

Challenge Launch: 5 February 2025

Distribution of Test Dataset: 1 April 2025

Final Model Submission: 21 May 2025

Competition Result Announcement: 31 May 2025

 Task (Anomalous Sound Detection of Drones) 

ICSV31-AI-Challenge (2nd KSNVE AI Challenge) aims to diagnose the state of drones by detecting anomalous sounds caused by mechanical failures in propellers and motors in noisy environments. In particular, drone sounds that vary depending on operational conditions, such as flight directions, along with background noise, make this task highly challenging. Participants are required to train deep learning models detecting anomalous drone sounds in test data, through the model training using the training dataset.

 Submission (Due: 21 May 2025) 

Participation is team-based, and at least one team member must be a registered attendee of the ICSV31 at the time of model submission. The congress will also hold a dedicated workshop session for participating teams.

Participants must submit four files for challenge participation:

1. Evaluation Dataset Performance
2. Test Dataset Performance
3. Reproducible Training and Evaluation Code
4. Technical Report*