Related Experiment Video
Updated: Sep 18, 2025
06:37
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
Published on: December 15, 2023
4.1K
Sensor-Driven Real-Time Recognition of Basketball Goal States Using IMU and Deep Learning
Jiajin Zhang1,2, Rong Guo1,2, Yan Zhu2,3
1College of Big Data, Yunnan Agricultural University, Kunming 650201, China.
Sensors (Basel, Switzerland)
|June 27, 2025
Summary
This study introduces a real-time basketball goal recognition system using inertial measurement unit (IMU) sensors and deep learning. The CNN-LSTM-Attention model achieved 87.79% accuracy in identifying shot outcomes like swishes and misses.
Area of Science:
- Sports Analytics
- Artificial Intelligence
- Sensor Technology
Background:
- Advancements in AI, machine vision, and IoT are transforming sports analytics.
- Accurate player performance measurement is crucial in basketball.
- Real-time analysis of shooting execution is a key area for improvement.
Purpose of the Study:
- To develop a real-time goal state recognition system for basketball using IMU sensors.
- To classify four shooting scenarios: rebounds, swishes, other shots, and misses.
- To evaluate the effectiveness of deep learning models for shot classification.
Main Methods:
- Installation of IMU sensors around the basketball net to capture motion data.
- Utilizing five deep learning models: CNN, RNN, LSTM, CNN-LSTM, and CNN-LSTM-Attention.
- Analyzing acceleration, angular velocity, and angular changes for shot execution analysis.
Main Results:
- The CNN-LSTM-Attention model demonstrated superior performance in identifying goal states.
- Achieved an accuracy of 87.79% in real-time shot type classification.
- The system proved robust and efficient in a complex sports environment.
Conclusions:
- The developed system offers a high level of real-time goal state recognition in basketball.
- Results support applications in skill analysis, performance evaluation, and intelligent training equipment.
- Provides an efficient and practical solution for athletes and coaches to enhance training.
