Related Experiment Video
Updated: Jul 19, 2025
11:41
Evaluation of an Exclusive Spur Dike U-Turn Design with Radar-Collected Data and Simulation
Published on: February 1, 2020
20.4K
mm-TPG: Traffic Policemen Gesture Recognition Based on Millimeter Wave Radar Point Cloud
Xiaochao Dang1,2, Wenze Ke1, Zhanjun Hao1,2
1College of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, China.
Sensors (Basel, Switzerland)
|August 12, 2023
Summary
This study introduces mm-TPG, a novel system for traffic-police gesture recognition using millimeter-wave radar. The technology ensures accurate and robust recognition in diverse conditions, enhancing autonomous driving safety.
Area of Science:
- Computer Vision
- Robotics
- Sensor Technology
Background:
- Autonomous driving systems require sophisticated environmental perception.
- Traffic signal and sign recognition are critical for safe navigation.
- Gesture recognition is a key component of interpreting traffic signals.
Purpose of the Study:
- To develop and evaluate mm-TPG, a traffic-police gesture recognition system.
- To leverage millimeter-wave radar for high-precision gesture detection.
- To improve the robustness of gesture recognition in complex environments.
Main Methods:
- Utilized a 60 GHz frequency-modulated continuous-wave (FMCW) millimeter-wave radar sensor.
- Applied a double-threshold filtering algorithm for data denoising.
- Employed ResNet18 for feature extraction and gated recurrent units for classification.
Main Results:
- The mm-TPG system demonstrated high accuracy in recognizing traffic-police gestures.
- The system proved robust across varying lighting and weather conditions.
- Achieved effective gesture recognition in complex real-world scenarios.
Conclusions:
- Millimeter-wave radar is a viable technology for traffic-police gesture recognition.
- The mm-TPG system offers a reliable solution for enhancing autonomous driving safety.
- Further development can integrate this system into advanced driver-assistance systems.
