A Lightweight Traffic Police Action Recognition Deep Learning Network for Edge Device
- Resource Type
- Conference
- Authors
- Gankhuyag, Ganzorig; Yae, Haejoo; Shim, Youngbo; Park, Changgue; Min, Kyoungwon
- Source
- 2022 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia) Consumer Electronics-Asia (ICCE-Asia), 2022 IEEE International Conference on. :1-3 Oct, 2022
- Subject
- Aerospace
Communication, Networking and Broadcast Technologies
Computing and Processing
Engineering Profession
Fields, Waves and Electromagnetics
Geoscience
Photonics and Electrooptics
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Transportation
Deep learning
Law enforcement
Gesture recognition
Real-time systems
Hardware
Task analysis
Autonomous vehicles
Action recognition
A Lightweight deep learning model
- Language
The traffic police gesture recognition is necessary for the perception task of autonomous vehicles. Most of the previous SOTA algorithms are considering accuracy instead of network capability to run edge devices of autonomous vehicles. Since the hardware resources of autonomous vehicles are limited, we propose a lightweight model that can recognize the action of traffic police. We compared our proposed network with SOTA methods and experimented with an open dataset. The results show that the proposed method archives an accuracy rate of 100% same as the SOTA method. And inference speed is faster than the SOTA method and higher than real-time requirements at RTX3090(150 fps) and 33.3 fps at the NVIDIA Jetson Xavior NX board.