DOI QR코드

DOI QR Code

Real Time Face detection Method Using TensorRT and SSD

TensorRT와 SSD를 이용한 실시간 얼굴 검출방법

  • 유혜빈 (한경대학교 ICT로봇기계공학부) ;
  • 박명숙 (한경대학교 ICT로봇기계공학부) ;
  • 김상훈 (한경대학교 ICT로봇기계공학부)
  • Received : 2020.07.07
  • Accepted : 2020.08.26
  • Published : 2020.10.31

Abstract

Recently, new approaches that significantly improve performance in object detection and recognition using deep learning technology have been proposed quickly. Of the various techniques for object detection, especially facial object detection (Faster R-CNN, R-CNN, YOLO, SSD, etc), SSD is superior in accuracy and speed to other techniques. At the same time, multiple object detection networks are also readily available. In this paper, among object detection networks, Mobilenet v2 network is used, models combined with SSDs are trained, and methods for detecting objects at a rate of four times or more than conventional performance are proposed using TensorRT engine, and the performance is verified through experiments. Facial object detector was created as an application to verify the performance of the proposed method, and its behavior and performance were tested in various situations.

최근에는 딥러닝 기술을 이용하여 물체 검출 및 인식에서 성능이 크게 향상되는 새로운 접근방법들이 빠르게 제안되고 있다. 객체, 특히 얼굴객체 검출에 관한 여러 기법(Faster R-CNN, R-CNN, YOLO, SSD 등) 중 SSD는 다른 기법들보다 정확도와 속도에서 우수하다. 동시에 여러 객체 검출 네트워크들(object detection network)도 쉽게 이용할 수 있다. 본 논문에서는 객체 검출 네트워크 중 Mobilenet v2 network를 이용하고 SSD와 결합한 모델을 훈련하고, TensorRT engine을 이용하여 기존의 성능보다 4배 이상의 속도로 객체를 검출하는 방법에 대해 제안하고 실험을 통해 성능을 검증한다. 제안한 방법의 성능 검증을 위한 응용으로 얼굴객체 검출기(facial object detector)를 만들어 다양한 상황에서 동작과 성능을 실험하였다.

Keywords

References

  1. Zhengxia Zou, Zhenwei Shi, Member, IEEE, Yuhong Guo, and Jieping Ye, Senior Member, IEEE - Object Detection in 20 Years: A Survey.
  2. Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, Alexander C. Berg1/UNC Chapel Hill Zoox Inc. Google Inc. University of Michigan, Ann-Arbor - SSD: Single Shot MultiBox Detector.
  3. Mark Sandler, Andrew Howard Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen/Google Inc. - MobileNetV2: Inverted Residuals and Linear Bottlenecks.
  4. Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton - ImageNet Classification with Deep Convolutional Neural Networks.
  5. Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun - Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.
  6. CV-Tricks.com-Learn Machine Learning, AI & Computer Vision - Object-detection/Faster-r-cnn-yolo-ssd.
  7. Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam - MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications.
  8. "Face Recognition on Jetson Nano using TensorRT," https://towardsdatascience.com/face-recognition-using-tensorrt-on-jetson-nano-set-up-in-less-than-5min-7c00bf730085
  9. "NVIDIA TensorRT Documentation," https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html
  10. Joseph Redmon(University of Washington), Santosh Divvala (Allen Institute for Artificial Intelligence), Ross Girshick (Facebook AI Research), Ali Farhadi(University of Washington) - You Only Look Once: Unified, Real-Time Object Detection.
  11. https://github.com/jkjung-avt/tf_trt_models
  12. https://github.com/jkjung-avt/tensorrt_demos
  13. https://github.com/AastaNV/TRT_object_detection
  14. https://github.com/dusty-nv/jetson-inference