Journal of Convergence for Information Technology (융합정보논문지)

Convergence Society for SMB (중소기업융합학회)
권호 표지
DOI QR코드

DOI QR Code

Lightweight Convolution Module based Detection Model for Small Embedded Devices

소형 임베디드 장치를 위한 경량 컨볼루션 모듈 기반의 검출 모델

  • Park, Chan-Soo (Dept. of Plasma Bio Display, KwangWoon University) ;
  • Lee, Sang-Hun (Ingenium College of Liberal Arts, KwangWoon University) ;
  • Han, Hyun-Ho (College of General Education, University of Ulsan)
  • 박찬수 (광운대학교 대학원 플라즈마바이오디스플레이) ;
  • 이상훈 (광운대학교 인제니움학부) ;
  • 한현호 (울산대학교 교양학부)
  • Received : 2021.08.04
  • Accepted : 2021.09.20
  • Published : 2021.09.28
Download PDF
⟨ Previous Next ⟩

Abstract

In the case of object detection using deep learning, both accuracy and real-time are required. However, it is difficult to use a deep learning model that processes a large amount of data in a limited resource environment. To solve this problem, this paper proposes an object detection model for small embedded devices. Unlike the general detection model, the model size was minimized by using a structure in which the pre-trained feature extractor was removed. The structure of the model was designed by repeatedly stacking lightweight convolution blocks. In addition, the number of region proposals is greatly reduced to reduce detection overhead. The proposed model was trained and evaluated using the public dataset PASCAL VOC. For quantitative evaluation of the model, detection performance was measured with average precision used in the detection field. And the detection speed was measured in a Raspberry Pi similar to an actual embedded device. Through the experiment, we achieved improved accuracy and faster reasoning speed compared to the existing detection method.

딥러닝을 이용한 객체 검출의 경우 정확도와 실시간성을 모두 요구한다. 그러나, 한정된 자원 환경에서는 수 많은 양의 데이터를 처리하는 딥러닝 모델을 사용하기 어렵다. 이러한 문제 해결을 위해 본 논문에서는 소형임베디드 장치를 위한 객체 검출을 모델을 제안하였다. 일반적인 검출 모델과 달리 사전 학습된 특징 추출기를 제거한 구조를 사용하여 모델 크기를 최소화하였다. 모델의 구조는 경량화된 컨볼루션 블록을 반복해서 쌓는 구조로 설계하였다. 또한, 검출 오버헤드를 줄이기 위해 영역 제안 횟수를 크게 줄였다. 제안하는 모델은 공개 데이터 셋인 PASCAL VOC를 사용하여 학습 및 평가하였다. 모델의 정량적 평가를 위해 검출 분야에서 사용하는 average precision으로 검출 성능을 측정하였다. 그리고 실제 임베디드 장치와 유사한 라즈베리 파이에서 검출 속도를 측정하였다. 실험을 통해 기존 검출 방법 대비 향상된 정확도와 빠른 추론 속도를 달성하였다.

Keywords

References

  1. S. S. Kumar, M. Wang, D. M. Abraham, M. R. Jahanshahi, T. Iseley & J. C. Cheng. (2020). Deep learning-based automated detection of sewer defects in CCTV videos. Journal of Computing in Civil Engineering, 34(1), 04019047. https://doi.org/10.1061/(asce)cp.1943-5487.0000866
  2. V. K. Ha, J. Ren, X. Xu, S.,Zhao G. Xie & V. M. Vargas. (2018, July). Deep learning based single image super-resolution: A survey. In International Conference on Brain Inspired Cognitive Systems (pp. 106-119). Springer, Cham.
  3. K. Simonyan & A. Zisserman. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
  4. C. Chen, P. Zhao, C. X. Lu, W. Wang, A. Markham & N. Trigoni. (2020). Deep-learning-based pedestrian inertial navigation: Methods, data set, and on-device inference. IEEE Internet of Things Journal, 7(5), 4431-4441. https://doi.org/10.1109/jiot.2020.2966773
  5. P. Li, Y. Zang, C. Wang, J. Li, M. Cheng, L. Luo & Y. Yu. (2016, July). Road network extraction via deep learning and line integral convolution. In 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) (pp. 1599-1602). IEEE.
  6. L. Liu, W. Ouyang, X. Wang, P. Fieguth, J, Chen, X., Liu & M. Pietikainen. (2020). Deep learning for generic object detection: A survey. International journal of computer vision, 128(2), 261-318. https://doi.org/10.1007/s11263-019-01247-4
  7. A. Womg, M. J. Shafiee, F. Li & B. Chwyl. (2018, May). Tiny SSD: A tiny single-shot detection deep convolutional neural network for real-time embedded object detection. In 2018 15th Conference on Computer and Robot Vision (CRV) (pp. 95-101). IEEE.
  8. W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C. Y. Fu & A. C. Berg. (2016, October). Ssd: Single shot multibox detector. In European conference on computer vision (pp. 21-37). Springer, Cham.
  9. R. Avenash & P. Viswanath. (2019). Semantic Segmentation of Satellite Images using a Modified CNN with Hard-Swish Activation Function. In VISIGRAPP (4: VISAPP) (pp. 413-420).
  10. T. Y. Hsiao, Y. C. Chang, H. H. Chou & C. T. Chiu. (2019). Filter-based deep-compression with global average pooling for convolutional networks. Journal of Systems Architecture, 95, 9-18. https://doi.org/10.1016/j.sysarc.2019.02.008
  11. F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally & K. Keutzer. (2016). SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size. arXiv preprint arXiv:1602.07360.
  12. D. Xiao, F. Shan, Z. Li, B. T. Le, X. Liu & X. Li. (2019). A target detection model based on improved tiny-yolov3 under the environment of mining truck. IEEE Access, 7, 123757-123764. https://doi.org/10.1109/ACCESS.2019.2928603
  13. M. Everingham, L. Van Gool, C. K. Williams, J. Winn & A. Zisserman. (2010). The pascal visual object classes (voc) challenge. International journal of computer vision, 88(2), 303-338. https://doi.org/10.1007/s11263-009-0275-4
  14. J. Redmon & A. Farhadi. (2018). Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767.
  15. M. Tan & Q. Le. (2019, May). Efficientnet: Rethinking model scaling for convolutional neural networks. In International Conference on Machine Learning (pp. 6105-6114). PMLR.
  16. B. Zoph & Q. V. Le. (2016). Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578.
  17. K. He, X. Zhang, S. Ren & J. Sun. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
  18. Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., ... & Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861.
  19. M. Sandler, A. Howard, M. Zhu, A. Zhmoginov & L. C. Chen. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4510-4520).