JACIII Vol.25 No.1 pp. 40-49
doi: 10.20965/jaciii.2021.p0040


Helmet Detection Based on Deep Learning and Random Forest on UAV for Power Construction Safety

Guobing Yan, Qiang Sun, Jianying Huang, and Yonghong Chen

Guangdong Power Grid Corporation
757 Dongfeng East Road, Guangzhou, Guangdong 510600, China

Corresponding author

June 1, 2020
October 27, 2020
January 20, 2021
safety helmet, deep learning, convolutional neural network, random forest

Image recognition is one of the key technologies for worker’s helmet detection using an unmanned aerial vehicle (UAV). By analyzing the image feature extraction method for workers’ helmet detection based on convolutional neural network (CNN), a double-channel convolutional neural network (DCNN) model is proposed to improve the traditional image processing methods. On the basis of AlexNet model, the image features of the worker can be extracted using two independent CNNs, and the essential image features can be better reflected considering the abstraction degree of the features. Combining a traditional machine learning method and random forest (RF), an intelligent recognition algorithm based on DCNN and RF is proposed for workers’ helmet detection. The experimental results show that deep learning (DL) is closely related to the traditional machine learning methods. Moreover, adding a DL module to the traditional machine learning framework can improve the recognition accuracy.

Cite this article as:
Guobing Yan, Qiang Sun, Jianying Huang, and Yonghong Chen, “Helmet Detection Based on Deep Learning and Random Forest on UAV for Power Construction Safety,” J. Adv. Comput. Intell. Intell. Inform., Vol.25, No.1, pp. 40-49, 2021.
Data files:
  1. [1] G. Feng, W. Liu, S. Li, D. Tao, and Y. Zhou, “Hessian-Regularized Multitask Dictionary Learning for Remote Sensing Image Recognition,” IEEE Geoscience and Remote Sensing Letters, Vol.16, No.5, pp. 821-825, 2019.
  2. [2] M. Chaa, Z. Akhtar, and A. Attia, “3D palmprint recognition using unsupervised convolutional deep learning network and SVM classifier,” IET Image Processing, Vol.13, No.5, pp. 736-745, 2019.
  3. [3] J. Pei, Y. Huang, W. Huo, Y. Zhang, J. Yang, and T.-S. Yeo, “SAR Automatic Target Recognition Based on Multiview Deep Learning Framework,” IEEE Trans. on Geoscience and Remote Sensing, Vol.56, No.4, pp. 2196-2210, 2018.
  4. [4] F. Liu and Z. Wang, “PolishNet-2d and PolishNet-3d: Deep Learning-Based Workpiece Recognition,” IEEE Access, Vol.7, pp. 127042-127054, 2019.
  5. [5] Y. P. Huang and H. Basanta, “Bird image retrieval and recognition using a deep learning platform,” IEEE Access, Vol.7, pp. 66980-66989, 2019.
  6. [6] X. Long, W. Cui, and Z. Zheng, “Safety Helmet Wearing Detection Based On Deep Learning,” 2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conf. (ITNEC), pp. 2495-2499, 2019.
  7. [7] J. Li et al., “Safety helmet wearing detection based on image processing and machine learning,” 2017 9th Int. Conf. on Advanced Computational Intelligence (ICACI), pp. 201-205, 2017.
  8. [8] K. C. D. Raj, A. Chairat, V. Timtong, M. N. Dailey, and M. Ekpanyapong, “Helmet violation processing using deep learning,” 2018 Int. Workshop on Advanced Image Technology (IWAIT), pp. 1-4, 2018.
  9. [9] K. Li, X. Zhao, J. Bian, and M. Tan, “Automatic Safety Helmet Wearing Detection,” 2017 IEEE 7th Annual Int. Conf. on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER), pp. 617-622, 2017.
  10. [10] C. A. Rohith, S. A. Nair, P. S. Nair, S. Alphonsa, and N. P. John, “An Efficient Helmet Detection for MVD Using Deep Learning,” 2019 3rd Int. Conf. on Trends in Electronics and Informatics (ICOEI), pp. 282-286, 2019.
  11. [11] N. Boonsirisumpun, W. Puarungroj, and P. Wairotchanaphuttha, “Automatic Detector for Bikers With No Helmet Using Deep Learning,” 2018 22nd Int. Computer Science and Engineering Conf. (ICSEC), pp. 1-4, 2018.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Mar. 01, 2021