Abstract
This paper is dedicated to developing high-efficiency face detection and tracking method for big dynamic crowds or numerous pedestrians. Three modules constitute the proposed method, i.e., face candidate generation, face candidate verification, and face target tracking. In this work, face candidates are localized using the features of the face area, edge information, and skin color. Non-face parts in the face candidates are further verified by the C-SVM learning model and then removed, by which the face targets can be generated with lower computation-complexity and satisfactory accuracy than other approaches. Finally, the face targets are tracked by an efficient and reliable searching scheme for improving the effective face detection rate. Experimental results show that the average face detection rate (FDR) of 85%, average effective FDR of 95%, a frame rate of 28–66 frames per second (fps), and about 30 faces detected per frame are obtained from various test videos with big dynamic crowds or numerous pedestrians, indicating the feasibility of the proposed method to achieve unconstrained face detection with high-efficiency and cost-effectiveness. This result makes the proposed method more attractive for the video surveillance system as compared to other approaches, especially in the high computational complexity-based methods.
Similar content being viewed by others
References
Bochkovskiy A, Wang C-Y, Liao HYM (2020) YOLOv4: Optimal speed and accuracy of object detection, arXiv preprint: arXiv:2004.10934v1, 23 Apr. 2020
Cárdenas RJ, Beltrán CA, Gutiérrez JC (2019) Small face detection using deep learning on surveillance videos. Int J Mach Learn Comput 9(2):189–194
Chen C-H, Chen T-Y, Huang D-Y, Hu W-C, Guo Z-B, Wen C-K (2018) Real-time face detection in big crowd through face candidates. In: Proc. of 8th international congress on engineering and information, pp. 76-77
Chen J-C, Rajeev R, Swami S, Amit K, Chen C-H, Vishal M-P, Castillo D-C, Rama C (2018) Unconstrained still/video-based face verification with deep convolutional neural networks. Int J Comput Vis 126(4):272–291
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. Proc Int Conf Comput Vis Pattern Recog 1:886–893
Fukui H, Yamashita T, Yamauchi Y, Fujiyoshi H, Murase H (2015) Pedestrian detection based on deep convolutional neural network with ensemble inference network. IEEE Intell Veh Symp (IV) 223-228
Hoiem D, Efros A-A, Hebert M (2008) Putting objects in perspective. Int J Comput Vis 80(1):3–15
Hu W-C, Chen C-H, Chen T-Y, Huang D-Y, Wu Z-C (2015) Moving object detection and tracking from video captured by moving camera. J Vis Commun Image Represent 30:164–180
Huang D-Y, Chen C-H, Chen T-Y, Hu W-C, Lin Y-L (2016) A vehicle flow counting system in rainy environment based on vehicle feature analysis. J Inf Hiding Multimed Signal Process 7(1):101–114
Ishii Y, Hongo H, Yamamoto K, Niwa Y (2004) Face and head detection for a real-time surveillance system. Proc Int Conf Pattern Recog 3:298–301
Ishii I, Ichida T, Gu Q, Takaki T (2013) 500-fps face tracking system. J Real-Time Image Process 8(4):379–388
Ji S, Lu X, Xu Q (2014) A fast face detection method combining skin color feature and adaboost. Proc Int Conf Multisensor Fusion Inf Integr Intell Syst 1–5
Ji P, Kim Y, Yang Y, Kim Y-S (2016) Face occlusion detection using skin color ratio and LBP features for intelligent video surveillance systems. Proc Federated Conf Comput Sci Inf Sys 253–259
Jin H, Liu Q, Lu H, Tong X (2004) Face detection using improved LBP under Bayesian framework. Proc Int Conf Image Graph 306–309
Krizhevsky A, Sutskever I, Hinton G-E (2012) ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 1097–1105
Kwon H-J, Lee S-H, Hosseini S, Moon J, Koo H-I, Cho N-I (2017) Multiple face tracking method in the wild using color histogram features. IEEE Int Symp Signal Process Inf Technol 51–55
LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324
Li Z, Xue L, Tan F (2010) Face detection in complex background based on skin color features and improved AdaBoost algorithm. Proc IEEE Int Conf Prog Inf Comput 2:723–727
Li J, Karmoshi S, Zhu M (2017) Unconstrained face detection based on cascaded convolutional neural networks in surveillance video. Proc Int Conf Image Vis Comput 46–52
Marciniak T, Chmielewska A, Weychan R, Parzych M, Dabrowski A (2015) Influence of low resolution of images on reliability of face detection and recognition. Multimed Tools Appl 74(12):4329–4349
Mita T, Kaneko T, Hori O (2005) Joint Haar-like features for face detection. Proc Int Conf Comput Vis 2:1619–1626
Niu G, Chen Q (2018) Learning an video frame-based face detection system for security fields. J Vis Commun Image Represent 55:457–463
Online available: https://data.gov.tw/dataset/40584. Accessed 3 August 2020
Phung S-L, Bouzerdoum A, Chai D (2002) A novel skin color model in YCbCr color space and its application to human face detection. Proc Int Conf Image Process 1:289–292
Qian Y, Bi M, Tan T, Yu K (2016) Very deep convolutional neural networks for noise robust speech recognition. IEEE/ACM Trans Audio Speech Lang Process 24(12):2263–2276
Rajeshwari J, Karibasappa K, Gopal Krishna M-T (2014) Survey on skin based face detection on different illumination poses and occlusion. Proc Int Conf Contemp Comput Inf 728–733
Redmon J, Farhadi A (2018) YOLOv3: An incremental improvement, arXiv preprint: arXiv:180402767v2, 8 Apr. 2018
Rekha N, Kurian M-Z (2014) Face detection in real time based on HOG. Int J Adv Res Comput Eng Technol 3(4):1345–1352
Sobel I, Feldman G (1968) A 3×3 isotropic gradient operator for image processing. A talk at the Stanford Artificial Project 271–272
Sobottka K, Pitas I (1998) A novel method for automatic face segmentation, facial feature extraction and tracking. Signal Process Image Commun 12(3):263–281
Tan M, Le QV (2019) EfficientNet: rethinking model scaling for convolutional neural network, arXiv preprint: arXiv:190511946v3, 23 Nov. 2019
Viola P, Jones M (2001) Rapid object detection using a boosted cascade of simple features. Proc Int Conf Comput Vis Pattern Recog 511–518
Xiong Z, Yao Z, Ma Y, Wu X (2019) VikingDet: a real-time person and face detector for surveillance cameras. Proc IEEE Int Conf Adv Video Signal Based Surveill 1:1–7
Yu M, Yun L, Chen Z, Cheng F (2017) Research on video face detection based on AdaBoot algorithm training classifier. Proc Int Conf Electron Instrumen Inf Syst 1–6
Zhang L, Chu R, Xiang S, Liao S, Li S-Z (2007) Face detection based on multi-block LBP representation. Proc Int Conf Biom 11–18
Zulhadi Z, Shahrel A-S, Junita M-S (2018) Hierarchical skin-AdaBoost-neural network (H-SKANN) for multi-face detection. Appl Soft Comput 68(7):172–190
Acknowledgements
This work was partly supported by a grant from Ministry of Science and Technology, Taiwan, under the contracts MOST 107-2221-E-212-012, MOST 107-2622-E-992-024-CC3 and MOST 106-2221-E-151-061.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Huang, DY., Chen, CH., Chen, TY. et al. High-efficiency face detection and tracking method for numerous pedestrians through face candidate generation. Multimed Tools Appl 80, 1247–1272 (2021). https://doi.org/10.1007/s11042-020-09780-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-09780-y