Human Faces Detection and Tracking for Crowd Management in Hajj and Umrah
Source abstract
Abstract
Hajj and Umrah are two main religious duties for Muslims. To help faithfuls to perform their religious duties comfortably in overcrowded areas, a crowd management system is a must to control the entering and exiting for each place. Since the number of people is very high, an intelligent crowd management system can be developed to reduce human effort and accelerate the management process. In this work, we propose a crowd management process based on detecting, tracking, and counting human faces using Artificial Intelligence techniques. Human detection and counting will be performed to calculate the number of existing visitors and face detection and tracking will be used to identify all the humans for security purposes. The proposed crowd management system is composed form three main parts which are: (1) detecting human faces, (2) assigning each detected face with a numerical identifier, (3) storing the identity of each face in a database for further identification and tracking. The main contribution of this work focuses on the detection and tracking model which is based on an improved object detection model. The improved Yolo v4 was used for face detection and tracking. It has been very effective in detecting small objects in high-resolution images. The novelty contained in this method was the integration of the adaptive attention mechanism to improve the performance of the model for the desired task. Channel wise attention mechanism was applied to the output layers while both channel wise and spatial attention was integrated in the building blocks. The main idea from the adaptive attention mechanisms is to make the model focus more on the target and ignore false positive proposals. We demonstrated the efficiency of the proposed method through expensive experimentation on a publicly available dataset. The wider faces dataset was used for the train and the evaluation of the proposed detection and tracking model. The proposed model has achieved good results with 91.2% of mAP and a processing speed of 18 FPS on the Nvidia GTX 960 GPU.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Video Surveillance and Tracking Methods · Face recognition and analysis · Remote-Sensing Image Classification
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (42)
Show source-provided references
1. Pandey · Deep Learning for Image Processing Applications · 2017 · 31 · 1
2. Indoor image recognition and classification via deep convolutional neural network
3. Deep learning-based application for indoor scene recognition
4. A convolutional neural network to perform object detection and identification in visual large-scale data10.1089/big.2019.0093 ↗
5. Traffic signs detection for real-world application of an advanced driving assisting system using deep learning10.1007/s11063-019-10115-8 ↗
6. Design of a face recognition system based on convolutional neural network (CNN)10.48084/etasr.3490 ↗
7. Image inpainting based compact hash code learning using modified U-net
8. Class-driven content-based medical image retrieval using hash codes of deep features10.1016/j.bspc.2021.102601 ↗
9. A survey of deep neural network architectures and their applications10.1016/j.neucom.2016.12.038 ↗
10. B. Alexey, C. Y. Wang and H. Y. M. Liao, “Yolov4: Optimal speed and accuracy of object detection,” arXiv preprint arXiv:2004.10934, 2020.
11. CSPNet: A new backbone that can enhance learning capability of CNN
12. Spatial pyramid pooling in deep convolutional networks for visual recognition10.1109/TPAMI.2015.2389824 ↗
13. Path aggregation network for instance segmentation
14. Wider face: A face detection benchmark
15. Pedestrian detection based on light-weighted separable convolution for advanced driver assistance systems10.1007/s11063-020-10367-9 ↗
16. Pedestrian detection for advanced driver assistance systems using deep learning algorithms
17. YOLO9000: Better, faster, stronger
18. I. Forrest, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally et al., “SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size,” ArXiv preprint arXiv:1602.07360, 2016.
19. Crowd monitoring and classification: A survey
20. Deep urban event: A system for predicting citywide crowd dynamics at big events
21. Convolutional LSTM network: A machine learning approach for precipitation nowcasting
22. CCCNet: An attention based deep learning framework for categorized counting of crowd in different body states
23. Deep learning models for analysis of traffic and crowd management from surveillance videos
24. Ssd: Single shot multibox detector
25. Dense crowd counting from still images with convolutional neural networks10.1016/j.jvcir.2016.03.021 ↗
26. R. Joseph and A. Farhadi, “Yolov3: An incremental improvement,” ArXiv preprint arXiv:1804.02767, 2018.
27. Aggregated residual transformations for deep neural networks
28. Imagenet large scale visual recognition challenge10.1007/s11263-015-0816-y ↗
29. Densely connected convolutional networks
30. Feature pyramid networks for object detection
31. Attention is all you need
32. CutMix: Regularization strategy to train strong classifiers with localizable features
33. Focal loss for dense object detection
34. Rethinking the inception architecture for computer vision
35. UnitBox: An advanced object detection network
36. Distance-IoU loss: Faster and better learning for bounding box regression
37. CBAM: Convolutional block attention module
38. Finding hard faces with better proposals and classifier
39. Robust face detection via learning small faces on hard images
40. Deface: Deep efficient face network for small scale variations10.1109/ACCESS.2020.3012660 ↗
41. YOLO-Face: A real-time face detector10.1007/s00371-020-01831-7 ↗
42. RetinaFace: Single-shot multi-level face localisation in the wild