In the reality of 2021's Covid-19 pandemic there are a lot of government's restrictions made to reduce the virus spread speed in the society. One of the examples of such restrictions are the people per square meter limit in public places and shopping malls. Because manual counting of each person in such places is not possible due to limited time and money resources, this limit restriction is widely abused making the pandemic outbreak more dangerous. To face this problem author has presented a novel face and body detection model for the CCTV (Closed Circuit Television) monitoring systems, that automatically counts the amount of people in the monitored area by the use of Deep Learning.
and Kim [
In this paper a model of a Lightweight Convolutional Neural Network is proposed. The model is focused on fast detection of human upper-body and faces to roughly count the amount of people in the desired area.
The final network model was developed with an intention to be as light-weight as possible, maintaining the high accuracy. In order to achieve this the number of layers, as well as, the synapse count was kept at a bare minimum. The final model can be seen in Fig. 1.
As presented, the developed CNN (Convolutional Neural Network) contains 3 main convolutional segments followed by max polling. In the first, and third segment the kernel size is set to 5x5. In the middle segment however the filter sizes are varying and are set to 7x7, 5x5 and 3x3 in order to extract as many features as possible. All convolutional layers are followed by the ReLU (Rectified Linear Unit) activation function.
The pooling layers were set to reduce the image by a factor of 2.
• body, • no-body.
And the second one: • face, • no-face.
In presented detection model two neural networks were used for the final prediction. The first one was detecting 2 abstract classes: This approach, despite the fact of being slower, have the advantage over the classical one-network models in terms of the final customization. Because these two main classes are separated we can fine-tune the detection system after the training and set diferent detection thresholds for bodies and faces which can lead to much more accurate people count predictions.
Presented neural network model has achieved a high accuracy of over 99.94% for both the face and the body detection. Final metrics are shown in Tab. 2 and the training plots can be found in Fig. 2. The final confusion matrices are in Fig. 3 and Fig. 4.
Used metrics are: • Accuracy, • Precision, • Recall, • F1, • Specificity, • FDR (False Discovery Rate), • FPR (False Positive Rate), • FNR (False Negative Rate), • FOR (False Omission Rate), • NPV (Negative Predictive Value).
The results of the final system are shown in Fig. 6. In all examples the system was set with the same, default parameters to present the accuracy "out of the box". Because of the dual-CNN model there is a possibility to better fit the parameters to the specific camera and view making the predictions even more accurate.
In Fig. 5 there is one of the examples of the system in action. As we can see in most cases the CNN correctly detects human silhouettes on the image and draws a bounding box around them. In some cases, however, especially on the dark background the system has a problem to correctly detect the body and the certainty is too low to recognize this batch as a human. In some other regions of the image (especially on the left top) there are some inverted examples, when batches of the image are falsely recognized as the body.
This problems are mostly due to the fact that the model was made to be more general and to work in most common scenarios. To improve the classification and to better fit the specific camera, the fine-tuning of detection parameters, as well as, some post-training would be necessary. 1–9
Detection Model
This work
Hsu, Abdel-Mottaleb, and Jain [
Because of the global Covid-19 pandemic many governments prepared restrictions to the amount of people per square meter in public places such as shops and shopping malls. This approach, except of allowing shops to be run at all, created a huge logistical problem of counting the amount of people inside the desired area. To follow this restrictions every shop owner had to create some way of dealing with this problem. In smaller, regional shops the problem is almost non visible due to the fact that there are only allowed 2-3 people for entire building and the shop owner can easily count the people manually. In bigger shops however, where limits are much bigger, the problem starts to occur because the shop personnel has to serve the clients and have no time and possibility to count every new guest. Some owners deal with it by hiring additional personnel just for this purpose, however it is very expensive and especially in times of global pandemic, when the income is much smaller, this method is far from optimal. Even worse situation is in much bigger places such as shopping malls and other big, public places. Because there are many entrances and exits the manual counting even with additional personnel would be near impossible from the financial and logistical point of view, so in most places government restrictions are violated.
Presented system was made to address these problems with a minimal financial footprint, allowing shop owners to eficiently control the number of people in the monitored area and because of that respect the oficial restrictions and actively fight with the pandemic outbreak.
As we can see presented Lightweight-CNN solution allows the user to quickly count people located in a store, in a shopping mall or in any open public space with small resource, money and power consumption. Because of the high efectiveness of face and body detection the presented system counts the amount of people with high accuracy and due to the light-weighted architecture it does it in real-time even on high resolution cameras. What’s more the small architecture allows the system to run even on smaller and less powerful devices such as laptops or, for example, Raspberry Pie. Because of that it reduces the need of more expensive and much more power hungry PCs making it more environment friendly.
Author would like to acknowledge contribution to this research from the Rector of the Silesian University of Technology, Gliwice, Poland, under program “Initiative of Excellence—Research University” grant no. 08/IDUB/2019/84.