Smart Crowd Analyzer
Over the last decade, retailers are facing significant obstacles, such a staff planning, unavailability of stocks, accumulation of unwanted items, and the inability to accurately forecast demand, etc. It has been known, that without adequate preparation and strategy, the attempt to ca
2025-06-28 16:35:13 - Adil Khan
Smart Crowd Analyzer
Project Area of Specialization Internet of ThingsProject SummaryOver the last decade, retailers are facing significant obstacles, such a staff planning, unavailability of stocks, accumulation of unwanted items, and the inability to accurately forecast demand, etc. It has been known, that without adequate preparation and strategy, the attempt to capture more of the market is useless.
When a customer shops from a store, many questions come in mind of retailers such as what items were purchased? At what time? How long did they shop? and so, that retailers struggle to understand what data to focus on.
Nowadays customer has an abundance of choices and their preferences changes, making it difficult for retailers, to keep up with the trends as well as customer's shopping behavior. Complex retail operations and management is also not an easy task for retailers. All these problems result in poor performance/sales, and ultimately, result in profit loss. Thus, to prevent these issues, we propose an effective method, based on crowd analysis and AI, for better retail operations, customer satisfaction, and profit.
This project is modeled upon a people counter, namely, "Smart Crowd Analyzer", which is a bidirectional wireless crowd analysis device based on a smart networked video-camera that analyses crowd using artificial intelligence and deep learning algorithm. The project is based on prior research with the addition of embedded features such as group detection, age detection, height detection, gender determination, regular customer detection, and bag detection. These features allow us to determine a pattern in the customer’s behavior.
The methodology adopted in this work is to track and count people individually as well as in a group. The dataset is obtained by capturing images and by calibrating the camera position at the entrance to achieve precise camera projection. According to the traits, an analytical report is generated, that optimize sales, and helps in producing efficient marketing schemes.
The proposed work is aimed to gain deep analysis and tracking in retail operations. Furthermore, a comprehensive understanding of customer behavior and interaction, not only help retailers to build a relationship of loyalty with the customers but also help retailers in amplifying their sales and create mass production. The project also aims to aid our investors in tracking their business (especially when they have chain stores), automate task distribution, and ensure proper working process, such as automatically sends a message for the restocking.
For Future aspects, the proposed algorithm can be modified by adding an object detector, in case of theft/for security purposes. Further improvements can be made in the data collection section, such as setting goals, maintaining customer record and creating a backup on Cloud.
Adopting deep learning algorithms, the product features an accuracy of 97% or greater, a smart crowd analyzer that tops the industry of crowd analysis devices.
Project ObjectivesThe objective of the project is to develop an algorithm to count and monitor multiple people and through their traits, we predict the need for availability of that precise (size) of the item and through analyses of the sales, we comprehend the restocking of items.
The goal of this project is to use open-Frameworks C++ application on the Raspberry Pi to handle the camera input, image abstraction, tracking, and people counting.
- Detect the gender of people visiting.
- Detect the age of people with respect to classified age groups.
- Detect the height of customers, for future stock management.
- Detect the shopping bags of customers, estimating the number of people satisfied with the products.
- Detect the regular customers, for bridging the gap between retailers and customers. Also generating some discounts or priority for them.
- Detect groups of people visiting a shop. Hence, will be able to comprehend the days/ the month, when families or groups mostly visit a shop/retail.
- Generate stats live time.
- Generate monthly and yearly chart reports.
The methodology adopted for the features are:
Age Detection:
Once facial features (e.g. eyes, nose, mouth, etc.) are localized by PiCamera, their sizes and distances measured, ratios between them are calculated. Then, face classification is done into different age categories according to self-made rules. PiCamera will detect facial features live time and will compare it with models on which the system would be trained. LBP descriptor variations and a dropout-SVM classifier will be used to increase the accuracy of detection.
Gender Detection:
Webers Local texture Descriptor will be used for gender recognition, demonstrating near-perfect performance on the FERET benchmark. Popular Labeled Faces in the Wild (LFW) benchmark, primarily used for face recognition, will be used for this project. The method is a combination of LBP features with an AdaBoost classifier. As with age estimation, the main focus will be on the Adience set which contains images more challenging than those provided by LFW.
Height detection:
Through HoG (History of Orientated Gaussians) and SVN (Support Vector Machines) detector, tracking will be computed. The height of the person will be obtained by measuring the height of the contour of that person, after getting the coordinates from the bounding box pixel height is estimated. Afterward, some correlation could be estimated between pixel height and real-world height.
Group of People Detection:
HoG (History of Orientated Gaussians) and SVN (Support Vector Machines) detector will help to compute the tracking (similar to counter and height detection). In this case, contour dependence on each other is checked with time. From the initial position to the final position. If their contours have some relatable movement and are close to each other, it means that they are of the same group. Hence, this way, a group of peoples in the area will be detected.
Bag Detection:
Detection of shopping bags or objects would be done with SVN detection and HOG (as in the height detection). This bag-shaped contoured would be classified by the library. Region-based Convolutional Neural Networks, or R-CNNs, is a family of techniques for addressing object localization and recognition tasks, designed for model performance.
Regular Customer Detection:
Datasets will be generated containing the different faces of customers coming inside. Then, if that person comes again and his facial features will be matched with previously-stored datasets. It will be deduced that the person is a regular customer in a retail store.
Statistics Generation:
Data will be displayed in Chartjs.org. ChartJS is a lightweight javascript library that uses HTML5 and Canvas to generate and render charts. It will display data in a number of different chart types such as pie, bar, line and polar. It will obtain data from the database (MySQL, PHP, and Javascript) and then generate, display and update charts.
The project will provide a user with many benefits.
- A variety of embedded features such as group counting, age, height, gender determination, regular customer detection, staff exclusion, and bag detection.
- In group counting, our study has the capability to count groups of people rather than picking them off as individuals. It will comprehend the number of families/groups that visit a specific location and a specific time.
- It also distinguishes the person entering or leaving a particular place so that they are not counted twice in the total amount.
- Physical characteristics such as age, height, and gender, will result in knowing what age group of the common people is interested in certain products, coupled with the dominant gender of the people.
- Through this project, we hope that retailers will gain deep insights into retail operations and it will help them in producing effective marketing initiatives.
- It will help them develop a comprehensive understanding of customer behavior and interaction within stores or in shopping malls and public environments.
- This project will also aid our investors in tracking their business especially when they have chain stores.
- To conclude, it will help in increasing their sales and will create mass productivity, hence, their business will flourish.
Our Project service includes:
- Crowd Management
- Staff Management
- Visual Surveillance
- Customer Service
- Public Space Designing
- Data Analysis
After the implementation of the project, we hope to achieve:
- An Accuracy of 97% or more, which will make campaign marketing more effective.
- A Full HD 32MP Resolution of the wireless smart video-camera.
- Wide opening counting capability, that ensures accurate traffic counting at all entrances and end zones.
- Security Assurance.
- Bidirectional Pathway
- A better solution, achieving several advantages over other systems, such as more accuracy in conversion rate, easy installation, lesser human intervention, direction detection, etc.
- Data will be easily exported into any business intelligence through built-in integration modules.
- Excellent Quality Control and Stability
- Accurate statistics generation of people (Gender, Age, Height, Groups, Bag detection, and Regular Customers) at the end of the month and year accordingly.
- User-Friendly Interface.
| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 80000 | |||
| NVIDIA Jetson Nano Development Kit | Equipment | 1 | 30000 | 30000 |
| Stationary | Miscellaneous | 1 | 5000 | 5000 |
| HDMI Display | Equipment | 1 | 15000 | 15000 |
| NVIDIA Jetson Nano Accessories | Equipment | 1 | 3000 | 3000 |
| USB Camera | Equipment | 1 | 22000 | 22000 |
| Printouts and Documentation purposes | Miscellaneous | 1 | 5000 | 5000 |