What Is People Counting For?
People counting in public spaces is essential for the efficient management of stores, malls, airports, and passenger terminals. Beyond counting visitors, it offers advantages such as:
What Is the Traditional Approach to Counting People?
Traditionally, specialized people counting sensors have been used - they have evolved over the past 30 years as follows:
Infrared People Counters
These sensors count people by emitting infrared light beams and detecting interruptions to estimate the number of people.
Stereo People Counters
Stereo sensors improved counting accuracy by using cameras to calculate 3D distances and estimate the number of people based on size and shape.
ToF (Time-of-Flight) and LiDAR People Counters
Technologies like ToF and LiDAR made people counting more accurate by measuring distances with reflected light and creating 3D maps with lasers.
Evolution of traditional people counting sensor technologies over time.
The New Method for Large-Scale People Counting: AI on Security Cameras
A new player has recently emerged in the ecosystem - a counting technology with several advantages: AI applied to image processing with security cameras. It is a developing technology that extends counting coverage with high accuracy (above 99.9%). It also enables large-scale projects by reusing security camera infrastructure, reducing the required investment costs by 10x.
The Risk of Innovating with a New AI Counting Technology
AI has many advantages - but it comes with a risk: the current maturity level of the technology. Being a relatively new product, there are providers that do not have reliable counting algorithms and may deliver poor results.
An AI-based counting system must be evaluated by a professional, well-trained team within the company, because it is a maturing technology and you may find unreliable providers.
- 1
The provider must be reliable, with demonstrable experience and well-established clients in your industry.
- 2
It is important to request evidence of data accuracy - these can be live demonstrations and counting validation audits.
- 3
Evaluate the scalability of the system: Is it simple to install? Is it plug-and-play? Can it support many counting points? Does it integrate easily with your corporate systems?
- 4
Also consider that AI can extract much more data than just customer counting - it is advisable to research the extra features each system offers.
Advantages and Disadvantages of AI-Based People Counters
Advantages
Very low infrastructure costs
With what one traditional counter costs, you can install 10 AI-based counting points. You may even have zero cost if your cameras already exist for security purposes.
Greater reach and accuracy
A high-quality AI algorithm outperforms all types of traditional (overhead) people counting sensors in both counting reach and accuracy.
Scalability
With very low investment barriers, it can be deployed at large scale with ease.
More intelligence
By using image analysis, AI can detect more information and analytics than what is visible in the images.
Disadvantages
Risk of a bad outcome
Being a new technology, you must thoroughly and professionally evaluate your providers.
Conclusion
If you want a safe, traditional approach, it is recommended to use traditional people counting technologies. If you want to take advantage of current AI technologies to get their benefits, it is better to have a well-formed and trained team to evaluate different providers and make sure you will be successful.
Want to see KSI Vision's AI accuracy in your own cameras?
Request my demo
