FootfallCam Centroid™
Adding AI Video Analytics to Your Existing CCTV
- Processes up to 8 CCTVs in real-time
- Designed for human and car detection
- Conjunction with FootfallCam people counter and/or any CCTV cameras
- Easy to install, maintain, and integrate on FootfallCam Server or On-Premise Server.
- Made in UK; Manufactured by ODM
About this item
FootfallCam Centroid™ processes up to eight HD full-motion video streams in real-time and can be deployed as a low-power edge intelligent video analytics platform for Network Video Recorders (NVR), smart cameras, and IoT gateways. Applications include human detection, pose estimation and car detection.
2D AI Video Analytics
It has a powerful processor to deploy as a low-power edge intelligent video analytics platform for Network Video Recorders (NVR), smart cameras and IoT gateways. FootfallCam Centroid™ carries out object detection and classification for any industry.
- Pedestrian counting
- Vehicle counting
- Area counting (eg: Crowd counting)
- Profile tracking
- Path tracking


Multi stream video analytics
FootfallCam Centroid™ can be connected to up to 8 CCTV cameras for maximum coverage and cost-effectiveness. The videos from PoE Switch/ DVR/ NVR are processed in real time to generate in-depth data analytics. The aggregated data from each raw video stream are available to be accessed through FootfallCam Analytic Manager V9™ with read-made modules and reports.
Learn MoreData analytics for both indoors & outdoors
Data analytics of FootfallCam Centroid™ only required videos and connection between FootfallCam Analytic Manager V9™. The deployment can be carried out for public areas, be it sheltered or unsheltered. For example: Football fields, public squares, amusement parks, museums, and more.
View Industry Solutions
Related Products
FootfallCam Centroid™
Crowd Detection in Large Area
-
Crowd Control to avoid Stampede
Keep track of crowd density to prevent congestion and chaotic at peak hours. -
Monitor Real-Time Occupancy Level
Live occupancy data with visual warnings and alerts when limits are approached or exceeded. -
Crew and Team Allocation
Divide the workforce into groups based on real-time situations.
Outdoor Street Counting
-
Measure Pedestrian Volume
Measure the usage of public facilities such as walk-way, pedestrian crossing or footbridge by traffic volume in order to improve or build new infrastructure in high-traffic areas as part of the planning in smart city. -
Measure Public Facility Usage
Measure the usage of public transportation to make informed infrastructure decisions such as improved bus routes or bigger shelters at popular locations

Vehicle counting/ License Plate Recognition
-
Adaptable in any Conditions
Work under challenging vision conditions such as snow accumulation, varying lighting conditions, partial occlusion from other vehicles. -
Replace Sporadic Counting
Act as road paradox to identify root cause of the inevitable traffic congestion in the city core.- Diversion planning can be done at peak hours on a daily, monthly or yearly event basis.
- To analyze the road traffic density, especially in mega cities, for future city planning.
-
Monitor Car Park
Run effectively on monitoring traffic flow in the car counting solution. It provides real-time occupancy of the car parks, analytics data of car park utilisation, and allows Big Data Benchmarking with industrial parking data such as traffic counting, average parked duration, and zone analytic.
Empty Shelf Detection
-
Stock Replenishment
- Identify the shelf out-of-stock with image processing.
- Generate an automated notification alert for store managers.
-
Enhance Customer Experience
- Reduce customer frustration based on out-of-stock information and data on fast-selling items.
- Allows the system to forecast item demand.
Skeleton Tracking
Answering managerial concerns based on data-driven metrics and analysis.
-
Product Engagement Analysis
By combining human motion tracking with product location, it is able to conduct product engagement analysis in multi-level such as area level, shelf level as well as product level. -
Pose and Behaviour Tracking
To optimize human detection and differentiate from other objects with features such as shoulders, elbows, hands and knees.
FootfallCam Centroid™
GENERAL SPECIFICATION |
|
---|---|
Model |
Centroid |
Weight |
270gm |
Casing Colour |
Black |
Casing Material |
Metal |
Total Dimensions |
104mm(W) x 81mm(D) x 60mm(H) |
Warranty |
1 year from first allocation date* |
* Warranty extension available upon request
PROCESSOR SPECIFICATION |
|
---|---|
CPU |
64-bit Quad-core 1.43GHz |
GPU |
128-core 921MHz |
Memory |
4GB 64-bit LPDDR4 1600MHz | 25.6 GB/s |
Video Encoder |
4Kp30 | (4x) 1080p30 | (2x) 1080p60 |
Video Decoder |
4Kp60 | (2x) 4Kp30 | (8x) 1080p30 | (4x) 1080p60 |
Power |
10W |
INTERFACES SPECIFICATION |
|
---|---|
USB |
4x USB 3.0 A (Host) | USB 2.0 Micro B (Device) |
Display |
HDMI | DisplayPort |
Networking |
Gigabit Ethernet (RJ45) |
Wireless |
M.2 Key-E with PCIe x1 |
Storage |
MicroSD card (16GB UHS-1 recommended minimum) |
SIM Card |
4G/LTE/3G |
Other I/O |
(3x) I2C | (2x) SPI | UART | I2S | GPIOs |
Power Supply |
5V4A DC Power Adapter |
OPERATIONAL |
|
---|---|
Average Data Transfer Rate* |
5.0 kilobytes/hour |
* Average Data Transfer Rate is measured with a pre-defined sample size of 20 requests per hour.
Product Specification

Installation Types