Computer vision for people flow analysis in an underground metro station
One of our customers, a CCTV system integration company, requested us to develop a system to count people and measure people flow in underground metro. The purpose of the system is to assist platform load and passenger queues. The video surveillance system had been already deployed there and RTSoft should propose a hardware and software add-on by a very competitive price.
RTSoft helps customers to build AI + IoT applications through integration of computer vision, data analysis and augmented reality. Our experience in embedded platforms (Intel Movidius, Nvidia Jetson, Google Coral) and dedicated ML frameworks (Openvino, TensorRT, TFLite) made it possible to fulfill this project.
In the early stage of the project RTSoft built people recognition algorithms and tested them onsite on several CCTV cameras in the collaboration with cusomter’s technical team to identify possible set of use cases and draft requirement for the solution. Since the end-solution was supposed to be implemented based on RTSoft OMGE proprietary platform it was quite a simple task to rapidly design data flows, develop and bring up the system and then scale it to multiple CCTV cameras. Then RTSoft developed a deployment ready docker with all key components inside:
Video frames capture
People recognition
Graphical user interface
Target reports and statictis
OTA software updates.
Finally, the system was successfully installed and passed through performance, load balancing and acceptance tests and was acquired as a software product by our customer.
Array
(
[TAGS] => Linux, ComputerVision
[~TAGS] => Linux, ComputerVision
[ID] => 114
[~ID] => 114
[NAME] => Computer vision for people flow analysis in an underground metro station
[~NAME] => Computer vision for people flow analysis in an underground metro station
[IBLOCK_ID] => 10
[~IBLOCK_ID] => 10
[IBLOCK_SECTION_ID] =>
[~IBLOCK_SECTION_ID] =>
[DETAIL_TEXT] =>
Solution
In the early stage of the project RTSoft built people recognition algorithms and tested them onsite on several CCTV cameras in the collaboration with cusomter’s technical team to identify possible set of use cases and draft requirement for the solution. Since the end-solution was supposed to be implemented based on RTSoft OMGE proprietary platform it was quite a simple task to rapidly design data flows, develop and bring up the system and then scale it to multiple CCTV cameras. Then RTSoft developed a deployment ready docker with all key components inside:
Video frames capture
People recognition
Graphical user interface
Target reports and statictis
OTA software updates.
Finally, the system was successfully installed and passed through performance, load balancing and acceptance tests and was acquired as a software product by our customer.
[~DETAIL_TEXT] =>
Solution
In the early stage of the project RTSoft built people recognition algorithms and tested them onsite on several CCTV cameras in the collaboration with cusomter’s technical team to identify possible set of use cases and draft requirement for the solution. Since the end-solution was supposed to be implemented based on RTSoft OMGE proprietary platform it was quite a simple task to rapidly design data flows, develop and bring up the system and then scale it to multiple CCTV cameras. Then RTSoft developed a deployment ready docker with all key components inside:
Video frames capture
People recognition
Graphical user interface
Target reports and statictis
OTA software updates.
Finally, the system was successfully installed and passed through performance, load balancing and acceptance tests and was acquired as a software product by our customer.
[DETAIL_TEXT_TYPE] => html
[~DETAIL_TEXT_TYPE] => html
[PREVIEW_TEXT] =>
One of our customers, a CCTV system integration company, requested us to develop a system to count people and measure people flow in underground metro. The purpose of the system is to assist platform load and passenger queues. The video surveillance system had been already deployed there and RTSoft should propose a hardware and software add-on by a very competitive price.
RTSoft helps customers to build AI + IoT applications through integration of computer vision, data analysis and augmented reality. Our experience in embedded platforms (Intel Movidius, Nvidia Jetson, Google Coral) and dedicated ML frameworks (Openvino, TensorRT, TFLite) made it possible to fulfill this project.
System features:
Visitors headcount
Crowd headcount
Queue detector
GDPRA compliance
[~PREVIEW_TEXT] =>
One of our customers, a CCTV system integration company, requested us to develop a system to count people and measure people flow in underground metro. The purpose of the system is to assist platform load and passenger queues. The video surveillance system had been already deployed there and RTSoft should propose a hardware and software add-on by a very competitive price.
RTSoft helps customers to build AI + IoT applications through integration of computer vision, data analysis and augmented reality. Our experience in embedded platforms (Intel Movidius, Nvidia Jetson, Google Coral) and dedicated ML frameworks (Openvino, TensorRT, TFLite) made it possible to fulfill this project.
This update system is a cloud solution designed to increase the efficiency of automatic deployment of new software versions across the entire fleet of Smart Meters, store and update software in the cloud, and swiftly eliminate software bugs and security holes.
One of our partners, a prominent manufacturer of controllers and smart meters for power industry automation, oreder us to develop a software cloud solution for updating smart meter systems. This task is critical for managing a fleet of connected devices, either completely autonomous or not available for qualified on-site maintenance.
System features
The system is based on the RITMS UP2DATE platform created by RTSoft engineers. The platform allows users to update software swiftly, efficiently and reliably both in the global network and in corporate networks, including OEM partners.
The solution contains the following main components:
One of our customers, a CCTV system integration company, requested us to develop a system to count people and measure people flow in underground metro. The purpose of the system is to assist platform load and passenger queues. The video surveillance system had been already deployed there and RTSoft should propose a hardware and software add-on by a very competitive price.
RTSoft helps customers to build AI + IoT applications through integration of computer vision, data analysis and augmented reality. Our experience in embedded platforms (Intel Movidius, Nvidia Jetson, Google Coral) and dedicated ML frameworks (Openvino, TensorRT, TFLite) made it possible to fulfill this project.
RTSoft designed and developed the firmware for a smart robotics controller that makes the controller an excellent platform for educational and business uses.
The system software implements the abstraction interface for work with various sensors and actuators like ultrasonic, camera, thermo, photo, encoder motor, servo motor and many others in Real-Time. The programming API is available in python and C/C++.
The robotics platform features the color touch display with the graphical interface, which can also be customized by a user via the programming API.
Besides on-board GUI the solution implements two remote interfaces: WebDAV and ssh. Integration with a cloud is supported via MQTT protocol.
The connectivity is available via WiFi, Bluetooth and USB Ethernet. SD card and USB flash drives can be used to distribute data to/from the controller. Multiple controllers can be connected with each other via CAN interface where a Master controller can seamlessly operate with remote sensors and actuators connected to a Slave controller(s) in the same real-time manner.
RTSoft has been chosen by Motherson Innovation GmbH, an innovative automotive company, for prototyping “The Empathic Cockpit” – a digital cockpit of the future, harmoniously absorbing the newest available technologies for reaching a unique level of comfort and real-time functionality.
The solution was presented at the CES 2018 Show in Las Vegas.