OpenMV
Shields
Lens
Robotics
Book
Video
Download
Docs
Forum
OpenMV.io
GithubThe issue of pets not being leashed remains a recurring management challenge in communities and parks—visible yet difficult to regulate. Manual inspections are prone to blind spots, while conventional surveillance systems struggle to automatically identify detailed behaviours. With OpenMV, whether a pet is leashed or not can now be directly recognised by the system for the first time.

In public areas such as communities, parks, and pedestrian streets, pets being left off-leash is a frequent and difficult-to-manage issue.
Manual inspections are prone to temporal and spatial blind spots, while conventional video surveillance—although capable of “seeing”—struggles to automatically determine the specific behaviour of “leash usage,” resulting in insufficient enforcement. Leveraging SingTown’s OpenMV intelligent cameras, the system employs AI-powered visual capabilities to automatically identify on-site pet leash status, thereby providing technical support for civilised pet ownership management.
Cameras are deployed at community entrances and exits, major passageways, or key areas to continuously capture footage.
OpenMV runs object detection algorithms on the edge device to simultaneously identify “humans” and “pets” in the image, and further analyses small targets between them. By combining leash-line feature recognition with spatial relationship modelling, it determines whether the pet is under effective restraint.
When the system detects a scenario where a person and their pet are walking together without a leash, it can instantly output the result on the device side, trigger voice alerts via connected devices, or report the incident to the community management platform to enable prompt intervention.
OpenMV deploys complex visual recognition and decision-making logic directly on the camera edge device, offering advantages such as low power consumption, low latency, and no requirement for continuous internet connectivity—making it suitable for long-term operation scenarios such as communities and parks, thereby upgrading civilized pet management from “passive persuasion” to “proactive identification.”

AI Sentinel Based on OpenMV: Automatic Alert for Unattended Key Locations
Automatically detects whether the door of a key location remains open for an extended period and issues a timely alert.

Personnel crossing boundary triggers an alarm; OpenMV interprets the “sense of security boundary”
Detecting personnel or equipment crossing virtual perimeter lines.

“AI Urban Management Officer” is Here: An Automated Street Vending Detection System Built on OpenMV
Automatically identifies illegal street vending activities to support daily urban governance.

Improper placement of gas cylinders? Use OpenMV to automatically trigger hazard alerts
Automatically identifies non-compliant placement positions of gas cylinders to proactively detect potential gas safety hazards.

Did you perform live-line work without wearing insulating gloves? OpenMV will immediately issue an alert!
Automatically identifies whether workers are wearing insulating gloves to assist in safe operations.

Utilising the OpenMV smart camera to identify surface defects on aluminium plates in real time
Online identification of defects on aluminium plate surfaces, such as scratches and dents, to support quality control.