Unattended Objects
A foreign object in the lane is always a potential cause of dangerous situations. Both large and small objects can lead to an accident, because not all drivers respond to obstacles on time and correctly. Roadly allows you to quickly identify dropped and abandoned items and improve the road safety.
Solution metrics
95%
Recognition accuracy
Accuracy measured on test videos in the daytime
- < 3
Number of false positives per day per camera
≥ 10 FPS
Frames per second
requirement
≥ HD
Recommended video stream quality
10 px
Object size requirements in the frame
per objects
Technology Description
An object on the road is not recognized as an "event" by the conventional CCTV cameras. Meanwhile, a dropped or left item, even a small one, is a potential threat. In an attempt to avoid it, the driver may suddenly pull the car to the side, which can lead to a collision.
Road services are not able to constantly monitor the objects on the roads. Even with the existing surveillance cameras, the operators do not always have enough time to detect such an object in a timely manner, especially in a dense traffic flow.
Roadly is able to detect the presence of a stationary object (foreign object) on the lane or in another control zone with an advanced detection algorithm.
Road services are not able to constantly monitor the objects on the roads. Even with the existing surveillance cameras, the operators do not always have enough time to detect such an object in a timely manner, especially in a dense traffic flow.
Roadly is able to detect the presence of a stationary object (foreign object) on the lane or in another control zone with an advanced detection algorithm.
- Improving traffic safety due to the timely detection and elimination of foreign objects.
- Reducing the risk of accidents caused by the presence of dropped loads, abandoned objects, etc.
The Roadly system, unlike conventional video cameras, is capable of detecting the presence of a stationary object (foreign object) on the road or in another monitoring area. The algorithm for identifying such an object involves background analysis and a series of operations for processing event candidates, based on which the system notifies about a dropped object.
Screenshots and demo videos
Features of the technology
Instant recognition
Operating in heavy traffic
Automatic notification
Improving traffic safety