Non-Vehicle Wheeled Object Detection
What it does. Where it can be used: camera mount height, distance, and angle of view. Chained Classifications.Book a Demo
In Internal Testing
What it does:
Looks for the shape of a wheeled contraption that isn't a car or truck in video feeds. Will find everything from shopping carts, to wheelchairs, to ATVs, to strollers, to shipping u-boats, to wheelbarrows, to bicycles. If you are looking for a thing that has wheels and isn't a vehicle, this is the best place to look.
Allows you to create alerts, filter event feeds and 24/7 views based on the presence of a that wheeled thing. Allows you to run chained classification and recognition models.
Chained Classification Models
We're working on a classifier that separates the different types of objects found by the Non-Vehicle Wheeled Object Detector, so that you can search events by the subgroups like cart, wheelchair, shopping cart, etc, instead of just the main group of unsorted Non-Vehicle Wheeled Object events.
Interaction with Person Detections
Obviously, whenever a bike is moving, it is highly likely that a person is riding it. Depending on the wheeled object, the camera may not be able to see that person. Sometimes, a wheeled object detection will create a people detection alert, but not always. This depends on the position of the camera, the person, and the wheeled object.
In order to detect a cart, bike, or similar object in a video frame, the camera has to be able to see that vehicle at a minimum of 40x40 pixel. This means that there is a range of installation parameters for person detection to work correctly.
A computer vision model will only work as expected when used in the situation that it was developed around. This object detector was trained on bicycles, shopping carts, etc, outdoors. It was not trained on indoor video and performs erratically when used indoors. It will find chairs and vacuums and correctly report that it sees a wheeled things that is not a car. We recommend use outdoors, for these reasons. Models only work on their trained use case.
Camera Mounting Height
We recommend no higher than 8 or 9 feet for fixed lens cameras. Varifocal cameras or PTZ cameras will depend on the vertical angle and distance from the camera.
With all video analytics subject distance plays an important role. If the object is too far away it will make it difficult to differentiate the vehicle from the background or other objects. Detections are significantly less accurate with less than 80% of an object in the camera's view and almost impossible with less than 40% in view.
With survail you can detect an object that is as small as 20x20 pixels, but accuracy falls off if the object is not at least 40x40 pixels, so 40x40 is the default minimum object evaluation size. Accuracy increases as you increase the minimum object size. You can determine the minimum object size for survail to evaluate if an object is a person either globally (for all cameras) or with specific per-camera overrides.
Objects must be Mostly in View
Detections are significantly less accurate with less than 80% of an object or person in the camera's view and almost impossible with less than 40% of the object or person in view. When a car or person is mostly hidden behind a wall or only partially visible in the camera view, there won’t always be enough of the object’s outline visible to be able to know what the object is.
Limitation: Objects within Objects
When objects overlap it’s difficult to discern when one object starts and the other ends. Machine learning works by learning the background and then determining what an object is by looking at the outline of its shape.
Limitation: 100 Objects Evaluated per Frame
Computer Vision models for real time video need to move fast. If you need to analyze 15 frames per second, then your analysis can’t take longer than 1/15 of a second. This is why the most popular computer vision frameworks limit the number of objects that can be evaluated, unusually at around 100 objects per frame.
Training Data Limitation
Machine learning models work based on the data you give them, and only that data. The data collected to create the car detector uses 100% outdoor images and videos. Because of this, it can think that certain objects that it has never seen before, such as carts with wheels or chairs / tables with wheels are cars. We do not recommend running the car detector indoors.
This non-vehicle wheeled object detection model was NVIDIA. The classifier was made by Survail and will continue to learn.