Object detection is the process of finding instances of real-world objects such as persons, cars, vehicle, animals, bicycles and buildings in images or videos.
Object detection algorithms typically use deep learning algorithms to recognize instances of an object category.
Given an image or a video stream, an object detection model can identify which of a known set of objects might be present and provide information about their positions within the image. It will output a list of the objects it detects, the location of a bounding box that contains each object, and a score that indicates the confidence that detection was correct.

An object detection model is trained to detect the presence and location of multiple classes of objects.

Software has been trained to detect more than 1000 objects.
To interpret results, you can look at the score and the location for each detected object. The score is a number between 0% and 100% that indicates confidence that the object was genuinely detected.

The closer the number is to 1, the more confident the model is.

You can decide a cut-off threshold below which you will discard detection results.

For our example, we might decide a sensible cut-off is a score of 30% (meaning a probability that the detection is valid). In that case, we would ignore the last two objects in the array, because those confidence scores are below 30%

The cut-off you use should be based on whether you are more comfortable with false positives (objects that are wrongly identified, or areas of the image that are erroneously identified as objects when they are not), or false negatives.