Skip to main content

General Object Detection

Description​

General Object Detection is a tool that detects objects in an image using a pre-trained model. Where the user can select the category of objects to be detected.

Settings​

Model size​

The size of the model. The larger the model, the more accurate the detection but the slower the detection speed.

The following model sizes are available:

  • Tiny: The smallest model size. Fastest detection speed but lowest accuracy.
  • Small: Small model size. Fast detection speed but lower accuracy.
  • Medium: Medium model size. Medium detection speed and accuracy.
info

In our tests using CPU, the Tiny model approximately is 2x faster than the Small model, and the Small model is approximately 2x faster than the Medium model.

Categories​

A list of categories of objects to be detected. The following categories are available:

  • People
    • person.
  • Animals
    • dog, cat, bird, elephant, horse, sheep, cow, bear, zebra, giraffe.
  • Vehicles
    • bicycle, car, motorcycle, bus, truck.
  • Objects
    • knife, phone, scissors.
tip

You can use the name of the detected object as filters in the Counter tool. See Counter - Detected Class for more information.

NMS Threshold​

The NMS threshold is the minimum threshold for non-maximum suppression. Non-maximum suppression is a technique used to reduce the number of bounding boxes by removing the ones that overlap too much with other bounding boxes. A lower NMS threshold will result in fewer bounding boxes, but with potentially higher accuracy, whereas a higher threshold will result in more bounding boxes, but with lower accuracy.

For examples see Object Detection - NMS Threshold.

Confidence Threshold​

The confidence threshold is the minimum confidence score a detection should have to be considered valid. Detections with confidence scores below this threshold will be discarded. A higher confidence threshold will result in fewer detections, but with higher accuracy, whereas a lower threshold will result in more detections, but with potentially lower accuracy.

For examples see Object Detection - Confidence Threshold.

Display Results​

Overlay Results​

Whether to draw the results on top of the image frame.