Go to documentation repository
Documentation for Intellect 4.11.0-4.11.3. Documentation for other versions of Intellect is available too.
There are three types of object classification by the smart detection tools in Intellect.
- Standard. The following objects can be classified: a human, a vehicle, and other object (see Cross line detector configuration and Motion in the Area detector configuration). The method is based on determining the ratio of width to height of an object: if the width is greater than the height—a vehicle, if the width is less than the height—a human.
- Advanced. The following objects can be classified with higher accuracy due to fine-tuning: a human, a group of humans, a vehicle, noise, an object carried into the area, an object carried out of the area, other object (see CAM_VMDA_DETECTOR VMDA detection).
- Neural filter is a neural network-based classification. Any objects can be classified to a high precision. The neural network is trained individually for each use case. See Configuring the neural filter.
Overview
Content Tools