| Description | To train neural networks, |
...
you must collect and submit to AxxonSoft |
...
videos and images from your actual cameras taken in the same resolution and |
...
in the same conditions as in your future application. For example, if you need your neural network |
...
to work outdoors, videos must contain all |
...
weather conditions (sun, rain, snow, fog, |
...
and so on) in different times of day ( |
...
...
evening, night). If the collection requirements for the data submitted for training the neural network model are met, and if you operate the neural network in the conditions that are as similar as possible to the conditions in which the data was collected, we guarantee the overall accuracy (training in operating conditions) of neural network analytics from 90% to 97% and the percentage of false positives of 5-7%. For general neural networks (training wasn't performed in operating conditions), we guarantee the overall accuracy of 80-95% and the percentage of false positives of 5-20%. The requirements can be changed or added to at any time |
| General requirements for collected data |
...
...
- data, specific requirements for object images, scene, angle, lighting,
|
...
...
...
neural network in different conditions of time of day, lighting, angle, object types, or weather,
|
...
...
...
...
Example. It is necessary to detect a person in the surveillance area at night and during the day. - Data collected correctly:
|
...
- videos of the surveillance area, each five minutes long are submitted for training;
- the object of interest appears in the frame in each video
|
...
...
- videos were recorded in night conditions, two—in daytime conditions.
- Data collected incorrectly:
|
...
- videos of the surveillance area, each five minutes long are submitted for training;
- the object of interest appears in the frame in each video
|
...
- ;
- two fragments were recorded in night conditions, one—in daytime conditions
|
...
...
| Additional requirements for |
...
| collected data for each neural analytics tool |
...
ToolNeural Filter| Neurofilter | At least 1000 frames containing different objects of interest in the given scene conditions, and the same number of frames containing no objects (noise frames) |
|
Neural Tracker | Three to five video | videos containing objects of interest in the given scene conditions. The more the number and variability of the situations in the scene, the better |
|
Posture detection tools| Pose Detection | 10 seconds of video of a scene with no persons.
At least 100 different persons in the given scene conditions.
Attention! Different conditions mean, among others, different |
|
postures an individual tilting limbs patterns, etc.)Personal protective equipment detection toolspositions of body parts, and so on) | Equipment detection (PPE) | A list of all reference equipment with examples must be collected from the object and |
|
agreed Several video recordings each of videos with personnel in the given scene conditions.
Personnel must move and change |
|
posture position in the collected |
|
video recordingsvideos, as well as remove and put on equipment at intervals of 30 seconds.
Since the |
|
Personal protective equipment detection tools are designed for artificial constant lighting, |
|
video recordings videos in other lighting conditions |
|
are not Fire and Smoke detection tools| PPE detection VL | | Fire Detection | At least 1000 frames containing different objects of interest in the given scene conditions, and the same number of frames containing no objects (noise frames) |
|
Object presence detection tool| Smoke Detection | | Object Presence Detection | At least 1000 frames containing different objects of interest in the given scene conditions, and the same number of frames containing no objects (noise frames) | | Food recognition |
|
* | Images of at least 80% of the actual menu items must be provided. Each menu item requires 20 to 40 images shot in different conditions |
|
...
...
This analytics will be available in future versions |
|
|
...
** Accuracy is indicated for a neural network model, which was trained under operating conditions.
*** A general neural network is a neural network that was not trained under operating conditions.
...
