4.Advanced Settings
4.1Set the detector
 |
1. You can make the following settings in [Set the detector]. - [Detector number]: Select the detector you want to use. You can select from detectors 1 to 3. (Detector number): (Detector name) will be displayed. Default: 1:Detector1 - [Learning Model Name]: You can enter up to 20 half-width characters. Default: Detector1 to 3 - [Initialize detector]: Check this when clearing the learning information of the detector selected in [Detector number] and executing new learning. - [Set]: Click to reflect the settings. |
4.2Set Detection Object
 |
|
1. [Function] You can set the Detection Function for each of the five [Detection Objects]. [New object]: You can add a new object you want to detect. [Improving false detection]: Improve false detection of human, vehicle and bicycle. [Improving missed detection]: Improve missed detection of human, vehicle and bicycle. 2. [Name] Set the name of detection object. You can set up to 20 half-pitch characters. 3. [Target] If [Improving false detection] or [Improving missed detection] is selected for [Function], select detection object to be improved. Select from [Human], [Vehicle], and [Bicycle]. 4. Trash box icon If you press the [Set] after clicking, the settings for the selected detection object will be deleted. Settings to be removed: [Function], [Name], [Target], Settings of bounding box, Settings of [Training data expansion] 5. [Set] Click to reflect the settings. |
4.3Advanced learning settings
|
 |
1. [Expanded learning data Screen] You can automatically increase the variations in learning images when it is impossible to collect dark or reversed images in the actual environment. Click [Display] to open the settings screen. |
 |
・ [Brightness] - To correct the brightness, select [Correct brightness]. When this is selected, set the [Maximum] and [Minimum]. - [Maximum]: Sets the highest value in the brightness range. 0 to 128 - [Minimum]: Sets the smallest value in the brightness range. -128 to 0 ・ [Invert] - Select from [Invert left/right] or [Invert vertically]. ・ [Color] - Select whether to add the black-and-white images for the learning image. To add a black-and-white converted image to a learned image. Select [Black-and-white image] to add a converted image. ・ [Applicable detection object] - Select the Detection object to which [Training data expansion] applies. Check the detection object to which [Training data expansion] applies. ・ [Set] - Reflect the settings and return to [Advanced learning settings]. |
2. [Distinguish between colors] To perform learning by converting all learning images to black-and-white images, select [Off]. Learning by setting it to [Off] also makes it easier to detect color-coded detection object. Default: [On] |
4.4Saving the learning image
 |
|
4.5Perform Learning Screen
 |
|
4.6Demo screen
 |
|
4.7Simulation Screen
 |
|
4.8Maintenance
 |
|
 |
1. [Download/Upload] Select the operation to be performed on camera. - [Download]: Downloads detector and learning images from camera to the PC as zip files. The files to be downloaded are selected in [Download Files]. The destination for saving the zip file is selected on the folder browse screen that appears after clicking the [Start] button. - [Upload]: Uploads zipped files generated by [Download] from PC to camera. The files to be uploaded are specified by [Upload files]. |
2. [Download Files] Select the data to download from camera. Set when [Download] is selected in [Download/Upload]. [Detector + Image]: Download the detector and learning images. |
3. [Upload files] Select the file to be uploaded to camera. The file specified here is the zip file generated by [Download]. Set this when [Upload] is selected in [Download/Upload]. |
| ||||
