Object Detection-Image Analysis
Feature Description
Object detection utilizes deep learning neural network models to automatically determine and identify target categories and locations in images. It can detect multiple categories of targets simultaneously and outputs results in XML format, recording target categories, coordinates, and confidence levels. This feature demonstrates fast detection speed and high accuracy.
Parameter Description
| Parameter Name | Default Value | Description | Type |
|---|---|---|---|
| Source Data Path | Specifies the folder path containing the images to be detected | String | |
| Model File | Specifies the model file (*.sdm) for image object detection | String | |
| Probability Threshold | 0.5 | The system calculates the probability score for each detected object matching target features. Only objects with scores above this threshold will be saved in detection results. Default: 0.5. | Double |
| Other Parameters (Optional) |
false | Check this box to enable deduplicate threshold configuration | Boolean |
| Result File Path | Specifies the storage path for output results | Datasource | |
| Result File Name | Specifies the name for result files | String |
Output
| Parameter Name | Description | Type |
|---|---|---|
| Result Dataset | Result dataset | DatasetVector |