Count Objects refers to automatically counting the number of interesting objects in images. It has several applications in industries, agriculture, medicine, etc. In saiwa Count Object service two deep learning networks are provided: Detectron2 and YOLOv5. By default the two networks are trained over COCO dataset which consists 12 classes and 80 objects like humans, vehicles, animals, etc. (For a list of default objects see “Advanced Settings” below). For more technical information read Count Objects and Object Detection service white papers.
Upon your interest, we at saiwa© re-train the networks on your specific objects of interests. Then using the same interface you can count any other objects in your input images. You only need to fill up the request form using “Request for customization” option. Additionally, you can re-train the both networks yourself using saiwa© “Deep Learning” service.
The features of saiwa© Count Objects service includes:
- Providing state-of-the-art deep learning algorithms
- Complete user control over the amount of uncertainty of counted objects (by setting “Confidence” parameter in “Advanced Settings”)
- Exporting and archiving the results in user cloud space or locally
- Modifying the objects
- Re-train the same networks over user-defined datasets using “Deep Learning” service
- Request for re-train the networks over user-defined datasets by saiwa© team using “Request for customization” option
- Apply on several images
- Preview and download the resulting images or detailed information of counted objects
Count Objects applications include but are not limited to:
1. Industrial applications
2. Agricultural applications
3. Medical applications