Data Fields | |
| bool | image_sync |
| Defines if the object detection is synchronized to the image or runs in a separate thread. If set to true, the detection is run for every grab, otherwise, the thread runs at its own speed, which can lead to new detection once in a while. | |
| bool | enable_tracking |
| Defines if the object detection will track objects across images flow. | |
| bool | enable_mask_output |
| Defines if the mask object will be computed. | |
| enum SL_DETECTION_MODEL | model |
| Enable human pose estimation with skeleton keypoints output (SL_DETECTION_MODEL). | |
| bool | enable_body_fitting |
| Defines if the body fitting will be applied. | |
| enum SL_BODY_FORMAT | body_format |
| Defines the body format outputed by the sdk when retrieveObjects is called. | |
| float | max_range |
| Defines a upper depth range for detections. Defined in UNIT set at SL_Camera::open. Default value is set to SL_Initparameters::depth_maximum_distance (can not be higher). | |
| struct SL_BatchParameters | batch_parameters |
| Batching system parameters. Batching system (introduced in 3.5) performs short-term re-identification with deep learning and trajectories filtering. BatchParameters::enable need to be true to use this feature (by default disabled) | |
| enum SL_OBJECT_FILTERING_MODE | filtering_mode |
| Defines the filtering mode that should be applied to raw detections. | |
| float | prediction_timeout_s |
| When an object is not detected anymore, the SDK will predict its positions during a short period of time before switching its state to SEARCHING. It prevents the jittering of the object state when there is a short misdetection. The user can define its own prediction time duration. More... | |
Sets the object detection parameters.
| float SL_ObjectDetectionParameters::prediction_timeout_s |
When an object is not detected anymore, the SDK will predict its positions during a short period of time before switching its state to SEARCHING.
It prevents the jittering of the object state when there is a short misdetection. The user can define its own prediction time duration.
