Task for the detection and contouring of objects detected in a video.
In the input parameters it is expected:
Input video file, location of the video on which the detection is to be performed.
Output video file, where the detection result will be saved.
Path of the dmod file, which will be used as a model to perform the detections.
Confidence threshold: Accuracy of the detections performed by the AI model.
Only detections with a confidence higher than the one set in this parameter will be used for the rest of the processes.
Accuracy 0, implies that all detections will be evaluated, this may introduce erroneous detections in the process.
Accuracy very close to 1, implies that only the clearest detections for the model will be evaluated, this may bias the detections of valid objects.
By default, the value of 0.2 dramatically decreases anomalous detections and allows enough flexibility to maximize the number of detections.
Frame detections: This value defines how many frames to process the detections. As this value increases, the videos will be processed faster because fewer detections will be performed. For example, if the value is 4, one out of every 4 frames of the input video will be detected.
In the advanced parameters we can configure:
Parallel factor: The number of execution threads.
Frame range: The range of the video over which the detections will be performed, expressed in minutes and seconds. All means that the entire video will be processed. 1:30 processes the entire video from 1 minute and 30 seconds. 1:40-2:30 processes the video in the range of frames from 1:40 to 2:30, reducing the duration of the output video.
Crop video to frame range: Crop video to the defined frame range. If this option is enabled the output video will be cropped to the frame range selected in the previous parameter. If this option is not selected, the output video will have the same size as the input video, but only detections in the selected frame range will be performed.
Stroke Size: Percentage of vertical magnification. The percentage is calculated as a function of the detection height.
Buffer width: Percentage of horizontal enlargement over the detection made with AI. The percentage is calculated as a function of the detection width.
Buffer height: Percentage of vertical magnification over the detection made with AI. The percentage is calculated as a function of the detection height.