I have 2 parallel neural nets running
- I am using MobileNetSpatialDetectionNetwork to detect persons (works fine and I get detections and also x,y,z coordinates in a single message)
- I am trying to implement https://github.com/geaxgx/depthai_yunet to run on the device, but also want the spatial coordinates of the detected faces
To do this I am running 1 manip node, 1 NN, and 1 script node on the device:
- 1 manip to prepare the camRgb output to the NN
- 1 NN to do inference
- 1 script to do post-processing to find face detections which results in bounding boxes, landmarks, and confidence scores and seq number
Is there a way for me to output this data as a SpatialLocationCalculatorConfig message in the script node? I would like to output this into a SpatialLocationCalculator to create a SpatialLocationCalculatorData message. How do I ensure that the depth frame is synched with the correct seq number?
