Regarding YOLOV8 spatial Detection

susantini

Hi Erik,
Currently YOLO V8 on oakd supports only detections. By when you can update the model with fetching the coordinates(x,y,z)?

erik

Hi susantini ,
So actually the SpatialDetectionNetworks combine depth information with object detection models to get the 3D coordinates (see 3d object localization docs). So using YoloSpatialDetectionNetwork should already do that for you. Thoughts?
Thanks, Erik

susantini

erik I tried with keeping YoloSpatialDetectionNetwork but its not working.THe frame itself is not opening.Can yolo confirm if yolov8 model on oak just gives detection or detection with spatial coordinates

erik

Hi susantini ,
Perhaps YoloV8 hasn't been officially supported by the depthai firmware, so parsing of NN results isn't working, which means no (spatial) detections will be available. Best to ask about the status on depthai-ml-training Github repo (Issue).
Thanks, Erik