AI / ML / NN¶
OAK cameras can run any AI model, even custom architectured/built ones. You can even run multiple AI models at the same time, either in parallel or series (a demo here).
Subpages:
Converting model to MyriadX blob tutorial showcases model conversion and compilation steps to .blob format so you can run the model on the device.
Deploying Custom Models provides step-by-step tutorial on how to convert, compile and deploy the model to OAK device
Use one of 250+ pre-trained models; either from OpenVINO Model Zoo or DepthAI Model Zoo
AI vision tasks¶
We have open-source examples and demos for many different AI vision tasks, such as:
Object detection models provide bounding box, confidence, and label of all detected objects. Demos: MobileNet, Yolo, EfficientDet, Palm detection.
Landmark detection models provide landmarks/keypoints of an object. Demos: Human pose, hand landmarks, and facial landmarks.
Semantic segmentation models provide label/class for each pixel. Demos: Person segmentation, multiclass segmentation, road segmentation.
Classification models provide classification label and confidence in that label. Demos: EfficientNet, Tensorflow classification, fire classification, emotions classification.
Recognition models provide byte array that can be used for recognition or recognized feature itself. Demos: Face recognition, person identification, OCR, license plate recognition.
There are also many other AI vision tasks that don’t fall in any of the categories above, like crowd counting, monocular depth estimation, gaze estimation, or age/gender estimation.
All of the demos above run on color/grayscale frames. Many of these vision tasks can be fused with the depth perception (on the OAK camera itself), which unlocks the power of Spatial AI.
Model Performance¶
AI model performance depends on the accelerator that’s on the OAK device. For current devices that use RVC2 you can find the performance results here.