Pier camera stills only need a log of whether a person, vehicle, or animal is in the frame. There is no labeled custom-species folder and no pixel-level mask requirement. Which approach fits?
Select an answer to reveal the explanation.
Short Explanation
Think of pier stills that only need person, vehicle, or animal in the frame. No custom-species folder, no pixel masks. Amazon Rekognition. A SageMaker vision trainer is the wrong spend.
Full Explanation
Amazon Rekognition covers a standard person, vehicle, or animal detection need without a custom labeled set. A SageMaker Image Classification or Object Detection job is the wrong spend when labels and masks are not required. Comprehend and DeepAR are not vision detectors.