MLS-C01 · Question #193
A company has video feeds and images of a subway train station. The company wants to create a deep learning model that will alert the station manager if any passenger crosses the yellow safety line…
The correct answer is A. Use Amazon Rekognition Custom Labels to label the dataset and create a custom. The core challenges are: (1) bounding boxes cannot precisely demarcate a thin line like the yellow safety line, and (2) the video data must stay confidential. Amazon Rekognition Custom Labels (Option A) trains a custom model within your own AWS account using images stored in…
Question
A company has video feeds and images of a subway train station. The company wants to create a deep learning model that will alert the station manager if any passenger crosses the yellow safety line when there is no train in the station. The alert will be based on the video feeds. The company wants the model to detect the yellow line, the passengers who cross the yellow line, and the trains in the video feeds. This task requires labeling. The video data must remain confidential. A data scientist creates a bounding box to label the sample data and uses an object detection model. However, the object detection model cannot clearly demarcate the yellow line, the passengers who cross the yellow line, and the trains. Which labeling approach will help the company improve this model?
Options
- AUse Amazon Rekognition Custom Labels to label the dataset and create a custom
- BUse an Amazon SageMaker Ground Truth object detection labeling task. Use Amazon
- CUse Amazon Rekognition Custom Labels to label the dataset and create a custom
- DUse an Amazon SageMaker Ground Truth semantic segmentation labeling task. Use a
How the community answered
(38 responses)- A84% (32)
- B8% (3)
- C3% (1)
- D5% (2)
Explanation
The core challenges are: (1) bounding boxes cannot precisely demarcate a thin line like the yellow safety line, and (2) the video data must stay confidential. Amazon Rekognition Custom Labels (Option A) trains a custom model within your own AWS account using images stored in S3, satisfying the confidentiality requirement. Custom Labels supports both image-level classification and bounding-box object detection with a managed labeling and training workflow. Options B and C may rely on Amazon Mechanical Turk (public workforce) for labeling, which would expose confidential video data to external workers. Option D (SageMaker Ground Truth semantic segmentation) could technically address the yellow line precision issue, but the rest of that option - likely specifying a public labeling workforce - violates the confidentiality constraint. Custom Labels with a private workforce keeps all data within the company's AWS environment.
Topics
Community Discussion
No community discussion yet for this question.