MLS-C01 · Question #318
A company wants to create an artificial intelligence (A? yoga instructor that can lead large classes of students. The company needs to create a feature that can accurately count the number of students
The correct answer is C. Object Detection D. Pose estimation. To count students and evaluate their yoga poses from video frames, object detection is used for counting individuals, and pose estimation is used for analyzing body movements and angles.
Question
A company wants to create an artificial intelligence (A? yoga instructor that can lead large classes of students. The company needs to create a feature that can accurately count the number of students who are in a class. The company also needs a feature that can differentiate students who are performing a yoga stretch correctly from students who are performing a stretch incorrectly. Determine whether students are performing a stretch correctly, the solution needs to measure the location and angle of each student's arms and legs. A data scientist must use Amazon SageMaker to access video footage of a yoga class by extracting image frames and applying computer vision models. Which combination of models will meet these requirements with the LEAST effort? (Choose two.)
Options
- AImage Classification
- BOptical Character Recognition (OCR)
- CObject Detection
- DPose estimation
- EImage Generative Adversarial Networks (GANs)
How the community answered
(32 responses)- A6% (2)
- B3% (1)
- C75% (24)
- E16% (5)
Why each option
To count students and evaluate their yoga poses from video frames, object detection is used for counting individuals, and pose estimation is used for analyzing body movements and angles.
Image classification assigns a single label to an entire image, meaning it could classify an image as "yoga class" but cannot count individual students or analyze their body positions.
Optical Character Recognition (OCR) is used to extract text from images, which is irrelevant to counting people or analyzing body poses.
Object detection models are designed to identify and locate instances of objects (e.g., students) within an image and can count them. This directly addresses the requirement to accurately count the number of students in a class.
Pose estimation models accurately identify key points on the human body, such as joints (arms and legs), and their spatial relationships. This allows for measuring locations and angles, which is essential to differentiate between correct and incorrect yoga stretches.
Image Generative Adversarial Networks (GANs) are used for generating new images or modifying existing ones, which is not required for counting students or evaluating poses.
Concept tested: Computer vision model types for object detection and pose analysis
Source: https://aws.amazon.com/machine-learning/computer-vision/
Topics
Community Discussion
No community discussion yet for this question.