Answer-first summary for fast verification
Answer: TensorFlow Object Detection API for its ability to identify and locate multiple objects within images accurately
The TensorFlow Object Detection API is the most suitable choice for this task because it is specifically designed to identify and locate multiple objects within images, which is crucial for detecting obstacles from vehicle snapshots. It supports real-time processing and can be scaled to handle the demands of thousands of vehicles. XGBoost with BigQueryML (A) is not suitable as it is optimized for structured data, not image analysis. A linear learner with TensorFlow Estimator API (B) is inadequate for image data as it is better suited for regression and classification tasks. The TabNet algorithm with TensorFlow (D) is inappropriate because it is optimized for tabular data, not for processing images. For more information, refer to the TensorFlow Object Detection API documentation and examples.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
You are working on a project to enhance the safety of autonomous vehicles by developing a model that can analyze real-time snapshots from a moving vehicle to detect and classify various obstacles on the road. The project is constrained by the need for high accuracy, real-time processing capabilities, and scalability to handle thousands of vehicles simultaneously. Your team has decided to use Google's Vertex AI for model development and deployment. Considering these requirements, which of the following techniques or algorithms is the most suitable for this task? (Choose one correct option)
A
XGBoost with BigQueryML for its efficiency in handling large datasets
B
A linear learner with TensorFlow Estimator API for its simplicity and speed in training
C
TensorFlow Object Detection API for its ability to identify and locate multiple objects within images accurately
D
TabNet algorithm with TensorFlow for its advanced feature selection capabilities on tabular data
No comments yet.