Object Detection

What is the purpose of a bounding box in object detection?

• To provide a visual representation of the detected objects

• To store the coordinates of the bounding boxes

• To improve the accuracy of the object detection algorithm

• To provide a reference for the object detection algorithm

In the YOLO algorithm, at training time, only one cell ---the one containing the center/midpoint of an object--- is responsible for detecting this object.

• True

• False

What is object tracking in machine learning?

• A technique to detect objects in an image

• A technique to classify objects in an image

• A technique to locate and track objects in a video or image sequence

• A technique to segment objects in an image

___ is a Python library that makes it easy to train TensorFlow Lite models using your own data with just a few lines of code, no machine learning expertise required.

• Task library

• TensorFlow

• PyTorch

• Model Maker

Which of the following is not a popular object detection algorithm?

• YOLO (You Only Look Once)

• R-CNN (Region-based Convolutional Neural Network)

• LSTM (Long Short-Term Memory)

• SSD (Single Shot MultiBox Detector)

Which of the following is a challenge in object tracking?

• Illumination changes

• Object occlusion

• Background distractions

• All of the above

Which of the following is a common application of object tracking in computer vision?

• Object detection

• Object recognition

• Face detection

• Image segmentation

If you build a neural network that inputs a picture of a person’s face and outputs N landmarks on the face (assume the input image always contains exactly one face), how many output units will the network have?

• 1N

• 2N

• 3N

• 4N

Which of the following is a common evaluation metric for object detection?

• Intersection over Union (IoU)

• Mean Absolute Error (MAE)

• F1 Score

• Accuracy

Which of the following is a limitation of object detection algorithms?

• Difficulty in detecting small objects

• High computational complexity

• Dependence on training data

• All of the above