Q#1: In AI, perception refers to:
(A) The process of sensing and interpreting the environment
(B) Only reasoning
(C) BFS only
(D) DFS only
Answer: (A) The process of sensing and interpreting the environment
Q#2: Computer vision is a subfield of:
(A) AI perception
(B) NLP only
(C) BFS only
(D) DFS only
Answer: (A) AI perception
Q#3: Sensors in AI perception include:
(A) Cameras, microphones, LIDAR, and touch sensors
(B) Only keyboards
(C) BFS only
(D) DFS only
Answer: (A) Cameras, microphones, LIDAR, and touch sensors
Q#4: Image processing involves:
(A) Transforming and analyzing images to extract information
(B) Only generating text
(C) BFS only
(D) DFS only
Answer: (A) Transforming and analyzing images to extract information
Q#5: Edge detection identifies:
(A) Boundaries between regions in an image
(B) Only colors
(C) BFS only
(D) DFS only
Answer: (A) Boundaries between regions in an image
Q#6: Thresholding is used to:
(A) Separate foreground from background
(B) Only detect edges
(C) BFS only
(D) DFS only
Answer: (A) Separate foreground from background
Q#7: Feature extraction in perception involves:
(A) Identifying meaningful characteristics from raw data
(B) Only raw pixels
(C) BFS only
(D) DFS only
Answer: (A) Identifying meaningful characteristics from raw data
Q#8: Pattern recognition is:
(A) Classifying data based on features
(B) Only tokenization
(C) BFS only
(D) DFS only
Answer: (A) Classifying data based on features
Q#9: Supervised learning in perception requires:
(A) Labeled training data
(B) Only unlabeled data
(C) BFS only
(D) DFS only
Answer: (A) Labeled training data
Q#10: Unsupervised learning in perception is used for:
(A) Clustering or discovering patterns without labels
(B) Only classification
(C) BFS only
(D) DFS only
Answer: (A) Clustering or discovering patterns without labels
Q#11: Object recognition aims to:
(A) Identify objects in an image
(B) Only detect colors
(C) BFS only
(D) DFS only
Answer: (A) Identify objects in an image
Q#12: Convolutional Neural Networks (CNNs) are used for:
(A) Image and video perception tasks
(B) Only NLP
(C) BFS only
(D) DFS only
Answer: (A) Image and video perception tasks
Q#13: Pooling layers in CNNs:
(A) Reduce spatial dimensions while preserving important features
(B) Increase resolution
(C) BFS only
(D) DFS only
Answer: (A) Reduce spatial dimensions while preserving important features
Q#14: Edge, corner, and blob detectors are:
(A) Classical computer vision feature detectors
(B) Only neural networks
(C) BFS only
(D) DFS only
Answer: (A) Classical computer vision feature detectors
Q#15: Object localization identifies:
(A) The position of objects in an image
(B) Only presence of object
(C) BFS only
(D) DFS only
Answer: (A) The position of objects in an image
Q#16: Semantic segmentation labels:
(A) Each pixel in an image with a class
(B) Only bounding boxes
(C) BFS only
(D) DFS only
Answer: (A) Each pixel in an image with a class
Q#17: Instance segmentation distinguishes:
(A) Different instances of the same class
(B) Only class labels
(C) BFS only
(D) DFS only
Answer: (A) Different instances of the same class
Q#18: Optical flow estimates:
(A) Motion of objects between consecutive frames
(B) Only static images
(C) BFS only
(D) DFS only
Answer: (A) Motion of objects between consecutive frames
Q#19: Depth perception in AI can use:
(A) Stereo cameras or LIDAR sensors
(B) Only RGB cameras
(C) BFS only
(D) DFS only
Answer: (A) Stereo cameras or LIDAR sensors
Q#20: Feature matching is used for:
(A) Comparing keypoints between images
(B) Only clustering
(C) BFS only
(D) DFS only
Answer: (A) Comparing keypoints between images
Q#21: Template matching identifies:
(A) Objects by comparing with predefined templates
(B) Only random features
(C) BFS only
(D) DFS only
Answer: (A) Objects by comparing with predefined templates
Q#22: Histogram of Oriented Gradients (HOG) is used for:
(A) Object detection by analyzing gradient directions
(B) Only color detection
(C) BFS only
(D) DFS only
Answer: (A) Object detection by analyzing gradient directions
Q#23: SIFT features are:
(A) Scale-Invariant Feature Transform descriptors for keypoints
(B) Only raw pixels
(C) BFS only
(D) DFS only
Answer: (A) Scale-Invariant Feature Transform descriptors for keypoints
Q#24: SURF features are:
(A) Speeded-Up Robust Features for object recognition
(B) Only colors
(C) BFS only
(D) DFS only
Answer: (A) Speeded-Up Robust Features for object recognition
Q#25: YOLO algorithm is used for:
(A) Real-time object detection
(B) Only segmentation
(C) BFS only
(D) DFS only
Answer: (A) Real-time object detection
Q#26: Mask R-CNN extends:
(A) Faster R-CNN for instance segmentation
(B) Only edge detection
(C) BFS only
(D) DFS only
Answer: (A) Faster R-CNN for instance segmentation
Q#27: Scene understanding involves:
(A) Recognizing objects and relationships in an image
(B) Only colors
(C) BFS only
(D) DFS only
Answer: (A) Recognizing objects and relationships in an image
Q#28: 3D perception in AI uses:
(A) Depth maps, point clouds, or volumetric representations
(B) Only 2D images
(C) BFS only
(D) DFS only
Answer: (A) Depth maps, point clouds, or volumetric representations
Q#29: Sensor fusion combines:
(A) Data from multiple sensors for improved perception
(B) Only one sensor
(C) BFS only
(D) DFS only
Answer: (A) Data from multiple sensors for improved perception
Q#30: Speech perception in AI involves:
(A) Recognizing and interpreting spoken language
(B) Only text
(C) BFS only
(D) DFS only
Answer: (A) Recognizing and interpreting spoken language
Q#31: Audio signal processing includes:
(A) Noise reduction, feature extraction, and spectrogram analysis
(B) Only tokenization
(C) BFS only
(D) DFS only
Answer: (A) Noise reduction, feature extraction, and spectrogram analysis
Q#32: Automatic Speech Recognition (ASR) converts:
(A) Speech into text
(B) Text into speech only
(C) BFS only
(D) DFS only
Answer: (A) Speech into text
Q#33: Visual perception in AI involves:
(A) Image, video, and scene understanding
(B) Only text
(C) BFS only
(D) DFS only
Answer: (A) Image, video, and scene understanding
Q#34: Feature selection improves:
(A) Accuracy and efficiency of perception systems
(B) Only raw data storage
(C) BFS only
(D) DFS only
Answer: (A) Accuracy and efficiency of perception systems
Q#35: Noise in perception data can be:
(A) Sensor noise, lighting variation, or occlusion
(B) Only correct information
(C) BFS only
(D) DFS only
Answer: (A) Sensor noise, lighting variation, or occlusion
Q#36: Robust perception systems handle:
(A) Noise, ambiguity, and changing environments
(B) Only perfect data
(C) BFS only
(D) DFS only
Answer: (A) Noise, ambiguity, and changing environments
Q#37: Motion detection uses:
(A) Frame differencing, optical flow, or background subtraction
(B) Only single images
(C) BFS only
(D) DFS only
Answer: (A) Frame differencing, optical flow, or background subtraction
Q#38: Pose estimation determines:
(A) Position and orientation of objects or humans
(B) Only presence of object
(C) BFS only
(D) DFS only
Answer: (A) Position and orientation of objects or humans
Q#39: Human activity recognition analyzes:
(A) Movements in video to infer actions
(B) Only static images
(C) BFS only
(D) DFS only
Answer: (A) Movements in video to infer actions
Q#40: Perception in robotics enables:
(A) Navigation, object manipulation, and environment interaction
(B) Only text processing
(C) BFS only
(D) DFS only
Answer: (A) Navigation, object manipulation, and environment interaction
Q#41: LIDAR sensors provide:
(A) Distance measurements for 3D perception
(B) Only color images
(C) BFS only
(D) DFS only
Answer: (A) Distance measurements for 3D perception
Q#42: Depth cameras like Kinect measure:
(A) Distance of objects from the sensor
(B) Only 2D images
(C) BFS only
(D) DFS only
Answer: (A) Distance of objects from the sensor
Q#43: Semantic perception involves:
(A) Understanding meaning of objects and scenes
(B) Only raw pixels
(C) BFS only
(D) DFS only
Answer: (A) Understanding meaning of objects and scenes
Q#44: Active perception in AI:
(A) Chooses actions to improve sensing quality
(B) Only passive observation
(C) BFS only
(D) DFS only
Answer: (A) Chooses actions to improve sensing quality
Q#45: Sensor calibration ensures:
(A) Accurate and consistent measurements from sensors
(B) Only random values
(C) BFS only
(D) DFS only
Answer: (A) Accurate and consistent measurements from sensors
Q#46: Object tracking follows:
(A) Objects across consecutive frames
(B) Only single frame detection
(C) BFS only
(D) DFS only
Answer: (A) Objects across consecutive frames
Q#47: Multi-sensor perception enhances:
(A) Accuracy, robustness, and reliability of perception systems
(B) Only single sensor data
(C) BFS only
(D) DFS only
Answer: (A) Accuracy, robustness, and reliability of perception systems
Q#48: Perception uncertainty can be handled using:
(A) Probabilistic models and Bayesian inference
(B) Only deterministic rules
(C) BFS only
(D) DFS only
Answer: (A) Probabilistic models and Bayesian inference
Q#49: Scene reconstruction builds:
(A) 3D models from images or sensor data
(B) Only 2D sketches
(C) BFS only
(D) DFS only
Answer: (A) 3D models from images or sensor data
Q#50: The ultimate goal of perception in AI is:
(A) Enable intelligent systems to sense, interpret, and act effectively in the environment
(B) Only memorize data
(C) BFS only
(D) DFS only
Answer: (A) Enable intelligent systems to sense, interpret, and act effectively in the environment