📖 Tier 1: Prepare & Study Guide ✓ 100% Solved with Rationales

Computer Vision & Geospatial Remote Sensing AI (Artificial Intelligence) Solved Questions & Notes (2026) - Apex Rankers

Artificial Intelligence & Data Science > Artificial Intelligence > Computer Vision & Geospatial Remote Sensing AI

82 Total Solved Questions
~123 mins Estimated Reading Time
1 Subject Areas / Chapters
Select Topic Area / Chapter: Click any section below to switch questions

Computer Vision & Geospatial Remote Sensing AI

100%
Showing 25 of 82 (30%)
🎯 Practice
Jump:
Q. 1 Artificial Intelligence
Difficulty: Medium (1 Mark)
What is the primary difference between Two-Stage and One-Stage Object Detectors?
A
Two-stage detectors (Faster R-CNN) first generate Region Proposals (RPN) and then classify/refine them; One-stage detectors (YOLO, SSD) predict bounding boxes and class probabilities directly in a single dense grid pass
✓ Correct
B
Two-stage detectors process images in black and white; One-stage detectors in color
C
Two-stage detectors run on CPU; One-stage detectors on GPU
D
Two-stage detectors only detect 2 objects per image
💡 Step-by-Step Explanation & Concept Rationale
Two-stage models prioritize detection accuracy/mAP; one-stage models achieve real-time inference speeds (>60 FPS) suitable for video streams and drone feeds.
Q. 2 Artificial Intelligence
Difficulty: Hard (1 Mark)
In 'Faster R-CNN', what is the role of the 'Region Proposal Network' (RPN)?
A
A lightweight convolutional network that slides over feature maps to generate candidate bounding box proposals (RoIs) with objectness scores and anchor box offsets
✓ Correct
B
A module that scales image brightness
C
A module that converts bounding boxes to text captions
D
A classifier that performs OCR on road signs
💡 Step-by-Step Explanation & Concept Rationale
RPN replaced slow CPU selective search with fast GPU-based anchor proposals, sharing convolutional features with the downstream detection network.
Q. 3 Artificial Intelligence
Difficulty: Medium (1 Mark)
In YOLO (You Only Look Once), what is the 'Non-Maximum Suppression' (NMS) post-processing algorithm?
A
An iterative algorithm that filters out overlapping redundant bounding boxes, keeping only the highest confidence box and eliminating boxes with IoU (Intersection over Union) > threshold
✓ Correct
B
A method to suppress dark background pixels in images
C
A neural network layer that speeds up backpropagation
D
A technique for cropping images to square shapes
💡 Step-by-Step Explanation & Concept Rationale
NMS cleans up dense multi-box detections, ensuring each unique physical object is localized with exactly one bounding box.
Q. 4 Artificial Intelligence
Difficulty: Medium (1 Mark)
What is 'Intersection over Union' (IoU) / Jaccard Index in object detection and semantic segmentation evaluation?
A
Area of Overlap / Area of Union: |A intersect B| / |A union B| between predicted bounding box/mask and ground-truth annotation
✓ Correct
B
The sum of image width and height
C
The ratio of precision to recall
D
The angle between two bounding box diagonals
💡 Step-by-Step Explanation & Concept Rationale
IoU >= 0.5 is the standard threshold for True Positive detection in PASCAL VOC and COCO mAP evaluations.
Q. 5 Artificial Intelligence
Difficulty: Hard (1 Mark)
What is 'Mean Average Precision' (mAP, e.g. mAP@0.5, mAP@0.5:0.95) in object detection?
A
The mean of the Average Precision (area under the Precision-Recall curve) calculated across all object categories and IoU threshold intervals
✓ Correct
B
The average classification accuracy across all pixels
C
The speed of object detection in frames per second
D
The mean pixel intensity across RGB channels
💡 Step-by-Step Explanation & Concept Rationale
COCO mAP@0.5:0.95 averages AP across 10 IoU thresholds (from 0.50 to 0.95 with step 0.05) to rigorously penalize localization inaccuracies.
Q. 6 Artificial Intelligence
Difficulty: Hard (1 Mark)
What is 'U-Net' architecture (Ronneberger et al. 2015) and why is it the gold standard for biomedical and satellite image segmentation?
A
An encoder-decoder network featuring skip connections that concatenate high-resolution spatial feature maps from contracting paths directly to expanding upsampling paths
✓ Correct
B
A network shaped like a circle that loops infinitely
C
A generative network that produces synthetic images from text
D
A network that processes 1D audio waves
💡 Step-by-Step Explanation & Concept Rationale
U-Net skip connections preserve precise pixel-level spatial boundaries lost during downsampling, essential for flood inundation and tumor boundary segmentation.
Q. 7 Artificial Intelligence
Difficulty: Medium (1 Mark)
What is the primary difference between 'Semantic Segmentation' and 'Instance Segmentation'?
A
Semantic segmentation labels every pixel with a class (e.g. all people are red); Instance segmentation labels every pixel AND differentiates distinct object instances (e.g. Person 1 is red, Person 2 is blue)
✓ Correct
B
Semantic is for text; Instance is for images
C
Semantic is 2D; Instance is 3D
D
There is no difference between them
💡 Step-by-Step Explanation & Concept Rationale
Instance segmentation (e.g. Mask R-CNN, SAM) detects individual objects with distinct mask boundaries, whereas semantic segmentation (e.g. DeepLab) groups all instances into one class mask.
Q. 8 Artificial Intelligence
Difficulty: Hard (1 Mark)
In 'Mask R-CNN', what operation replaced 'RoIPool' to eliminate spatial quantization errors and achieve sub-pixel mask alignment?
A
RoIAlign (using bilinear interpolation to extract feature values at continuous floating-point locations without discrete coordinate rounding)
✓ Correct
B
Max Pooling with stride 4
C
Global Average Pooling
D
Batch Normalization
💡 Step-by-Step Explanation & Concept Rationale
He et al. showed RoIPool's coordinate rounding introduced substantial spatial misalignments; RoIAlign resolves this with continuous bilinear sampling.
Q. 9 Artificial Intelligence
Difficulty: Hard (1 Mark)
What is 'Vision Transformer' (ViT, Dosovitskiy et al. 2020)?
A
An architecture that splits an image into a sequence of non-overlapping patches (e.g. 16x16 pixels), projects them linearly into token embeddings, and processes them with standard Transformer Encoders
✓ Correct
B
A transformer used in optical fiber internet cables
C
A camera lens that zooms automatically using AI
D
A convolutional network that processes text prompts
💡 Step-by-Step Explanation & Concept Rationale
ViT showed that standard Transformer architectures with minimal inductive bias surpass CNNs on large pre-training scales (JFT-300M, ImageNet-21k).
Q. 10 Artificial Intelligence
Difficulty: Hard (1 Mark)
What is 'Swin Transformer' (Hierarchical Vision Transformer using Shifted Windows)?
A
A vision transformer that computes self-attention within local non-overlapping windows and shifts window partitioning across layers to achieve linear O(N) computational complexity
✓ Correct
B
A transformer that swings back and forth during training
C
A vision model trained on swimming pool images
D
A model that processes images in reverse order
💡 Step-by-Step Explanation & Concept Rationale
Swin Transformer provides multi-scale hierarchical feature maps and linear computational complexity relative to image size, making it a powerful general backbone for dense prediction.
Q. 11 Artificial Intelligence
Difficulty: Hard (1 Mark)
What is 'Segment Anything Model' (SAM, Kirillov et al. / Meta 2023)?
A
A foundation model for zero-shot promptable image segmentation that generates high-quality masks from points, bounding boxes, or free-form text prompts
✓ Correct
B
A computer software that edits video audio tracks
C
A tool for segmenting hard drive disk partitions
D
A database partitioning tool for PostgreSQL
💡 Step-by-Step Explanation & Concept Rationale
SAM was trained on 1 billion masks (SA-1B), enabling zero-shot generalization to segment any object in natural, medical, or satellite imagery.
Q. 12 Artificial Intelligence
Difficulty: Medium (1 Mark)
In multispectral satellite remote sensing (e.g. Sentinel-2, Landsat-8), what is the 'Normalized Difference Vegetation Index' (NDVI) formula?
A
NDVI = (NIR - Red) / (NIR + Red)
✓ Correct
B
NDVI = (Red - Blue) / (Red + Blue)
C
NDVI = (SWIR - Green) / (SWIR + Green)
D
NDVI = (Thermal - Visible) / (Thermal + Visible)
💡 Step-by-Step Explanation & Concept Rationale
Healthy green vegetation absorbs red light (chlorophyll absorption) and strongly reflects Near-Infrared (NIR); NDVI ranges from -1 to +1.
Q. 13 Artificial Intelligence
Difficulty: Hard (1 Mark)
What index is universally calculated from Near-Infrared (NIR) and Green bands to detect and map standing flood waters and open water bodies from satellite imagery?
A
Normalized Difference Water Index (NDWI = (Green - NIR) / (Green + NIR))
✓ Correct
B
Normalized Difference Vegetation Index (NDVI)
C
Enhanced Vegetation Index (EVI)
D
Soil Adjusted Vegetation Index (SAVI)
💡 Step-by-Step Explanation & Concept Rationale
McFeeters NDWI uses Green and NIR to delineate open water surfaces; water has high reflectance in green and near-total absorption in NIR.
Q. 14 Artificial Intelligence
Difficulty: Hard (1 Mark)
What is the 'Normalized Difference Built-up Index' (NDBI) used for in satellite urban analysis?
A
NDBI = (SWIR - NIR) / (SWIR + NIR), used to delineate urban impervious infrastructure, concrete, and built-up settlements
✓ Correct
B
Measuring forest tree density
C
Detecting ocean oil spills
D
Mapping agricultural crop moisture
💡 Step-by-Step Explanation & Concept Rationale
Built-up concrete and urban materials exhibit higher reflectance in Shortwave Infrared (SWIR) compared to NIR.
Q. 15 Artificial Intelligence
Difficulty: Hard (1 Mark)
What is 'Synthetic Aperture Radar' (SAR) (e.g. Sentinel-1 C-band SAR) and why is it indispensable for flood disaster monitoring in cloudy weather?
A
An active microwave sensor that penetrates thick storm clouds, heavy monsoon rain, and operates day or night, providing all-weather surface radar backscatter
✓ Correct
B
An optical digital camera that takes color photos in sunlight
C
A thermal infrared camera measuring land surface heat
D
A sound wave sensor measuring acoustic noise
💡 Step-by-Step Explanation & Concept Rationale
Optical satellites cannot see the ground through cloud cover during active monsoon storms; SAR microwaves penetrate clouds and detect flood water as dark specular reflectors.
Q. 16 Artificial Intelligence
Difficulty: Hard (1 Mark)
In SAR flood imagery analysis, why do calm standing flood waters appear as dark (low backscatter) pixels in radar images?
A
Smooth standing water acts as a specular reflector, bouncing radar microwave pulses away from the satellite antenna, resulting in near-zero signal return
✓ Correct
B
Water absorbs all radar energy into thermal heat
C
Water reflects radar pulses back directly to the satellite
D
Water freezes into ice under radar pulses
💡 Step-by-Step Explanation & Concept Rationale
Specular reflection directs the radar beam away from the sensor (low dB backscatter), creating sharp contrast against rough, bright land surfaces.
Q. 17 Artificial Intelligence
Difficulty: Hard (1 Mark)
What is 'Change Detection' (e.g. Bi-Temporal Siamese Networks) in satellite disaster damage assessment?
A
Comparing pre-disaster and post-disaster satellite imagery pairs to identify damaged buildings, collapsed bridges, and inundated roads using deep neural feature differences
✓ Correct
B
Detecting changes in computer operating system files
C
Checking weather temperature changes over 24 hours
D
Measuring seasonal crop planting cycles
💡 Step-by-Step Explanation & Concept Rationale
Siamese networks extract deep feature representations from registered pre/post image pairs to classify structural collapse and flood inundation.
Q. 18 Artificial Intelligence
Difficulty: Medium (1 Mark)
What is 'Spatial Resolution' in satellite remote sensing (e.g. Sentinel-2 at 10m vs WorldView-3 at 0.3m)?
A
The physical ground area represented by a single image pixel (e.g. 10m means 1 pixel covers a 10m x 10m ground footprint)
✓ Correct
B
The total number of spectral color bands
C
The frequency of satellite orbital flyovers
D
The file size of the downloaded satellite image
💡 Step-by-Step Explanation & Concept Rationale
Higher spatial resolution (smaller pixel size in meters) allows detection of smaller physical ground objects (individual tents vs broad regional floods).
Q. 19 Artificial Intelligence
Difficulty: Medium (1 Mark)
What is 'Temporal Resolution' (Revisit Time) in satellite constellations?
A
The time elapsed between consecutive satellite observations of the exact same geographical point on Earth (e.g. 5 days for Sentinel-2, daily for PlanetScope)
✓ Correct
B
The shutter exposure speed of the satellite camera
C
The lifespan of the satellite battery in orbit
D
The time taken to download data from the cloud
💡 Step-by-Step Explanation & Concept Rationale
High temporal resolution (frequent revisits) is critical for tracking dynamic, rapid-onset flash floods and cyclone paths in real time.
Q. 20 Artificial Intelligence
Difficulty: Medium (1 Mark)
What is 'Spectral Resolution' in earth observation sensors?
A
The number, width, and wavelength range of specific electromagnetic spectral bands (e.g. RGB, RedEdge, NIR, SWIR, Thermal) captured by the sensor
✓ Correct
B
The spatial size of the camera sensor chip
C
The zoom magnification level of the optical lens
D
The frame rate of video recording
💡 Step-by-Step Explanation & Concept Rationale
Hyperspectral sensors have hundreds of narrow contiguous bands; multispectral sensors have 10-15 broad bands.
Q. 21 Artificial Intelligence
Difficulty: Hard (1 Mark)
What is 'Radiometric Resolution' in remote sensing sensors (e.g. 8-bit vs 12-bit vs 16-bit)?
A
The sensor's sensitivity to subtle differences in reflected electromagnetic energy, determined by the number of digital quantization levels (e.g. 12-bit = 4,096 levels)
✓ Correct
B
The physical radio frequency of satellite downlink
C
The radiation shielding thickness of the satellite casing
D
The power wattage of solar panels
💡 Step-by-Step Explanation & Concept Rationale
Higher radiometric resolution allows distinguishing subtle moisture and soil variations in shadow or dark terrain.
Q. 22 Artificial Intelligence
Difficulty: Hard (1 Mark)
What is 'Atmospheric Correction' (e.g. BOA / Level-2A surface reflectance) in optical satellite preprocessing?
A
Removing atmospheric scattering, aerosol absorption, and Rayleigh distortion to convert Top-Of-Atmosphere (TOA) radiance into true Surface Reflectance (BOA)
✓ Correct
B
Warming up the satellite sensor with heaters
C
Cleaning dust off the satellite camera lens
D
Adjusting camera shutter speed for wind gusts
💡 Step-by-Step Explanation & Concept Rationale
Atmospheric correction ensures reflectance values are physically comparable across different dates and seasons.
Q. 23 Artificial Intelligence
Difficulty: Medium (1 Mark)
What is 'Cloud Masking' (e.g. Fmask / SCL in Sentinel-2) prior to geospatial AI analysis?
A
Identifying and filtering out clouds, cirrus, and cloud shadows from satellite imagery so they are not misclassified as floodwater, snow, or urban structures
✓ Correct
B
Drawing artificial clouds onto images for aesthetics
C
Masking cloud computing IP addresses
D
Encrypting satellite data files in the cloud
💡 Step-by-Step Explanation & Concept Rationale
Cloud shadows have low reflectance and can be easily confused with floodwater unless masked out.
Q. 24 Artificial Intelligence
Difficulty: Hard (1 Mark)
What is 'Pansharpening' in satellite image processing?
A
Fusing a high-resolution panchromatic (grayscale) band with lower-resolution multispectral color bands to produce a high-resolution color composite image
✓ Correct
B
Sharpening a physical kitchen frying pan
C
Increasing image brightness uniformly
D
Cropping an image with a rectangular marquee tool
💡 Step-by-Step Explanation & Concept Rationale
Pansharpening blends the high spatial detail of panchromatic sensors with the rich spectral data of multispectral sensors.
Q. 25 Artificial Intelligence
Difficulty: Hard (1 Mark)
What is 'Object-Based Image Analysis' (OBIA) compared to Pixel-Based Classification?
A
Grouping adjacent pixels into homogeneous vector image segments (superpixels) based on texture, shape, and context before classification, reducing 'salt-and-pepper' noise
✓ Correct
B
Classifying pixels completely independently without spatial context
C
Deleting objects from an image
D
Drawing vector bounding boxes manually
💡 Step-by-Step Explanation & Concept Rationale
OBIA uses algorithms like SLIC or multiresolution segmentation to mimic human visual cognitive interpretation.
Study Stream Progress: Showing 25 of 82 Questions (30%)
Jump to:

Ready to Test Your Retention & Speed?

Now that you have reviewed the study questions and rationales, test yourself in our interactive 1-by-1 practice engine or take the full official timed mock exam.