Study guide
8.4 Image Processing, Classification and LiDAR
SURCON Professional Examination — Surveyor Nigeria
Track your progress as you read
Finished sections get a check mark.
1 Chapter 1: The SURCON Professional Examination
1.1 The Surveyor's-Cadre Examination: Papers VI, VII and the Folio 1.2 Enrolment, Pupilage and the Certificate of Experience 1.3 Paper VII: The Professional Essay 1.4 Compiling the Survey Folio 1.5 The Oral Interview and Project Defence 1.6 Contemporary Professional Issues for the Essay and Interview
2 Chapter 2: The SURCON Act (Cap S18 LFN 2004)
2.1 The SURCON Act: Establishment, Membership and Functions 2.2 The Registrar and the Four-Part Register 2.3 Registration of Surveyors, Technologists and Technicians 2.4 Approved Qualifications, Supervision of Training and Appeals 2.5 Professional Discipline: the Disciplinary Committee and the Investigating Panel 2.6 Penalties, Offences and the Right to Practise
3 Chapter 3: Survey Co-ordination Act, Survey Laws and Regulations
3.1 The Survey Co-ordination Act 3.2 State Survey Laws: Plans, Deposit and Protection of Survey Marks 3.3 Survey Regulations: Field Survey Methods and the Standard of Survey 3.4 Survey Regulations: Demarcation and Beacon Construction 3.5 Survey Plans, Records and Information 3.6 Resurvey, Boundary Disputes and the Surveyor as Witness
4 Chapter 4: Land Law for Surveyors
4.1 The Land Use Act 1978: Vesting and Land Administration 4.2 Rights of Occupancy, Certificates of Occupancy and Deemed Grants 4.3 Alienation, Consent and the Nullity Rule 4.4 Revocation and Compensation under Sections 28 to 30 4.5 Land Registration Systems and LIS Integration 4.6 Minerals, Planning and Boundary Legislation
5 Chapter 5: Professional Practice, Ethics and Management
5.1 Professional Ethics and Client Relations 5.2 Charging for Survey Work, Records and the Surveyor's Signature 5.3 Establishing and Running a Survey Practice 5.4 Engagement, Liability, Quality Assurance and Safety
6 Chapter 6: Geodesy and Control
6.1 Minna Datum and Geodetic Reference Frames in Nigeria 6.2 Height Systems and Geoid Undulation 6.3 The Nigeria Transverse Mercator Projection and Grid Belts 6.4 GNSS Positioning, NIGNET and Control Networks 6.5 Geodetic Computations and Network Adjustments 6.6 Geodetic Astronomy and Azimuth Determination 6.7 Datum Transformation in Practice
7 Chapter 7: Computations, Land Surveying and LIS
7.1 Error Theory and Least Squares 7.2 Traverse Computation and Adjustment 7.3 Areas, Volumes and Setting Out 7.4 GIS Spatial Data Models and Topology 7.5 Land Information Systems and Spatial Databases 7.6 Web GIS, Cartography and Spatial Data Infrastructure
8 Chapter 8: Photogrammetry, Remote Sensing, Hydrography and Engineering
8.1 Fundamentals of Aerial Photogrammetry 8.2 UAV Photogrammetry and Structure from Motion 8.3 Satellite Remote Sensing and Image Interpretation 8.4 Image Processing, Classification and LiDAR 8.5 Sounding Systems and Hydrographic Equipment 8.6 Hydrographic Data Reductions and Tidal Datums 8.7 IHO S-44 Standards and Offshore Survey Practice 8.8 Engineering Route Surveying and Curve Geometry 8.9 Tunnelling, Mining Surveys and Deformation Monitoring
8.4 Image Processing, Classification and LiDAR
Key Takeaways Explain This Topic AI
Digital image preprocessing involves radiometric calibration, atmospheric correction (TOA to surface reflectance), and geometric orthorectification.
Supervised classification (e.g., Maximum Likelihood, Random Forest) relies on analyst training samples, whereas Unsupervised classification (K-Means, ISODATA) clusters data automatically.
Classification accuracy assessment uses confusion matrices to derive Overall Accuracy, User's Accuracy, Producer's Accuracy, and the Kappa Coefficient.
LiDAR active laser ranging computes target distance using D = c * t / 2 based on pulse round-trip time-of-flight.
Canopy Height Models (CHM) are derived by subtracting bare-earth Digital Elevation Models (DEM) from top-surface Digital Surface Models (DSM).
Last updated: August 2026
Image Processing, Classification & LiDAR
Modern photogrammetry and remote sensing workflows culminate in digital image processing, automated automated land-cover classification, and high-density active 3D point cloud generation using Light Detection and Ranging (LiDAR) . Mastery of these analytical techniques is essential for SURCON candidates involved in modern environmental, forestry, urban, and engineering surveying.
Digital Image Preprocessing
Raw satellite and airborne sensor imagery contains systematic radiometric, atmospheric, and geometric distortions that must be corrected before quantitative spatial analysis.
1. Radiometric Correction
Adjusts digital numbers (DN) to compensate for sensor detector variation, solar illumination geometry, and solar zenith angle variations over time. DN values are converted to Top-of-Atmosphere (TOA) Radiance ( L λ L_\lambda L λ ) using calibrated gain and bias values.
2. Atmospheric Correction
Solar radiation passing twice through Earth's atmosphere undergoes scattering (Rayleigh and Mie scattering) and atmospheric absorption by water vapor, ozone, and aerosols. Atmospheric correction converts TOA Radiance into true Surface Reflectance (Bottom-of-Atmosphere / BOA) .
Dark Object Subtraction (DOS) : An empirical image-based correction method that assumes deep clear water or shadow pixels should have near-zero reflectance, subtracting the minimum pixel value across the image.
Radiative Transfer Models : Physics-based algorithms (e.g., FLAASH , 6S) that model atmospheric parameters using elevation, humidity, and atmospheric aerosol models.
3. Geometric Rectification & Orthorectification
Aligns image coordinates with ground geographic coordinates. Orthorectification uses a DEM and ground control points (GCPs) to correct for camera tilt and terrain relief displacement on a pixel-by-pixel basis, producing an orthorectified image.
Image Classification Methods
Image classification converts continuous multispectral pixel data into discrete thematic land cover maps (e.g., agriculture, water, forest, built-up area). ┌───────────────────────────────────────────────┐
- │ Multispectral Image Data │
- └───────────────────────┬───────────────────────┘
- │
- ┌───────────────────────────────┴───────────────────────────────┐
- ▼ ▼
- ┌───────────────────────┐ ┌───────────────────────┐
- │ Supervised Methods │ │ Unsupervised Methods │
- │ (Requires Training) │ │ (Automated Clustering)│
- ├───────────────────────┤ ├───────────────────────┤
- │ • Maximum Likelihood │ │ • K-Means Clustering │
- │ • Random Forest (ML) │ │ • ISODATA Algorithm │
- │ • Support Vector (SVM)│ │ │
- └───────────────────────┘ └───────────────────────┘
- Supervised Classification
The analyst defines representative training sites (polygons) of known land-cover classes on the image. The statistical properties of these training samples are used to train a classifier algorithm:
Maximum Likelihood Classifier (MLC) : Assumes normal (Gaussian) distribution of pixel values per class. Calculates the probability that a given pixel belongs to a specific class and assigns the pixel to the class with maximum probability.
Random Forest (RF) : An ensemble machine learning algorithm that constructs dozens of decision trees on random subsets of training data, assigning classes based on majority voting. RF handles complex non-linear relationships without assuming Gaussian distribution.
Unsupervised Classification
Automated algorithms group image pixels into natural spectral clusters without prior analyst training data:
K-Means : Aggregates pixels into K K K specified clusters based on Euclidean spectral distance, iteratively updating cluster mean vectors.
ISODATA (Iterative Self-Organizing Data Analysis Technique) : An advanced clustering method that allows clusters to split, merge, or be discarded dynamically based on standard deviation thresholds.
Classification Accuracy Assessment
A classification is incomplete until its accuracy is quantified using an independent validation dataset displayed in a Confusion Matrix (Error Matrix) .
Classified Data \ Reference Ground Truth Class A (Forest) Class B (Water) Row Total User's Accuracy (1 - Commission Error)
Class A (Forest) n 11 n_{11} n 11 (Correct) n 12 n_{12} n 12 n 1 + n_{1+} n 1 + n 11 / n 1 + n_{11} / n_{1+} n 11 / n 1 +
Class B (Water) n 21 n_{21} n 21 n 22 n_{22} n 22 (Correct) n 2 + n_{2+}\; n 2 + n 22 / n 2 + n_{22} / n_{2+} n 22 / n 2 +
Column Total n + 1 n_{+1} n + 1 n + 2 n_{+2} n + 2 N N N (Total)
Producer's Accuracy (1 - Omission) n 11 / n + 1 n_{11} / n_{+1} n 11 / n + 1 n 22 / n + 2 n_{22} / n_{+2} n 22 / n + 2 Overall Accuracy = ∑ n i i / N = \sum n_{ii} / N = ∑ n ii / N
Overall Accuracy : Total diagonal correct pixels divided by total sample size N N N .
Producer's Accuracy : Measures omission error (probability that a ground truth reference pixel is correctly classified on the map).
User's Accuracy : Measures commission error (probability that a pixel classified on the map actually represents that class on the ground).
Kappa Coefficient ( κ \kappa κ ) : Quantifies classification accuracy corrected for chance agreement: κ = N ∑ i = 1 k n i i − ∑ i = 1 k ( n i + ⋅ n + i ) N 2 − ∑ i = 1 k ( n i + ⋅ n + i ) \kappa = \frac{N \sum_{i=1}^{k} n_{ii} - \sum_{i=1}^{k} (n_{i+} \cdot n_{+i})}{N^2 - \sum_{i=1}^{k} (n_{i+} \cdot n_{+i})} κ = N 2 − ∑ i = 1 k ( n i + ⋅ n + i ) N ∑ i = 1 k n ii − ∑ i = 1 k ( n i + ⋅ n + i )
LiDAR Fundamentals
LiDAR (Light Detection and Ranging) is an active airborne or terrestrial remote sensing technology that measures distances using high-frequency laser pulses (typically 1 , 064 nm 1,064\text{ nm} 1 , 064 nm for topographic systems, 532 nm 532\text{ nm} 532 nm green laser for bathymetric systems).
Time-of-Flight Ranging Equation
Distance D D D from aircraft laser scanner to target surface is derived from pulse time-of-flight t t t : D = c ⋅ t 2 D = \frac{c \cdot t}{2} D = 2 c ⋅ t
Where c c c is the speed of light ( 3.0 × 10 8 m/s 3.0 \times 10^8\text{ m/s} 3.0 × 1 0 8 m/s ) and t t t is the elapsed round-trip time between pulse emission and return detection.
Discrete Return vs. Full Waveform LiDAR
Discrete Return LiDAR : Records discrete return echoes when the laser pulse strikes physical surfaces (e.g., First Return = canopy top; Intermediate Returns = branches; Last Return = bare ground).
Full Waveform LiDAR : Digitizes the continuous energy return wave across time, capturing complex canopy structure density in forestry applications.
Deliverables: Point Density and Canopy Models
Point Density : Measured in points per square meter ( pts/m 2 \text{pts/m}^2 pts/m 2 ). High-density LiDAR ( > 10 − 20 pts/m 2 > 10-20\text{ pts/m}^2 > 10 − 20 pts/m 2 ) penetrates dense vegetation canopies to capture ground terrain.
Ground Filtering : Algorithms (e.g., Cloth Simulation Filtering - CSF, Progressive Morphological Filtering) separate ground point returns from non-ground returns.
Canopy Height Model (CHM) : Quantifies true vegetation height above terrain by subtracting the bare-earth DEM from the top-surface DSM: CHM = DSM − DEM \text{CHM} = \text{DSM} - \text{DEM} CHM = DSM − DEM