Related Experiment Video
Updated: May 14, 2025
09:19
Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging
Published on: April 18, 2025
224
Enhancing Historical Aerial Photographs: A New Approach Based on Non-Reference Metric and Photo Interpretation
Abdullah Harun Incekara1, Dursun Zafer Seker2
1Department of Geomatics Engineering, Tokat Gaziosmanpasa University, Taslicitlik, Tokat 60150, Türkiye.
Sensors (Basel, Switzerland)
|April 12, 2025
Summary
This study introduces a hierarchical dataset structure for deep learning super-resolution (SR) of historical aerial photos. This method improves image enhancement by training categories separately and selecting high-quality patches using the BRISQUE metric.
Area of Science:
- Computer Vision
- Image Processing
- Artificial Intelligence
Background:
- Deep learning-based super-resolution (SR) is a leading technique for improving low-resolution image quality.
- Historical aerial photographs present unique challenges for SR due to degradation and varying content.
- Existing SR models often struggle with diverse image datasets without specialized structuring.
Purpose of the Study:
- To propose and evaluate a hierarchical dataset structure for SR of grayscale historical aerial photographs.
- To assess the impact of this structured approach on SR model performance using a basic SR model.
- To correlate SR results with a non-reference image quality metric.
Main Methods:
- A hierarchical dataset was created based on photo interpretation elements: bare land/forestry (primary), residential (secondary), and farmland (tertiary).
- Each category was trained separately using a basic SR model, avoiding simultaneous training of all diverse image types.
- Enhanced images were generated for each category, and final images were assembled by selecting high-quality 5x5 pixel patches based on Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) scores.
Main Results:
- The hierarchical dataset structure led to improved SR results compared to conventional training methods.
- Separate training of image categories allowed the basic SR model to handle diverse features more effectively.
- Quality assessment using BRISQUE and reference-based metrics confirmed the positive impact of the structured dataset approach.
Conclusions:
- A hierarchical dataset structure significantly enhances the performance of basic super-resolution models for historical aerial photographs.
- The method of training separate categories and selecting high-quality patches improves the fidelity of enhanced images.
- This approach offers a viable strategy for improving image quality in historical image archives.
Related Concept Videos
01:25Methods of Obtaining Topography
30
Topography involves measuring and mapping land elevations, natural features, and artificial structures to create accurate representations of the terrain. Topographic surveying relies on traditional and modern methods, each with distinct advantages and limitations.Traditional Surveying Methods:Transit stadia surveys and plane table surveys were widely used traditional surveying methods. These techniques relied on instruments like theodolites and stadia rods for measuring distances and angles,...
30
01:15Depth Perception and Spatial Vision
479
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
479
01:26Influence of Earth's Curvature and Atmospheric Refraction on Leveling
38
During leveling, the Earth's curvature and atmospheric refraction introduce deviations in the line of sight from a true horizontal reference. When the line of sight is leveled, it remains perpendicular to the plumb line only at a single point. Beyond this, it deviates due to the Earth’s curvature, represented by the correction C. For a sight distance D, the deviation can be derived using the relationship:This relationship shows that the deviation increases quadratically with distance.
38
01:30Design Example: Identifying the Locations of Monuments in the Field Using Global Positioning System Device
16
Surveyors use Global Positioning System (GPS) technology to measure the precise location and elevation of points on Earth. In a recent survey, GPS receivers were used to determine the coordinates and elevations of two park monuments. The process involved careful mission planning, data collection, and correction to ensure accuracy. The survey began with mission planning to identify optimal satellite visibility and minimize Position Dilution of Precision (PDOP). A geodetic control point...
16
01:12Differential Leveling
99
Differential leveling is a precise method in surveying used to determine the elevation difference between two points. Its primary goal is to establish accurate vertical measurements to create level surfaces or grade lines critical for designing and constructing infrastructures such as roads, bridges, and buildings.The procedure for differential leveling begins with setting up and leveling the instrument at a point where the benchmark can be seen. The level rod is held on the benchmark (BM), and...
99
01:29Plotting of Topographic Maps
26
Topographic maps represent the Earth's surface features using contour lines, which connect points of equal elevation to create a two-dimensional representation of three-dimensional terrain. Creating a topographic map requires a systematic approach.Begin by plotting a scaled grid and marking intersections corresponding to the survey's elevation data points. Assign elevation values at these intersections to build the base map. Next, determine contour levels using a consistent contour interval,...
26