Object-based change detection and classification algorithms, implemented in Matlab and IDL programs, can effectively detect and classify changes in objects in bitemporal datasets.

Object-based change detection and classification

This paper introduces an object-based classification of remote sensing data for change detection, which classifies groups of pixels representing existing objects in a GIS database, and presents results from two test areas.

Object-based classification of remote sensing data for change detection

Object-based change detection using correlation image analysis and image segmentation techniques produces more accurate change detection results (Kappa approximately 90%) than traditional per-pixel analysis.

Object‐based change detection using correlation image analysis and image segmentation

This new approach for object-based change detection in remote sensing images is robust and accurate, integrating intensity and texture differences to detect changes in objects across different temporal images.

A new approach toward object-based change detection

Self-adaptive weight-change vector analysis effectively detects multiple changes in high-resolution remotely sensed images, outperforming standard change vector analysis.

Multi-Feature Object-Based Change Detection Using Self-Adaptive Weight Change Vector Analysis

The proposed object-based approach using multiple classifiers and multi-scale uncertainty analysis effectively detects changes in high-resolution remote sensing images, enhancing image analysis accuracy.

Object-Based Change Detection Using Multiple Classifiers and Multi-Scale Uncertainty Analysis

The ZED 2 stereo camera effectively detects object-level changes in real-world environments, enhancing the utility of the proposed object-based 3D change detection method.

Object-Based Change Detection Algorithm with a Spatial AI Stereo Camera

The OB-Reflectance method accurately detects forest change using high spatial resolution satellite images, with high detection accuracy (> 90%) and overall Kappa (> 0.80) compared to pixel-based methods.

Forest change detection by statistical object-based method

The proposed object-based graph model effectively generates reliable difference images from high resolution remote sensing images, outperforming state-of-the-art approaches in unsupervised change detection tasks.

An object-based graph model for unsupervised change detection in high resolution remote sensing images

Our DCA-Det framework effectively detects changed geographic entities in remotely sensed imagery, outperforming state-of-the-art methods on object-level metrics.

Object-level change detection with a dual correlation attention-guided detector

The proposed object-based change detection method using deep learning networks in very high-resolution satellite images effectively detects changes without ground truth data, outperforming traditional approaches.

Uncertainty Analysis for Object-Based Change Detection in Very High-Resolution Satellite Images Using Deep Learning Network

The proposed framework effectively detects changes in built-up land from high-resolution remote sensing images by combining pixel-level change detection and object-level recognition.

Change detection of built-up land: A framework of combining pixel-based detection and object-based recognition

The proposed method effectively detects new buildings and changes related to demolished buildings in very-high-resolution imagery, with a low rate of false alarms and missed detections compared to other methods.

Object-Based Building Change Detection by Fusing Pixel-Level Change Detection Results Generated from Morphological Building Index

This paper presents an enhanced multiresolution segmentation procedure for object-based change detection, improving consistency and performance in detecting shape changes in images.

Multiresolution segmentation adapted for object-based change detection

Our proposed method combining deep learning and object-based image analysis achieves higher accuracy and computational efficiency compared to pixel-based methods, with no significant difference in overall accuracy between feature fusion schemes.

Change detection using deep learning approach with object-based image analysis

This paper proposes an unsupervised object-based change detection and classification approach using object features, which improves detection of small structural changes in high-resolution imagery compared to traditional pixel-based algorithms.

Change detection using the object features

This unsupervised change detection and classification procedure using object features in high-resolution imagery improves results compared to traditional pixel-based algorithms.

Change detection using object features

Larger changes in novel, complex three-dimensional objects are more difficult to detect than smaller changes, and training to recognize objects before detection does not significantly affect sensitivity levels.

Detecting Changes in Novel, Complex Three-dimensional Objects

AI-based change detection methods show promise in urban planning, environmental monitoring, and disaster assessment, but face challenges in heterogeneous big data processing, unsupervised AI, and AI reliability.

Change Detection Based on Artificial Intelligence: State-of-the-Art and Challenges

This paper reviews various change detection techniques, highlighting the importance of comparing different algorithms to find the best approach for a specific application.

Change detection techniques

These studies suggest that object-based change detection methods, including classification algorithms, correlation image analysis, and graph models, are more accurate and effective than traditional per-pixel approaches for detecting changes in high-resolution remote sensing images.