Long-Range depth estimation using learning based Hybrid Distortion Model for CCTV cameras

2025-12-19

AI Summary

Existing stereo vision methods suffer from severe accuracy degradation in CCTV-based ultra-long-range 3D localization (up to 5 km), primarily due to insufficient modeling of lens distortion—especially in long-baseline bundle adjustment. Method: We propose the first hybrid distortion model tailored for long-range photogrammetry: it extends the classical polynomial model with high-order terms and employs a lightweight neural network to learn residual distortions, thereby balancing physical interpretability and strong nonlinear fitting capability. The model is integrated into an end-to-end pipeline combining bundle adjustment optimization and GIS coordinate transformation. Results: Experiments demonstrate stable, high-precision 3D position estimation within 5 km, significantly outperforming pure geometric or purely learning-based baselines. The method supports real-time GIS visualization, enabling practical deployment in large-scale surveillance systems.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Intelligent Robots: State Estimation
• Search and Optimization: Distributed Search

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Large-scale security measurements

Abstract

Accurate camera models are essential for photogrammetry applications such as 3D mapping and object localization, particularly for long distances. Various stereo-camera based 3D localization methods are available but are limited to few hundreds of meters' range. This is majorly due to the limitation of the distortion models assumed for the non-linearities present in the camera lens. This paper presents a framework for modeling a suitable distortion model that can be used for localizing the objects at longer distances. It is well known that neural networks can be a better alternative to model a highly complex non-linear lens distortion function; on contrary, it is observed that a direct application of neural networks to distortion models fails to converge to estimate the camera parameters. To resolve this, a hybrid approach is presented in this paper where the conventional distortion models are initially extended to incorporate higher-order terms and then enhanced using neural network based residual correction model. This hybrid approach has substantially improved long-range localization performance and is capable of estimating the 3D position of objects at distances up to 5 kilometres. The estimated 3D coordinates are transformed to GIS coordinates and are plotted on a GIS map for visualization. Experimental validation demonstrates the robustness and effectiveness of proposed framework, offering a practical solution to calibrate CCTV cameras for long-range photogrammetry applications.

Problem

• Develops a hybrid distortion model for CCTV cameras
• Enables long-range 3D object localization up to 5 kilometers
• Improves camera calibration for photogrammetry using neural networks

Innovation

• Hybrid distortion model combining conventional and neural network
• Higher-order terms extension of conventional distortion models
• Neural network residual correction for enhanced long-range accuracy