Method for performing thermal image processing
By identifying and segmenting obvious object regions in thermal images, and applying contrast enhancement steps and high-frequency filtering methods, the problem of limited dynamic range of thermal imagers under high radiation intensity is solved, and the ability to identify and track low-contrast objects is improved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- AXIS
- Filing Date
- 2024-11-29
- Publication Date
- 2026-06-19
AI Technical Summary
Existing thermal imagers have limited dynamic range in high-radiation-intensity monitoring applications, resulting in a reduced signal-to-noise ratio and making it difficult to effectively distinguish and track low-contrast objects.
By identifying and segmenting obvious object regions in thermal images, a contrast enhancement step is applied to divide blurred edge regions into background edges and object edges. Pixel intensity is adjusted to improve contrast, and high-frequency filtering is used for sharpening.
Without increasing computational complexity, it improves the contrast of thermal images and enhances the recognizability of low-contrast areas, making it suitable for object differentiation and tracking during surveillance activities.
Smart Images

Figure CN120107573B_ABST