基於巨觀邊緣感知與對比圖分析的高動態範圍成像
| dc.contributor | 高文忠 | zh_TW |
| dc.contributor | Kao, Wen-Chung | en_US |
| dc.contributor.author | 鄭翔元 | zh_TW |
| dc.contributor.author | Cheng, Hsiang-Yuan | en_US |
| dc.date.accessioned | 2025-12-09T08:31:20Z | |
| dc.date.available | 2025-08-14 | |
| dc.date.issued | 2025 | |
| dc.description.abstract | 本研究主要探討高動態範圍影像處理中,在極端光照條件下的影像主體重建與色調映射問題。當畫面遭遇強烈背光、低光源或大面積背景干擾時,傳統的影像處理方法經常無法有效地凸顯主體,且在壓縮動態範圍過程中容易造成細節喪失與色彩失真。本研究針對上述問題,提出一套考慮巨集邊緣資訊的影像處理方法,結合全域與區域對比度評估,透過調整適合的色調映射曲線,使暗部細節清晰且避免亮部過曝。此外,研究中亦針對色彩還原問題,於色彩轉換過程中引入色域映射模型的補償機制,有效避免傳統方法常見的色相偏移與飽和失真現象。本論文透過實驗驗證所提出方法的有效性,並經由業界常見的客觀指標評估其在亮度、色彩準確性與視覺對比度上的改善效果,期望能提供未來影像訊號處理系統設計的重要參考。 | zh_TW |
| dc.description.abstract | This study addresses subject reconstruction and tone mapping in HDR images under extreme lighting—strong backlight, low illumination, or large-area distractions. We propose a framework that leverages macro-edge information and combines global and local contrast evaluation to adapt tone-mapping curves, preserving shadow detail without over-exposing highlights. To improve color fidelity, an OKLab-based compensation is applied during color conversion, reducing hue shifts and saturation errors. Experimental results and VCX metrics confirm notable gains in luminance reconstruction, color accuracy, and visual contrast, offering a practical reference for future ISP system design. | en_US |
| dc.description.sponsorship | AI跨域應用研究所 | zh_TW |
| dc.identifier | 612K0020C-48366 | |
| dc.identifier.uri | https://etds.lib.ntnu.edu.tw/thesis/detail/71e44b4e5a49c1f02f5c0dde7a89bbd8/ | |
| dc.identifier.uri | http://rportal.lib.ntnu.edu.tw/handle/20.500.12235/126198 | |
| dc.language | 中文 | |
| dc.subject | 高動態範圍 | zh_TW |
| dc.subject | 色調重現 | zh_TW |
| dc.subject | 色域映射 | zh_TW |
| dc.subject | 對比增強 | zh_TW |
| dc.subject | HDR | en_US |
| dc.subject | Tone Reproduction | en_US |
| dc.subject | Tone Mapping | en_US |
| dc.subject | Contrast Enhancement | en_US |
| dc.title | 基於巨觀邊緣感知與對比圖分析的高動態範圍成像 | zh_TW |
| dc.title | High Dynamic Range Imaging via Macro-Edge Awareness and Contrast Map Analysis | en_US |
| dc.type | 學術論文 |
Files
Original bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- 202500048366-110691.pdf
- Size:
- 8.48 MB
- Format:
- Adobe Portable Document Format
- Description:
- 學術論文