TUNGI SHAROITDA VIDEOKUZATUV TASVIRLARINI RAQAMLI FILTRLASH ASOSIDA KOMPYUTER KО‘RISH TIZIMLARINING ANIQLIGINI OSHIRISH
DOI:
https://doi.org/10.54613/ku.v18iC.1737Keywords:
raqamli filtr, videotasvir, IP-kamera, tungi tasvir, median filtr, bilateral filtr, CLAHE, gamma-korreksiya, obyektni aniqlash, OpenCVAbstract
Ushbu maqola raqamli filtrlash asosida IP video kuzatuv kameralaridan kechasi olinadigan tasvirlar bо‘yicha kompyuter kо‘rish tizimlarida obyektlarni aniqlashni yaxshilash vazifasiga bag‘ishlangan. Tajriba obyekti sifatida Hikvision IP Model: TL7534101K kamerasidan olingan tungi video kadrlar tanlandi. Tasvirlar shovqinga tо‘la kontrast past obyektlarning chegaralari aniq emas va yoritish juda past bо‘lganda rang komponentlari о‘rtasida kо‘plab nomuvofiqliklar mavjud. Bu sharoitlar harakatni aniqlash obyektni segmentatsiyalash va tasniflash algoritmlarining mustahkamligini cheklaydi. Tadqiqotimizda median Gaussian va bilateral filtrlar gamma-korreksiya hamda kontrastni cheklangan adaptiv gistogramma tenglashtirish CLAHE algoritmlarining tizim va signalni qayta ishlash qismlaridagi roli о‘rganildi. Har bir filtrning kompyuter kо‘rish natijalariga ta’siri ilmiy va amaliy jihatdan asoslangan bо‘lgan dastlabki preprotsessing ketma-ketligi taklif qilindi. Natijalar shuni kо‘rsatadiki tungi tasvirlarni kо‘rib chiqqanda bitta filtrning о‘zi yetarli emas va shovqinni mahalliy kontrastni hamda konturlarni moslashtirishga qaratilgan yanada ilg‘or xususiyatlarda kо‘rsatilgandek juda ma’qul hisoblanadi.
Foydalanilgan adabiyotlar:
Bommes M. Fazekas A. Volkenhoff T. Oeser M. Video Based Intelligent Transportation Systems – State of the Art and Future Development. Transportation Research Procedia 2016.
2. Gonzalez R.C. Woods R.E. Digital Image Processing. 4th edition. Pearson 2018.
3. Tran D.Q. Aboah A. Jeon Y. Shoman M. Park M. Park S. Low-Light Image Enhancement Framework for Improved Object Detection in Fisheye Lens Datasets. CVPR Workshops 2024.
4. Gonzalez R.C. Woods R.E. Digital Image Processing. 4th edition. Pearson 2018.
5. OpenCV Documentation. Image Filtering; Redmon J. Divvala S. Girshick R. Farhadi A. You Only Look Once: Unified Real-Time Object Detection. CVPR 2016.
6. Tran D.Q. Aboah A. Jeon Y. Shoman M. Park M. Park S. Low-Light Image Enhancement Framework for Improved Object Detection in Fisheye Lens Datasets. CVPR Workshops 2024.
7. Liu F. va boshqalar. A review of advancements in low-light image enhancement using deep learning. Neurocomputing 2025.
Downloads
Published
Iqtiboslik olish
Issue
Section
License
Copyright (c) 2026 QO‘QON UNIVERSITETI XABARNOMASI
This work is licensed under a Creative Commons Attribution 4.0 International License.