Geri Dön

Spatiotemporal features and deep learning methods for video classification

Başlık çevirisi mevcut değil.

PDF İndir

  1. Tez No: 770941
  2. Yazar: RUKIYE SAVRAN KIZILTEPE
  3. Danışmanlar: PROF. JOHN Q GAN
  4. Tez Türü: Doktora
  5. Konular: Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrol, Elektrik ve Elektronik Mühendisliği, Computer Engineering and Computer Science and Control, Electrical and Electronics Engineering
  6. Anahtar Kelimeler: Belirtilmemiş.
  7. Yıl: 2022
  8. Dil: İngilizce
  9. Üniversite: University of Essex
  10. Enstitü: Yurtdışı Enstitü
  11. Ana Bilim Dalı: Belirtilmemiş.
  12. Bilim Dalı: Belirtilmemiş.
  13. Sayfa Sayısı: 169

Özet

Özet yok.

Özet (Çeviri)

Classification of human actions from real-world video data is one of the most important topics in computer vision and it has been an interesting and challenging research topic in recent decades. It is commonly used in many applications such as video retrieval, video surveillance, humancomputer interaction, robotics, and health care. Therefore, robust, fast, and accurate action recognition systems are highly demanded. Deep learning techniques developed for action recognition from the image domain can be extended to the video domain. Nonetheless, deep learning solutions for two-dimensional image data cannot be directly applicable for the video domain because of the larger scale and temporal nature of the video. Specifically, each frame involves spatial information, while the sequence of frames carries temporal information. Therefore, this study focused on both spatial and temporal features, aiming to improve the accuracy of human action recognition from videos by making use of spatiotemporal information. In this thesis, several deep learning architectures were proposed to model both spatial and temporal components. Firstly, a novel deep neural network was developed for video classification by combining Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). Secondly, an action template-based keyframe extraction method was proposed and temporal clues between action regions were used to extract more informative keyframes. Thirdly, a novel decision-level fusion rule was proposed to better combine spatial and temporal aspects of videos in two-stream networks. Finally, an extensive investigation was conducted to find out how to combine various information from feature and decision fusion to improve the video classification performance in multi-stream neural networks. Extensive experiments were conducted using the proposed methods and the results highlighted that using both spatial and temporal information is required in video classification architectures and employing temporal information effectively in multi-stream deep neural networks is crucial to improve video classification accuracy.

Benzer Tezler

  1. Tez No

    542575

    Human activity recognition using deep learning

    Derin öğrenme ile insan aktivitesi tanıma

    MURAT YALÇIN

    Yüksek Lisans

    İngilizce

    İngilizce

    2018

    Elektrik ve Elektronik Mühendisliğiİstanbul Teknik Üniversitesi

    Elektronik ve Haberleşme Mühendisliği Ana Bilim Dalı

    DR. ÖĞR. ÜYESİ HÜLYA YALÇIN

  2. Tez No

    761184

    Attention modeling with temporal shift in sign language recognition

    İşaret dili tanımada zamansal kayma ile dikkat modellemesi

    AHMET FARUK ÇELİMLİ

    Yüksek Lisans

    İngilizce

    İngilizce

    2022

    Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve KontrolBoğaziçi Üniversitesi

    Bilgisayar Mühendisliği Ana Bilim Dalı

    PROF. DR. LALE AKARUN ERSOY

  3. Tez No

    742492

    Nighttime fire detection from video

    Videodan gece yangın tespiti

    AHMET KERİM AĞIRMAN

    Doktora

    İngilizce

    İngilizce

    2022

    Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve KontrolAbdullah Gül Üniversitesi

    Elektronik ve Bilgisayar Mühendisliği Ana Bilim Dalı

    DR. ÖĞR. ÜYESİ KASIM TAŞDEMİR

  4. Tez No

    388272

    Video processing algorithms for wildfire surveillance

    Orman yangını gözetleme amaçlı video işleme algoritmaları

    OSMAN GÜNAY

    Doktora

    İngilizce

    İngilizce

    2015

    Elektrik ve Elektronik Mühendisliğiİhsan Doğramacı Bilkent Üniversitesi

    Elektrik-Elektronik Mühendisliği Ana Bilim Dalı

    PROF. DR. A. ENİS ÇETİN

  5. Tez No

    854831

    Video deinterlacing and demosaicing by deep learning

    Derin öğrenme ile video binisimsizlestirme ve demozaikleme

    RONGLEI JI

    Doktora

    İngilizce

    İngilizce

    2024

    Elektrik ve Elektronik MühendisliğiKoç Üniversitesi

    Elektrik ve Elektronik Mühendisliği Ana Bilim Dalı

    PROF. DR. AHMET MURAT TEKALP

Geri Dön