GPU-enabled real-time panoramic background subtraction

Download

index.pdf

Date

2015

Author

Büyüksaraç, Serdar

Metadata

Show full item record

Item Usage Stats

107
views

55
downloads

Extraction of foreground objects using a Pan-Tilt camera is a challenging task for various video surveillance applications. It requires several steps such as camera motion extraction, image registration, panorama generation and background subtraction. All these steps require significant computing power. While achieving this by using only Central Processing Unit (CPU) is a challenging task, it might be enabled by efficient parallelization of the algorithms to run on Graphics Processing Unit (GPU). In this thesis an adaptive panoramic background generation and foreground object detection algorithm is implemented on GPU/CPU to run in real-time.

Subject Keywords

Image processing., Digital cameras., Computer graphics., Graphics processing units.

URI

http://etd.lib.metu.edu.tr/upload/12619329/index.pdf
https://hdl.handle.net/11511/25045

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

Camera electronics and image enhancement software for infrared detector arrays Küçükkömürler, Alper; Akın, Tayfun; Department of Environmental Engineering (2012) This thesis aims to design and develop camera electronics and image enhancement software for infrared detector arrays. It first discusses the camera electronics suitable for infrared detector arrays, then it concentrates on image enhancement software that are implemented including defective pixel correction, contrast enhancement, noise reduction and pseudo coloring. After that, testing and results of the implemented algorithms were presented. Camera electronics and circuit operation frequency are selected c...
OCCLUSION-AWARE 3D MULTIPLE OBJECT TRACKER WITH TWO CAMERAS FOR VISUAL SURVEILLANCE Topcu, Osman; Alatan, Abdullah Aydın; ERCAN, ALİ ÖZER (2014-08-29) An occlusion-aware multiple deformable object tracker for visual surveillance from two cameras is presented. Each object is tracked by a separate particle filter tracker, which is initiated upon detection of a new person and terminated when s/he leaves the scene. Objects are considered as 3D points at their centre of masses as if their mass density is uniform. Point objects and corresponding silhouette centroids in two views together with the epipolar geometry they satisfy resulted in a practical tracking m...
Efficient MRF Energy Propagation for Video Segmentation via Bilateral Filters Sener, Ozan; Ugur, Kemal; Alatan, Abdullah Aydın (Institute of Electrical and Electronics Engineers (IEEE), 2014-08-01) Segmentation of an object from a video is a challenging task in multimedia applications. Depending on the application, automatic or interactive methods are desired; however, regardless of the application type, efficient computation of video object segmentation is crucial for time-critical applications; specifically, mobile and interactive applications require near real-time efficiencies. In this paper, we address the problem of video segmentation from the perspective of efficiency. We initially redefine the...
Comparison of histograms of oriented optical flow based action recognition methods Erciş, Fırat; Ulusoy, İlkay; Department of Electrical and Electronics Engineering (2012) In the task of human action recognition in uncontrolled video, motion features are used widely in order to achieve subject and appearence invariance. We implemented 3 Histograms of Oriented Optical Flow based method which have a common motion feature extraction phase. We compute an optical flow field over each frame of the video. Then those flow vectors are histogrammed due to angle values to represent each frame with a histogram. In order to capture local motions, The bounding box of the subject is divided...
Optical flow based video frame segmentation and segment classification Akpınar, Samet; Alpaslan, Ferda Nur; Department of Computer Engineering (2018) Video information retrieval is a field of multimedia research enabling us to extract desired semantic information from video data. In content-based video information retrieval, visual content obtained from video scenes is utilized. For developing methods to cope with content-based video information retrieval in terms of temporal concepts such as action, event, etc., representation of temporal information becomes critical. In this thesis, action detection is tackled based on a temporal video representation m...

Citation Formats

S. Büyüksaraç, “GPU-enabled real-time panoramic background subtraction,” M.S. - Master of Science, Middle East Technical University, 2015.