|
|
Exploitation of Graphics Processor as Accelerator - OpenCL Technology
Hrubý, Michal ; Jošth, Radovan (referee) ; Zemčík, Pavel (advisor)
This work deals with the OpenCL technology and its use for the task of object detection. The introduction is devoted to description of OpenCL fundamentals, as well as basic theory of object detection. Next chapter of the work is analysis, with design proposal which takes into consideration the possibilities of OpenCL. Further, there's description of implementation of detection application and experimental evaluation of detector's performance. The last chapter summarizes the achieved results.
|
|
|
Detecting Objects in Images
Kubínek, Jiří ; Beran, Vítězslav (referee) ; Hradiš, Michal (advisor)
This work is dedicated to methods used for object detection in images. There is a summary of several approaches and algorithms to solve this matter, especially AdaBoost algorithm with its improvement, WaldBoost and several features used for object detection. Vital part of this work is dedicated to extending training datasets for classifier training and extending the current object detection framework with histogram of gradients features implementation. Integral part of this work is analysis of results by experiments evaluation.
|
|
|
Object Detection Using Kinect
Řehánek, Martin ; Hradiš, Michal (referee) ; Španěl, Michal (advisor)
With the release of the Kinect device new possibilities appeared, allowing a simple use of image depth in image processing. The aim of this thesis is to propose a method for object detection and recognition in a depth map. Well known method Bag of Words and a descriptor based on Spin Image method are used for the object recognition. The Spin Image method is one of several existing approaches to depth map which are described in this thesis. Detection of object in picture is ensured by the sliding window technique. That is improved and speeded up by utilization of the depth information.
|
|
|
Object Detection and Tracking Using Interest Points
Bílý, Vojtěch ; Hradiš, Michal (referee) ; Juránek, Roman (advisor)
This paper deals with object detection and tracking using iterest points. Existing approaches are described here. Inovated method based on Generalized Hough transform and iterative Hough-space searching is proposed in this paper. Generality of proposed detector is shown in various types of objects. Object tracking is designed as frame by frame detection.
|
|
|
Raster Image Processing Using FPGA
Musil, Petr ; Kadlček, Filip (referee) ; Zemčík, Pavel (advisor)
This thesis describes the design and implementation of hardware unit to detect objects in the image. Design of unit is optimized for fast streaming processing. Object detection is performed by the trained classifiers using local image features. It describes a new technique for multi-scale detection. Detector used accelerating algorithm based on neighboring positions. The correct functionality of the detector is verified by simulation and part of a whole is implemented on development kit.
|
|
|
Learning Detectors by Tracking
Buchtela, Radim ; Beran, Vítězslav (referee) ; Hradiš, Michal (advisor)
This thesis is devoted to learn detectors by object tracking in video sequence. In this thesis, we discuss methods for object tracking, object detection and online learning and possibilities of their using in sophisticated techniques, which combine object tracking and online learning detectors.
|
|
|
Object Detection Using Hough Transform
Chroboczek, Martin ; Španěl, Michal (referee) ; Juránek, Roman (advisor)
This diploma thesis deals with object detection using mathematical technique called Hough transform. Hough transform technique is conceived in general terms from the de facto simplest use for the detection of elementary analytically describable shapes such as lines, ellipses, circles or simple analytically definable elements to sophisticated use for the detection of complex - analytically virtually indescribable - objects. These include cars or pedestrians who are detected on the basis of the photographic records of these objects and entities. The document thus maps the definition and use of the respective Hough transform subtechniques along with their basic classification on probabilistic and non-probabilistic methods. The work subsequently culminates in describing the general state-of-the-art technique called Class-Specific Hough Forests for Object Detection, introduces its definition, training procedure on a provided dataset and the detection of test patterns. In conclusion of this work,there is designed and implemented generally trainable object detector using this technique. And there is experimental evaluation of its quality.
|
|
|
Object Detection Using Kinect
Němec, Lukáš ; Veľas, Martin (referee) ; Španěl, Michal (advisor)
This paper address the problem of object recognition using Microsoft Kinect in the fi eld of computer vision. The objective of this work was to evaluate current methods of detection of objects using depth map (RGB-D sensor). The work deals with the enviroment of point cloud and Viewpoint Feature method. It also describes the use of binary classifi er in the context of object recognition. Object detection was implemented and performed experiments with it.
|
|
|
Estimation of Object Parameters from Images
Přibyl, Bronislav ; Hradiš, Michal (referee) ; Zemčík, Pavel (advisor)
Rapid expansion of communication technologies in last decade caused increased volume of information which is beeing generated and shared by people and organisations. It is permanently harder to identify relevant content today because of absence of tools and techniques which may support mass information management. As today's media have rather multimedial character image information is even more important. This project describes software for automatic estimation of predefined object parameters from images. A C++ implementation of this algorithm is also described.
|
|
|
Object Detection and Recognition in Image
Muzikářová, Michaela ; Hradiš, Michal (referee) ; Zemčík, Pavel (advisor)
This bachelor's thesis deals with design and implementation of client-server application for object recognition with the use of existing mobile application. Theoretical part describes the differences between human and computer vision, followed by information about object detection and recognition with selected methods. The next section provides a detailed overview of artificial neural networks, which were used for this work, with their qualities for object recognition. Following part examines selected mobile applications for object recognition, followed by existing frameworks and libraries with focus on artificial neural networks. Among these, Caffe Framework was selected for the work. The next section illustrates the progress of design and implementation and describes the system, along with experiments and dataset used to prove its functionality.
|
guest ::
