No description available.

Recent research approaches in semantics based video content analysis require shot boundary detection as the first step to divide video sequences into sections. Furthermore, with the advances in networking and computing capability, efficient retrieval of multimedia data has become an important issue. Content-based retrieval technologies have been widely implemented to protect intellectual property rights (IPR). In addition, automatic recognition of highlights from videos is a fundamental and challenging problem for content-based indexing and retrieval applications. In this thesis, a paradigm is proposed to segment, retrieve and interpret digital videos. Five algorithms are presented to solve the video segmentation task. Firstly, a simple shot cut detection algorithm is designed for real-time implementation. Secondly, a systematic method is proposed for shot detection using content-based rules and FSM (finite state machine). Thirdly, the shot detection is implemented using local and global indicators. Fourthly, a context awareness approach is proposed to detect shot boundaries. Fifthly, a fuzzy logic method is implemented for shot detection. Furthermore, a novel analysis approach is presented for the detection of video copies. It is robust to complicated distortions and capable of locating the copy of segments inside original videos. Then, iv objects and events are extracted from MPEG Sequences for Video Highlights Indexing and Retrieval. Finally, a human fighting detection algorithm is proposed for movie annotation.

The production line of industries are getting more efficient and having very high throughput. Different kinds of machineries are being used to make the production safe, fast, precise and reliable. Robot arm is such a machine which helps the production line to be more efficient and productive. Nowadays, many manufacturing industries are using robot-arms to get a competitive edge in manufacturing and can be outfitted for multiple applications like welding, material handling, thermal spraying, painting, drilling and so on. They are widely used to increase product quality and production demand and over all, to ensure safer, faster and efficient production. It is very important to control and maintain these machines very accurately. As a simple mistake of robot arm can cause excessive destructions and bring financial losses to the industries, the robotarms must be very accurate when they are functioning in their production settings.

Inthisthesiswefocusontheimpactofilluminationchangesinvideoand we discuss how we can minimize the impact of illumination variance in video processing systems. Identifyingandremovingshadowsautomaticallyisaverywellestablished and an important topic in image and video processing. Having shadowless image data would benefit many other systems such as video surveillance, tracking and object recognition algorithms. Anovelapproachtoautomaticallydetectandremoveshadowsispresented in this paper. This new method is based on the observation that, owing to the relative movement of the sun, the length and position of a shadow changes linearly over a relatively long period of time in outdoor environments,wecanconvenientlydistinguishashadowfromotherdark regions in an input video. Then we can identify the Reference Shadow as the one with the highest confidence of the mentioned linear changes. Once one shadow is detected, the rest of the shadow can also be identifiedandremoved. Wehaveprovidedmanyexperimentsandourmethod is fully capable of detecting and removing the shadows of stationary and moving objects. Additionally we have explained how reference shadows can be used to detect textures that reflect the light and shiny materials such as metal, glass and water. ...

The rise of deep learning has facilitated remarkable progress in video understanding. This thesis addresses three important tasks of video understanding: video object detection, joint object and action detection, and spatio-temporal action localization. Object class detection is one of the most important challenges in computer vision. Object detectors are usually trained on bounding-boxes from still images. Recently, video has been used as an alternative source of data. Yet, training an object detector on one domain (either still images or videos) and testing on the other one results in a significant performance gap compared to training and testing on the same domain. In the first part of this thesis, we examine the reasons behind this performance gap. We define and evaluate several domain shift factors: spatial location accuracy, appearance diversity, image quality, aspect distribution, and object size and camera framing. We examine the impact of these factors by comparing the detection performance before and after cancelling them out. The results show that all five factors affect the performance of the detectors and their combined effect explains the performance gap. While most existing approaches for detection in videos focus on objects or human actions separately, in the second part of this thesis we aim at detecting non-human centric actions, i.e., objects performing actions, such as cat eating or dog jumping. We introduce an end-to-end multitask objective that jointly learns object-action relationships. We compare it with different training objectives, validate its effectiveness for detecting object-action pairs in videos, and show that both tasks of object and action detection benefit from this joint learning. In experiments on the A2D dataset [Xu et al., 2015], we obtain state-of-the-art results on segmentation of object-action pairs. In the third part, we are the first to propose an action tubelet detector that leverages the temporal continuity of videos instead of operating at the frame level, as state-of-the-art approaches do. The same way modern detectors rely on anchor boxes, our tubelet detector is based on anchor cuboids by taking as input a sequence of frames and outputing tubelets, i.e., sequences of bounding boxes with associated scores. Our tubelet detector outperforms all state of the art on the UCF-Sports [Rodriguez et al., 2008], J-HMDB [Jhuang et al., 2013a], and UCF-101 [Soomro et al., 2012] action localization datasets especially at high overlap thresholds. The improvement in detection performance is explained by both more accurate scores and more precise localization.

This diploma thesis deals with the detection of fire and smoke from the image signal. The approach of this work uses a combination of convolutional and recurrent neural network. Machine learning models created in this work contain inception modules and blocks of long short-term memory. The research part describes selected models of machine learning used in solving the problem of fire detection in static and dynamic image data. As part of the solution, a data set containing videos and still images used to train the designed neural networks was created. The results of this approach are evaluated in conclusion.

The production line of industries are getting more efficient and having very high throughput. Different kinds of machineries are being used to make the production safe, fast, precise and reliable. Robot arm is such a machine which helps the production line to be more efficient and productive. Nowadays, many manufacturing industries are using robot-arms to get a competitive edge in manufacturing and can be outfitted for multiple applications like welding, material handling, thermal spraying, painting, drilling and so on. They are widely used to increase product quality and production demand and over all, to ensure safer, faster and efficient production. It is very important to control and maintain these machines very accurately. As a simple mistake of robot arm can cause excessive destructions and bring financial losses to the industries, the robotarms must be very accurate when they are functioning in their production settings.

The surveillance cameras serve various purposes ranging from security to traffic monitoring and marketing. However, with the increasing quantity of utilized cameras, manual video monitoring has become too laborious. In re- cent years, a lot of development in artificial intelligence has been focused on processing the video data automatically and then outputting the desired no- tifications and statistics. This thesis studies the state-of-the-art deep learning models for object detection in a surveillance video and takes an in-depth look at SSD architecture. We aim to enhance the performance of SSD by updating its underlying feature extraction network. We propose to replace the initially used VGG model by a selection of modern ResNet, Xception and NASNet classifica- tion networks. The experiments show that the ResNet50 model offers the best trade-off between speed and precision, while significantly outperforming VGG. With a series of modifications, we improved the Xception model to match the ResNet performance. On top of the architecture-based improvements, we ana- lyze the relationship between SSD and a number of detected classes and their selection. We also designed and implemented a new detector with the use of temporal context provided by the video frames. This detector delivers enhanced precision while...

Development of Internet and its massive spread resulted in increased volume of multimedia data. The increase in the amount of multimedia data raises the need for efficient similarity detection between multimedia files for the purpose of preventing and detecting violations of copyright licenses or for detection of similar or duplicate files. This thesis discusses the current options in the field of the content-based image and video comparison and focuses on the feature extraction techniques, distance metrics, design and implementation of the mediaDiff application module for the content-based comparison of video files.

Diese Studienarbeit gibt einen Überblick über ausgewählte Teile des Softwareentwicklungsprozesses für sicherheitsrelevante Applikationen am Beispiel eines videobasierten Zugerkennungssystems. Eine IP-Kamera und ein externer Bildverarbeitungscomputer wurden dazu mit einer speziell entworfenen, verteilten Software ausgestattet. Die in Ada und C geschriebenen Teile kommunizieren dabei über ein dediziertes, UDP-basiertes Netzwerkprotokoll. Beide Programme wurden intensiv anhand verschiedener Techniken analysiert, die in der Norm EN 50128 festgelegt sind, welche sich speziell an Software für Eisenbahnsteuerungs- und überwachungssysteme richtet. Eine an der Norm orientierte Struktur mit Verweisen auf die diskutierten Techniken zu Beginn eines jeden Abschnitts erlaubt einen schnellen Vergleich mit den originalen Anforderungen des Normtexts. Zusammenfassend haben sich die Techniken bis auf wenige Ausnahmen als sehr geeignet für die praktische Entwicklung von sicherer Software erwiesen. Allerdings entbindet die Norm durch ihre teils sehr abstrakten Anforderungen das am Projekt beteiligte Personal in keinster Weise von seiner individuellen Verantwortung. Entsprechend sind die hier vorgestellten Techniken für andere Projekte nicht ohne Anpassungen zu übernehmen.:1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 1.2 Description of the problem . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 1.3 Real-time constraints . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 1.4 Safety requirements . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 2 Implementation details . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 2.1 Camera type and output format . . . . . . . . . . . . . . . . . . . . . . . . . 11 2.2 Transfer Protocol . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 2.3 Real-world constrains . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 2.4 Train Detection Algorithm . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 3 EN 50128 requirements . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 3.1 Software architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 3.1.1 Defensive Programming . . . . . . . . . . . . . . . . . . . . . . . 20 3.1.2 Fully Defined Interface . . . . . . . . . . . . . . . . . . . . . . . . 21 3.1.3 Structured Methodology . . . . . . . . . . . . . . . . . . . . . . . 21 3.1.4 Error Detecting and Correcting Codes . . . . . . . . . . . . . . . . 29 3.1.5 Modelling . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30 3.1.6 Alternative optionally required measures . . . . . . . . . . . . . . 34 3.2 Software Design and Implementation . . . . . . . . . . . . . . . . . . . . . 35 3.2.1 Structured Methodology . . . . . . . . . . . . . . . . . . . . . . . 35 3.2.2 Modular Approach . . . . . . . . . . . . . . . . . . . . . . . . . . . 36 3.2.3 Components . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38 3.2.4 Design and Coding Standards . . . . . . . . . . . . . . . . . . . . 39 3.2.5 Strongly Typed Programming Languages . . . . . . . . . . . . . . 41 3.2.6 Alternative optionally required measures . . . . . . . . . . . . . . 44 3.3 Unit Testing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45 4 Outlook . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 47 5 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 48 / This paper intends to give an overview of selected parts of the software development process for safety-relevant applications using the example of a video-based train detection. An IP-camera and an external image processing computer were equipped with a custom-built, distributed software system. Written in Ada and C, the system parts communicate via a dedicated UDP-based protocol. Both programs were subject to intense analysis according to measures laid down in the EN 50128 standard specifically targeted at software for railway control and protection systems. Preceding each section, a structure resembling the standard document with references to the discussed measures allows for easy comparison with the original requirements of EN 50128. In summary, the techniques have proven to be very suitable for practical safe software development in all but very few edge-cases. However, the highly abstract descriptive level of the standard requires the staff involved to accept an enormous personal responsibility throughout the entire development process. The specific measures carried out for this project may therefore not be equally applicable elsewhere.:1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 1.2 Description of the problem . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 1.3 Real-time constraints . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 1.4 Safety requirements . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 2 Implementation details . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 2.1 Camera type and output format . . . . . . . . . . . . . . . . . . . . . . . . . 11 2.2 Transfer Protocol . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 2.3 Real-world constrains . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 2.4 Train Detection Algorithm . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 3 EN 50128 requirements . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 3.1 Software architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 3.1.1 Defensive Programming . . . . . . . . . . . . . . . . . . . . . . . 20 3.1.2 Fully Defined Interface . . . . . . . . . . . . . . . . . . . . . . . . 21 3.1.3 Structured Methodology . . . . . . . . . . . . . . . . . . . . . . . 21 3.1.4 Error Detecting and Correcting Codes . . . . . . . . . . . . . . . . 29 3.1.5 Modelling . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30 3.1.6 Alternative optionally required measures . . . . . . . . . . . . . . 34 3.2 Software Design and Implementation . . . . . . . . . . . . . . . . . . . . . 35 3.2.1 Structured Methodology . . . . . . . . . . . . . . . . . . . . . . . 35 3.2.2 Modular Approach . . . . . . . . . . . . . . . . . . . . . . . . . . . 36 3.2.3 Components . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38 3.2.4 Design and Coding Standards . . . . . . . . . . . . . . . . . . . . 39 3.2.5 Strongly Typed Programming Languages . . . . . . . . . . . . . . 41 3.2.6 Alternative optionally required measures . . . . . . . . . . . . . . 44 3.3 Unit Testing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45 4 Outlook . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 47 5 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 48