Comparison of Local Feature Detectors and Descriptors for Visual Object Categorization

Local features are used in many computer vision tasks including visual object categorization, content-based image retrieval and object recognition to mention a few. Local features are points, blobs or regions in images that are extracted using a local feature detector. To make use of extracted local features the localized interest points are described using a local feature descriptor. A descriptor histogram vector is a compact representation of an image and can be used for searching and matching images in databases. In this thesis the performance of local feature detectors and descriptors is evaluated for object class detection task. Features are extracted from image samples belonging to several object classes. Matching features are then searched using random image pairs of a same class. The goal of this thesis is to find out what are the best detector and descriptor methods for such task in terms of detector repeatability and descriptor matching rate.

Bag-of-Features Approach to Unsupervised Visual Object Categorisation

The large and growing number of digital images is making manual image search laborious. Only a fraction of the images contain metadata that can be used to search for a particular type of image. Thus, the main research question of this thesis is whether it is possible to learn visual object categories directly from images. Computers process images as long lists of pixels that do not have a clear connection to high-level semantics which could be used in the image search. There are various methods introduced in the literature to extract low-level image features and also approaches to connect these low-level features with high-level semantics. One of these approaches is called Bag-of-Features which is studied in the thesis. In the Bag-of-Features approach, the images are described using a visual codebook. The codebook is built from the descriptions of the image patches using clustering. The images are described by matching descriptions of image patches with the visual codebook and computing the number of matches for each code. In this thesis, unsupervised visual object categorisation using the Bag-of-Features approach is studied. The goal is to find groups of similar images, e.g., images that contain an object from the same category. The standard Bag-of-Features approach is improved by using spatial information and visual saliency. It was found that the performance of the visual object categorisation can be improved by using spatial information of local features to verify the matches. However, this process is computationally heavy, and thus, the number of images must be limited in the spatial matching, for example, by using the Bag-of-Features method as in this study. Different approaches for saliency detection are studied and a new method based on the Hessian-Affine local feature detector is proposed. The new method achieves comparable results with current state-of-the-art. The visual object categorisation performance was improved by using foreground segmentation based on saliency information, especially when the background could be considered as clutter.

Hand tracking in high-speed camera videos

Visual object tracking has been one of the most popular research topics in the field of computer vision recently. Specifically, hand tracking has attracted significant attention since it would enable many useful practical applications. However, hand tracking is still a very challenging problem which cannot be considered solved. The fact that almost every aspect of hand appearance can change is the fundamental reason for this difficulty. This thesis focused on 2D-based hand tracking in high-speed camera videos. During the project, a toolbox for this purpose was collected which contains nine different tracking methods. In the experiments, these methods were tested and compared against each other with both high-speed videos recorded during the project and publicly available normal speed videos. The results revealed that tracking accuracies varied considerably depending on the video and the method. Therefore, no single method was clearly the best in all videos, but three methods, CT, HT, and TLD, performed better than the others overall. Moreover, the results provide insights about the suitability of each method to different types and situations of hand tracking.

Probabilistic position and orientation estimation of rigid objects using an RGB-D sensor

The recent emergence of low-cost RGB-D sensors has brought new opportunities for robotics by providing affordable devices that can provide synchronized images with both color and depth information. In this thesis, recent work on pose estimation utilizing RGBD sensors is reviewed. Also, a pose recognition system for rigid objects using RGB-D data is implemented. The implementation uses half-edge primitives extracted from the RGB-D images for pose estimation. The system is based on the probabilistic object representation framework by Detry et al., which utilizes Nonparametric Belief Propagation for pose inference. Experiments are performed on household objects to evaluate the performance and robustness of the system.

Local Features in Image and Video Processing - Object Class Matching and Video Shot Detection

The usage of digital content, such as video clips and images, has increased dramatically during the last decade. Local image features have been applied increasingly in various image and video retrieval applications. This thesis evaluates local features and applies them to image and video processing tasks. The results of the study show that 1) the performance of different local feature detector and descriptor methods vary significantly in object class matching, 2) local features can be applied in image alignment with superior results against the state-of-the-art, 3) the local feature based shot boundary detection method produces promising results, and 4) the local feature based hierarchical video summarization method shows promising new new research direction. In conclusion, this thesis presents the local features as a powerful tool in many applications and the imminent future work should concentrate on improving the quality of the local features.

Post-processing and analysis of tracked hand trajectories

In this thesis, the suitability of different trackers for finger tracking in high-speed videos was studied. Tracked finger trajectories from the videos were post-processed and analysed using various filtering and smoothing methods. Position derivatives of the trajectories, speed and acceleration were extracted for the purposes of hand motion analysis. Overall, two methods, Kernelized Correlation Filters and Spatio-Temporal Context Learning tracking, performed better than the others in the tests. Both achieved high accuracy for the selected high-speed videos and also allowed real-time processing, being able to process over 500 frames per second. In addition, the results showed that different filtering methods can be applied to produce more appropriate velocity and acceleration curves calculated from the tracking data. Local Regression filtering and Unscented Kalman Smoother gave the best results in the tests. Furthermore, the results show that tracking and filtering methods are suitable for high-speed hand-tracking and trajectory-data post-processing.

Automatic image-based identification of Saimaa ringed seals

The Saimaa ringed seal is one of the most endangered seals in the world. It is a symbol of Lake Saimaa and a lot of effort have been applied to save it. Traditional methods of seal monitoring include capturing the animals and installing sensors on their bodies. These invasive methods for identifying can be painful and affect the behavior of the animals. Automatic identification of seals using computer vision provides a more humane method for the monitoring. This Master's thesis focuses on automatic image-based identification of the Saimaa ringed seals. This consists of detection and segmentation of a seal in an image, analysis of its ring patterns, and identification of the detected seal based on the features of the ring patterns. The proposed algorithm is evaluated with a dataset of 131 individual seals. Based on the experiments with 363 images, 81\% of the images were successfully segmented automatically. Furthermore, a new approach for interactive identification of Saimaa ringed seals is proposed. The results of this research are a starting point for future research in the topic of seal photo-identification.

Generative Part-Based Gabor Object Detector

Object detection is a fundamental task of computer vision that is utilized as a core part in a number of industrial and scientific applications, for example, in robotics, where objects need to be correctly detected and localized prior to being grasped and manipulated. Existing object detectors vary in (i) the amount of supervision they need for training, (ii) the type of a learning method adopted (generative or discriminative) and (iii) the amount of spatial information used in the object model (model-free, using no spatial information in the object model, or model-based, with the explicit spatial model of an object). Although some existing methods report good performance in the detection of certain objects, the results tend to be application specific and no universal method has been found that clearly outperforms all others in all areas. This work proposes a novel generative part-based object detector. The generative learning procedure of the developed method allows learning from positive examples only. The detector is based on finding semantically meaningful parts of the object (i.e. a part detector) that can provide additional information to object location, for example, pose. The object class model, i.e. the appearance of the object parts and their spatial variance, constellation, is explicitly modelled in a fully probabilistic manner. The appearance is based on bio-inspired complex-valued Gabor features that are transformed to part probabilities by an unsupervised Gaussian Mixture Model (GMM). The proposed novel randomized GMM enables learning from only a few training examples. The probabilistic spatial model of the part configurations is constructed with a mixture of 2D Gaussians. The appearance of the parts of the object is learned in an object canonical space that removes geometric variations from the part appearance model. Robustness to pose variations is achieved by object pose quantization, which is more efficient than previously used scale and orientation shifts in the Gabor feature space. Performance of the resulting generative object detector is characterized by high recall with low precision, i.e. the generative detector produces large number of false positive detections. Thus a discriminative classifier is used to prune false positive candidate detections produced by the generative detector improving its precision while keeping high recall. Using only a small number of positive examples, the developed object detector performs comparably to state-of-the-art discriminative methods.

Feature-based camera pose estimation

The estimating of the relative orientation and position of a camera is one of the integral topics in the field of computer vision. The accuracy of a certain Finnish technology company’s traffic sign inventory and localization process can be improved by utilizing the aforementioned concept. The company’s localization process uses video data produced by a vehicle installed camera. The accuracy of estimated traffic sign locations depends on the relative orientation between the camera and the vehicle. This thesis proposes a computer vision based software solution which can estimate a camera’s orientation relative to the movement direction of the vehicle by utilizing video data. The task was solved by using feature-based methods and open source software. When using simulated data sets, the camera orientation estimates had an absolute error of 0.31 degrees on average. The software solution can be integrated to be a part of the traffic sign localization pipeline of the company in question.

The Formation Of Internationalization Strategies Within The Construction Industry:Vision and Strategy

Internationalization represents a complex topic that has been researched for quite some time. However, since it continues to be extremely current a topic, its significance has not diminished, but maybe even increased in importance. Companies today face extreme pressure to enter new markets in the hope of growing, becoming more profitable, increasing market share, attracting new customers and meeting the requirements of its share- and stakeholders. In the increasingly global business environment of today, companies are facing both challenges and possible advantages of internationalization. Few companies are not operating internationally and it is becoming the question of ‘Why not?’ rather than ‘Why?’ to internationalize business operations. Internationalization and the importance of strategy are discussed in this research from the viewpoint of three case companies that were interviewed about internationalization strategies. This research project is a qualitative study that answers the research question of How is a business strategy constructed for entering a new market? The sub-questions are • How are goals set and what indicators are used to monitor the achievement of these goals? • What are the key characteristics of a strategy implementation process? The research method chosen for this study is a multiple-case study. Three case companies were chosen for the interviews in order to gain in-depth data of internationalization strategies within the construction industry.

Value added logistics in supply and demand chain. Smile. Part 2. eBusiness in a service business. Case: A maintenance and operations network in forest industry

VVALOSADE is a research project of professor Anita Lukka's VALORE research team in the Lappeenranta University of Technology. The VALOSADE includes the ELO technology program of Tekes. SMILE is one of four subprojects of the VALOSADE. The SMILE study focuses on the case of the company network that is composed of small and micro-sized mechanical maintenance service providers and forest industry as large-scale customers. The basic principle of the SMILE study is the communication and ebusiness in supply and demand networks. The aim of the study is to develop ebusiness strategy, ebusiness model and e-processes among the SME local service providers, and onthe other hand, between the local service provider network and the forest industry customers in a maintenance and operations service business. A literature review, interviews and benchmarking are used as research methods in this qualitative case study. The first SMILE report, 'Ebusiness between Global Company and Its Local SME Supplier Network', concentrated on creating background for the SMILE study by studying general trends of ebusiness in supply chains and networks of different industries. This second phase of the study concentrates on case network background, such as business relationships, information systems and business objectives; core processes in maintenance and operations service network; development needs in communication among the network participants; and ICT solutions to respond needs in changing environment. In the theory part of the report, different ebusiness models and frameworks are introduced. Those models and frameworks are compared to empirical case data. From that analysis of the empirical data, therecommendations for the development of the network information system are derived. In process industry such as the forest industry, it is crucial to achieve a high level of operational efficiency and reliability, which sets up great requirements for maintenance and operations. Therefore, partnerships or strategic alliances are needed between the network participants. In partnerships and alliances, deep communication is important, and therefore the information systems in the network also are critical. Communication, coordination and collaboration will increase in the case network in the future, because network resources must be optimised to improve competitive capability of the forest industry customers and theefficiency of their service providers. At present, ebusiness systems are not usual in this maintenance network. A network information system among the forest industry customers and their local service providers actually is the only genuinenetwork information system in this total network. However, the utilisation of that system has been quite insignificant. The current system does not add value enough either to the customers or to the local service providers. At present, thenetwork information system is the infomediary that share static information forthe network partners. The network information system should be the transaction intermediary, which integrates internal processes of the network companies; the network information system, which provides common standardised processes for thelocal service providers; and the infomediary, which share static and dynamic information on right time, on right partner, on right costs, on right format and on right quality. This study provides recommendations how to develop this system in the future to add value to the network companies. Ebusiness scenarios, vision, objectives, strategies, application architecture, ebusiness model, core processes and development strategy must be considered when the network information system will be developed in the next development step. The core processes in the case network are demand/capacity management, customer/supplier relationship management, service delivery management, knowledge management and cash flow management. Most benefits from ebusiness solutions come from the electrifying of operational level processes, such as service delivery management and cash flow management.

Robots and robotic systems for the electronics and telecommunication industry

Tämä diplomityö tutkii elektroniikka- ja telekommunikaatioteollisuutta sekä siihen läheisesti liittyviä robotteja ja robottijärjestelmiä. Tavoitteena on määrittää E&T-teollisuuden prosesseihin soveltuvien robottien testausmenetelmä. Tavoitteena on myös selvittää kahden ABB:n robotin soveltuvuutta E&T-teollisuuden tarpeisiin. Muutamia systemaattisia valmistusjärjestelmien suunnitteluun soveltuvia menetelmiä ja apuvälineitä on myös käsitelty. Alussa työ keskittyy elektroniikka- ja telekommunikaatioteollisuuden nykytilan tutkimiseen sekä siellä vallitsevien ja ennustettujen trendien kartoitukseen. Kohdat “Collaborative manufacturing” ja E&T-teollisuuden valmistusjärjestelmille asettamat vaatimukset käydään yksityiskohtaisesti läpi. Tutkimuksen pääkohteina ovat robotit, erityisesti ABB:n IRB 140 ja IRB 340 sekä robottien testausmenetelmän määrittäminen. Työssä käydään läpi IRB 340:llä suoritetut testit, jotka tehtiin sekä konenäköjärjestelmää apuna käyttäen että ilman. Myös TTKK:lla suoritetut robottitestit on käyty läpi. Robottien testituloksia on analysoitu ja vertailtu muihin robotteihin. Testausmenetelmät perustuvat ISO 9283 standardiin. Viimeinen osa työstä esittelee robottijärjestelmien systemaattiseen suunnitteluun soveltuvia menetelmiä ja apuvälineitä. Esillä ovat mm. Modular function deployment (MFD) ja The system design method (SDM).

Delivery Chain Management in the Elevator Industry

Tämän työn tarkoituksena oli kehittää toimintamalli, joka yhdenmukaistaisi Kone Elevators:in modernisointiliikealueen logistiset käytännöt. Toimintamalli luotiin kartoittamalla euroopan maayksiköiden nykyisiä logistisia käytäntöjä sekä perehtymällä asiaankuuluvaan kirjallisuuteen, case study:ihin sekä sähköisiin artikkeleihin. Tärkeää osaa työssä esittivät maayksiköiden sekä Koneen toimittajayksiköiden edustajien haastattelut. Haastatteluiden tuloksia vertailtiin ja analysoitiin. Niiden pohjalta huomattiin, että logistiset toimintatavat vaihtelevat maittain. Ongelmat ovat kuitenkin hyvin samanlaisia; tiedonkulun katkot toimitusprosessin aikana. Muiden Koneen liikealueiden toimintatapoja tutkimalla, haastattelujen tuloksia käyttämällä sekä kirjallisuustutkimuksen pohjalta muodostettiin näkemys parhaasta toimintatapamallista. Modernisointiliikealueen toimitusprosessi tullee perustumaan keskitettyyn ohjaukseen, mutta paikalliseen koordinointiin. Se tullee hyväksikäyttämään ulkoistetun logistiikan tarjoamia mahdollisuuksia sekä sähköistä tiedonsiirtoa. Fyysiselle siirrolle tarjotaan kolmea vaihtoehtoa, joista maayksiköt voivat valita tilanteeseen parhaiten sopivan.

Segmentation model for small and medium size business sector: Case Oy Compaq Computer Ab

Markkinasegmentointi nousi esiin ensi kerran jo 50-luvulla ja se on ollut siitä lähtien yksi markkinoinnin peruskäsitteistä. Suuri osa segmentointia käsittelevästä tutkimuksesta on kuitenkin keskittynyt kuluttajamarkkinoiden segmentointiin yritys- ja teollisuusmarkkinoiden segmentoinnin jäädessä vähemmälle huomiolle. Tämän tutkimuksen tavoitteena on luoda segmentointimalli teollismarkkinoille tietotekniikan tuotteiden ja palveluiden tarjoajan näkökulmasta. Tarkoituksena on selvittää mahdollistavatko case-yrityksen nykyiset asiakastietokannat tehokkaan segmentoinnin, selvittää sopivat segmentointikriteerit sekä arvioida tulisiko tietokantoja kehittää ja kuinka niitä tulisi kehittää tehokkaamman segmentoinnin mahdollistamiseksi. Tarkoitus on luoda yksi malli eri liiketoimintayksiköille yhteisesti. Näin ollen eri yksiköiden tavoitteet tulee ottaa huomioon eturistiriitojen välttämiseksi. Tutkimusmetodologia on tapaustutkimus. Lähteinä tutkimuksessa käytettiin sekundäärisiä lähteitä sekä primäärejä lähteitä kuten case-yrityksen omia tietokantoja sekä haastatteluita. Tutkimuksen lähtökohtana oli tutkimusongelma: Voiko tietokantoihin perustuvaa segmentointia käyttää kannattavaan asiakassuhdejohtamiseen PK-yritys sektorilla? Tavoitteena on luoda segmentointimalli, joka hyödyntää tietokannoissa olevia tietoja tinkimättä kuitenkaan tehokkaan ja kannattavan segmentoinnin ehdoista. Teoriaosa tutkii segmentointia yleensä painottuen kuitenkin teolliseen markkinasegmentointiin. Tarkoituksena on luoda selkeä kuva erilaisista lähestymistavoista aiheeseen ja syventää näkemystä tärkeimpien teorioiden osalta. Tietokantojen analysointi osoitti selviä puutteita asiakastiedoissa. Peruskontaktitiedot löytyvät mutta segmentointia varten tietoa on erittäin rajoitetusti. Tietojen saantia jälleenmyyjiltä ja tukkureilta tulisi parantaa loppuasiakastietojen saannin takia. Segmentointi nykyisten tietojen varassa perustuu lähinnä sekundäärisiin tietoihin kuten toimialaan ja yrityskokoon. Näitäkään tietoja ei ole saatavilla kaikkien tietokannassa olevien yritysten kohdalta.

Offset-print mottling measurement using machine vision

Mottling is one of the key defects in offset-printing. Mottling can be defined as unwanted unevenness of print. In this work, diameter of a mottle spot is defined between 0.5-10.0 mm. There are several types of mottling, but the reason behind the problem is still not fully understood. Several commercial machine vision products for the evaluation of print unevenness have been presented. Two of these methods used in these products have been implemented in this thesis. The one is the cluster method and the other is the band-pass method. The properties of human vision system have been taken into account in the implementation of these two methods. An index produced by the cluster method is a weighted sum of the number of found spots, and an index produced by band-pass method is a weighted sum of coefficients of variations of gray-levels for each spatial band. Both methods produce larger indices for visually poor samples, so they can discern good samples from the poor ones. The difference between the indices for good and poor samples is slightly larger produced by the cluster method. 11 However, without the samples evaluated by human experts, the goodness of these results is still questionable. This comparison will be left to the next phase of the project.