Automating condition monitoring of vegetation on railway trackbeds and embankments

Vegetation growing on railway trackbeds and embankments present potential problems. The presence of vegetation threatens the safety of personnel inspecting the railway infrastructure. In addition vegetation growth clogs the ballast and results in inadequate track drainage which in turn could lead to the collapse of the railway embankment. Assessing vegetation within the realm of railway maintenance is mainly carried out manually by making visual inspections along the track. This is done either on-site or by watching videos recorded by maintenance vehicles mainly operated by the national railway administrative body. A need for the automated detection and characterisation of vegetation on railways (a subset of vegetation control/management) has been identified in collaboration with local railway maintenance subcontractors and Trafikverket, the Swedish Transport Administration (STA). The latter is responsible for long-term planning of the transport system for all types of traffic, as well as for the building, operation and maintenance of public roads and railways. The purpose of this research project was to investigate how vegetation can be measured and quantified by human raters and how machine vision can automate the same process. Data were acquired at railway trackbeds and embankments during field measurement experiments. All field data (such as images) in this thesis work was acquired on operational, lightly trafficked railway tracks, mostly trafficked by goods trains. Data were also generated by letting (human) raters conduct visual estimates of plant cover and/or count the number of plants, either on-site or in-house by making visual estimates of the images acquired from the field experiments. Later, the degree of reliability of(human) raters’ visual estimates were investigated and compared against machine vision algorithms. The overall results of the investigations involving human raters showed inconsistency in their estimates, and are therefore unreliable. As a result of the exploration of machine vision, computational methods and algorithms enabling automatic detection and characterisation of vegetation along railways were developed. The results achieved in the current work have shown that the use of image data for detecting vegetation is indeed possible and that such results could form the base for decisions regarding vegetation control. The performance of the machine vision algorithm which quantifies the vegetation cover was able to process 98% of the im-age data. Investigations of classifying plants from images were conducted in in order to recognise the specie. The classification rate accuracy was 95%.Objective measurements such as the ones proposed in thesis offers easy access to the measurements to all the involved parties and makes the subcontracting process easier i.e., both the subcontractors and the national railway administration are given the same reference framework concerning vegetation before signing a contract, which can then be crosschecked post maintenance.A very important issue which comes with an increasing ability to recognise species is the maintenance of biological diversity. Biological diversity along the trackbeds and embankments can be mapped, and maintained, through better and robust monitoring procedures. Continuously monitoring the state of vegetation along railways is highly recommended in order to identify a need for maintenance actions, and in addition to keep track of biodiversity. The computational methods or algorithms developed form the foundation of an automatic inspection system capable of objectively supporting manual inspections, or replacing manual inspections.

Convex Hulls in Image Processing : A Scoping Review

The demands of image processing related systems are robustness, high recognition rates, capability to handle incomplete digital information, and magnanimous flexibility in capturing shape of an object in an image. It is exactly here that, the role of convex hulls comes to play. The objective of this paper is twofold. First, we summarize the state of the art in computational convex hull development for researchers interested in using convex hull image processing to build their intuition, or generate nontrivial models. Secondly, we present several applications involving convex hulls in image processing related tasks. By this, we have striven to show researchers the rich and varied set of applications they can contribute to. This paper also makes a humble effort to enthuse prospective researchers in this area. We hope that the resulting awareness will result in new advances for specific image recognition applications.

A proposed Model for Country Branding : an experimental Application on Nigeria

In the era of globalization, countries compete with each other for attention, respect and trust of potential consumers, investors, tourists, media and governments of other nations. Branding is the most powerful tool that a nation can utilize for effective differentiation strategies and for creating competitive advantage over other nations. Unfortunately, not every nations or destination marketers have a broad understanding of the concept of branding and how a country can be successfully branded. Hence, this study has proposed a model that could be used as a valuable guide for country branding. Also the model is recommended for countries struggling with image crisis; on the mission to improve the image internationally. Nigeria is a good example of countries with image crisis; it is one of the most populated countries in the world with a population of about 160 million inhabitants and growth rate of 2.553percent annually. Despite the abundant resources (e.g. coal, petroleum, natural gas etc.) that the nation is endowed with, it is quite disappointing that the population below poverty line is still at the alarming rate of 70percent of the total population. The mismanagement and poor leadership of the nation characterised by corruption, fraud, embezzlement of public fund etc. has culminated into serious image crisis that is slowing down the potential for investment and economic growth. However, there has been series of image rebranding campaigns but no tangible achievement has been recorded. It is quite questionable though, if image rebranding will provide the kind of future that Nigeria envisaged, considering the socio-political situation and the economic imbalance; compounded by the obvious fact that the nation has no known brand. Therefore, this paper argues that there is need to redirect the effort invested on image rebranding to the creation of a unique and competitive brand for the country. It was established from the study that a nation’s brand is capable of improving the reputation of the nation as well as stimulate the expectation of the target audience. However, it was also established from the study that a wrong approach to branding could mislead the target audience and attract negative publicity. Hence, as a contribution of the study to the field of branding, a model was proposed as a functional guide for country branding. Also, considering the abysmal performance of Nigeria’s image in the international community and to strengthen the argument that brand creation is required for the country; an experimental application of the proposed model was conducted using Nigeria as the case country. The first phase of the model suggested a major improvement in the society; this is required to further enhance the strengths of the country and to motivate the much needed community participation and confidence in the brand creation. It is the conclusion of the study that a strong nation brand can offset the image problem if it is built on something concrete, genuine, and uniquely identifiable with the country, capable of connecting to the cognitive psychology of the target audience.

Kravsammanställning samt utvärdering avbildvisningsprogramför diagnostik inom telepatologi : En fallstudiemed SIV-metoden som tillvägagångssätt

De flesta har i sin närhet någon som drabbats av cancer och sjukdomsfallen har ökat genom åren. Den yrkesgrupp som ställer diagnos av denna sjukdom är patologer. Bristen på patologer är idagsläget stor och det finns därför ett behov av att finna effektiva lösningar för att möta denna brist och en ökande mängd patienter. För att digitalisera vävnadsproven som diagnostiseras, scannas dessa in med en glasscanner. Dessa digitala bildfiler kan sedan visas i ett bildvisningsprogram och delas digitalt mellan patologer på distans. Detta begrepp kallas för telepatologi. Studien utgår utifrån följande frågeställningar: Vilka krav är väsentliga och bör ingå i en utvärdering för bildvisningsprogram avsedda för diagnostik inom telepatologi? Vilket bildvisningsprogram är mest lämpat att implementeras i ett webbaserat system baserat på dessa väsentliga krav? Syftet med studien är att undersöka vilka krav som är väsentliga och bör ingå i en utvärdering av bildvisningsprogram avsedda för diagnostik inom telepatologi, samt att utföra en utvärdering av ett urval bildvisningsprogramvaror med hjälp av dessa krav. En fallstudie genomfördes med datainsamlingsmetoderna: intervjuer med två personer från studiens samarbetspartner CGM, Frågeformulär där Sveriges patologer var respondenter samt dokumentstudier för att samla in information gällande bildvisningsprogrammen. Studien tillämpar utvalda delar ur Anders G. Nilssons SIV-metod som tillvägagångsätt för att samla in krav samt för att göra ett urval av bildvisningsprogram som sedan utvärderas gentemot dessa krav. Resultaten av datainsamlingarna analyserades och ledde till ett kravdokument med väsentliga krav.Tre så kallade utslagsgivande faktorer bland dessa krav var att bildvisningsprogrammet måste vara webbaserat utan installation på klient, funktioner för in- och ut-zoomning samt panorering måste finnas. Utvärderingen av utvalda bildvisningsprogram visade slutligen att OpenSlide var mest lämpad att implementeras i ett webbaserat system.

Retusch av landskapsfoto i annonser för turistmål : En kvantitativ undersökningkring den accepterade nivån av retusch

Etik kring bilder i annonser har diskuterats mycket, speciellt modell-, ochproduktbilder har kritiserats. Det tycks dock saknas forskning om acceptanskring efterbehandling av landskapsfotografier som ofta används vidmarknadsföring av turistmål. En webbenkätundersökning genomfördes medbildexempel för att undersöka vilken nivå av efterbehandling som ansågsverklighetstrogen, tilltalande och accepterbar i sådana annonser. Slutsatsenblev att fotografier där exponeringen korrigerats för att skapa en tydligare bildvar det mest accepterade. Skillnader i åsikter mellan åldrar, kön, de som haroch inte har tidigare erfarenhet av fotografi och retuschering diskuterades ochdet visade sig att kvinnor och de utan tidigare erfarenhet var lite mer kritiskatill efterbehandling. Det framkom att en del betraktare kan accepteraytterligare efterbehandling om den genomförs för att sälja en specifik känslaoch så länge inte betraktaren kan känna sig vilseledd.