1,721,035 research outputs found
Velocity moments for holistic shape description of temporal features
No full textThe increasing interest in processing sequences of images (rather than single ones) motivates development of techniques for sequence-based object analysis and description. Accordingly, new velocity moments have been developed to describe an object, not only by its shape but also by its motion through an image sequence. These moments are an extended form of centralised moments and compute statistical descriptions of the object and its behaviour. Two variations of this new technique are presented. The first uses the non-orthogonal Cartesian basis, while the second utilises the orthogonal Zernike one. Despite their difference in basis, both techniques exhibit favourable characteristics. Evaluation illustrates the advantages of using a complete image sequence (over single images), exploiting temporal correlation to improve a shape's statistical description, while also improving the performance of these statistical features under less favourable application scenarios, including occlusion and noise. To further characterise the velocity moments, they have been applied to gait recognition - a potential new biometric. Good recognition results have been achieved using relatively few features and basic feature selection and classification techniques. However, the prime aim of this new technique is to allow the generation of statistical features which encode shape and motion information, with generic application capability. Theoretical and applied analyses show the potential of this new sequence-based statistical technique and highlight the consistency of its performance attributes with those of conventional moments.</p
Zernike velocity moments for sequence-based description of moving features
No full textThe increasing interest in processing sequences of images motivates development of techniques for sequence-based object analysis and description. Accordingly, new velocity moments have been developed to allow a statistical description of both shape and associated motion through an image sequence. Through a generic framework motion information is determined using the established centralised moments, enabling statistical moments to be applied to motion based time series analysis. The translation invariant Cartesian velocity moments suffer from highly correlated descriptions due to their non-orthogonality. The new Zernike velocity moments overcome this by using orthogonal spatial descriptions through the proven orthogonal Zernike basis. Further, they are translation and scale invariant. To illustrate their benefits and application the Zernike velocity moments have been applied to gait recognition—an emergent biometric. Good recognition results have been achieved on multiple datasets using relatively few spatial and/or motion features and basic feature selection and classification techniques. The prime aim of this new technique is to allow the generation of statistical features which encode shape and motion information, with generic application capability. Applied performance analyses illustrate the properties of the Zernike velocity moments which exploit temporal correlation to improve a shape's description. It is demonstrated how the temporal correlation improves the performance of the descriptor under more generalised application scenarios, including reduced resolution imagery and occlusion
New Advances in Automatic Gait Recognition
No full textRecognising people by their gait is an emergent biometric. Until recently there was evaluation by few techniques on relatively small databases though with encouraging results. The potential of gait as a biometric has further been encouraged by the considerable amount of evidence available, especially in medicine and literature. This evident potential motivated development of new databases, new technique and more rigorous evaluation procedures. We describe the new techniques we have developed and their evaluation on our database to gain insight into the potential for gait as a biometric. We also describe some of our new approaches aimed to aid generalization capability for deployment of gait recognition. We show on these new and much larger databases, how our novel techniques continue to provide encouraging results for gait as a biometric, let alone as a human identifier, with especial regard for recognition at a distance
The Eco-hydrology of Lake Naivasha: A focus on sediment deposition and aggregation to investigate changes in water volume and methods of continual long term monitoring.
Get PDFLake Naivasha is an important economic asset for Kenya; it currently supports a growing population, a thriving tourism industry, geothermal energy production and over 60 flower farms which predominantly export to Europe. Recent declines in lake level and water quality have led to a marked increase in scientific studies with a common goal to improve management and conservation. The lake is vulnerable to long, hot periods with low rainfall, which increases evaporation rates resulting in concentrations of pollutants in the water rising. The effect of variations in water quality and availability are both felt locally and internationally. While the flower farms and other abstractive industries are easy to blame for the lakes decline in water level, sediment deposition is, and has been, occurring since the formation of Lake Naivasha. Changes in sediment load and streamflow are indicative of the health of the upper catchment. Upstream land usage has changed from natural forests and open land to farming and anthropogenic uses and due to erosion, riverine loads have increased in recent decades. By using remote sensing and coring, this study sought to identify areas of sediment deposition and quantify recent changes in deposition rates due to upstream erosion events or changes in land-management practices. A novel low-cost and easily replicable remote sensing technique was developed successfully to quantify deposition rates. Sedimentation was found to be most prominent in the northern area of Lake Naivasha at an average of 23 mm yr-1, displacing 308139 m³ of water each year. Current management plans set abstraction quotas using lake level measured in metres above sea level. While long-term fluctuations of lake-levels are consistent or perhaps even increasing, lake volume may in fact be slowly declining. This paper recommends that regular satellite and sonar remote sensing could be key to monitoring the health of the basin as well as effectively improving the management of Lake Naivasha which will ensure the long-term existence of the resource and the population and industry it supports
- …
