Trajectory-Based Morphological Operators: A Model for Efficient Image Processing

Mathematical morphology has been an area of intensive research over the last few years. Although many remarkable advances have been achieved throughout these years, there is still a great interest in accelerating morphological operations in order for them to be implemented in real-time systems. In this work, we present a new model for computing mathematical morphology operations, the so-called morphological trajectory model (MTM), in which a morphological filter will be divided into a sequence of basic operations. Then, a trajectory-based morphological operation (such as dilation, and erosion) is defined as the set of points resulting from the ordered application of the instant basic operations. The MTM approach allows working with different structuring elements, such as disks, and from the experiments, it can be extracted that our method is independent of the structuring element size and can be easily applied to industrial systems and high-resolution images.

Trends in mortality due to motor vehicle traffic accident injuries between 1987 and 2011 in a Spanish region (Comunitat Valenciana)

Objective: To analyse the time evolution of the rates of mortality due to motor vehicle traffic accidents (MVTA) injuries that occurred among the general population of Comunitat Valenciana between 1987 and 2011, as well as to identify trend changes by sex and age group. Methods: An observational study of annual mortality trends between 1987 and 2011. We studied all deaths due to MVTA injuries that occurred during this period of time among the non-institutionalised population residing in Comunitat Valenciana (a Spanish Mediterranean region that had a population of 5,117,190 inhabitants in 2011). The rates of mortality due to MVTA injuries were calculated for each sex and year studied. These rates were standardised by age for the total population and for specific age groups using the direct method (age-standardised rate – ASR). Joinpoint regression models were used in order to detect significant trend changes. Additionally, the annual percentage change (APC) of the ASRs was calculated for each trend segment, which is reflected in statistically significant joinpoints. Results: For all ages, ASRs decrease greatly in both men and women (70% decrease between 1990 and 2011). In 1990 and 2011, men have rates of 36.5 and 5.2 per 100,000 men/year, respectively. In the same years, women have rates of 8.0 and 0.9 per 100,000 women/year, respectively. This decrease reaches up to 90% in the age group 15–34 years in both men and women. ASR ratios for men and women increased over time for all ages: this ratio was 3.9 in 1987; 4.6 in 1990; and 5.8 in 2011. For both men and women, there is a first significant segment (p < 0.05) with an increasing trend between 1987 and 1989–1990. After 1990, there are 3 segments with a significant decreasing APC (1990–1993, 1993–2005 and 2005–2011, in the case of men; and 1989–1996, 1999–2007 and 2007–2011, in the case of women). Conclusion: The risk of death due to motor vehicle traffic accidents injuries has decreased significantly, especially in the case of women, for the last 25 years in Comunitat Valenciana, mainly as of 2006. This may be a consequence of the road-safety measures that have been implemented in Spain and in Comunitat Valenciana since 2004. The economic crisis that this country has undergone since 2008 may have also been a contributing factor to this decrease. Despite the decrease, ASR ratios for men and women increased over time and it is still a high-risk cause of death among young men. It is thus important that the measures that helped decrease the risk of death are maintained and improved over time.

Human Behaviour Recognition based on Trajectory Analysis using Neural Networks

Automated human behaviour analysis has been, and still remains, a challenging problem. It has been dealt from different points of views: from primitive actions to human interaction recognition. This paper is focused on trajectory analysis which allows a simple high level understanding of complex human behaviour. It is proposed a novel representation method of trajectory data, called Activity Description Vector (ADV) based on the number of occurrences of a person is in a specific point of the scenario and the local movements that perform in it. The ADV is calculated for each cell of the scenario in which it is spatially sampled obtaining a cue for different clustering methods. The ADV representation has been tested as the input of several classic classifiers and compared to other approaches using CAVIAR dataset sequences obtaining great accuracy in the recognition of the behaviour of people in a Shopping Centre.