Search

Cílem článku bylo posoudit přesnost fotogrammetrických výsledků pomocí snímků nízkonákladové kamery, mobilního telefonu Xiaomi Mi 10T Pro a profesionální digitální zrcadlové kamery Canon EOS 6D Mark II. Pro analýzu byla vybrána kaple. Na kapli vytvořeno celkem 51 vlícovacích a kontrolních dbodů a byla naskenována i pozemním laserovým skenerem. Blokové vyrovnání paprskových svazků a tvorba mesh modelů proběhla v programu Bentley ContextCapture. Statisticky byly testovány směrodatné 2D polohové odchylky a směrodatné výškové odchylky na kontrolních bodech a odchylky vůči referenčnímu mračnu bodů z terestrického laserového skenování. Z výsledků vyplývá, že při vhodně zvolené konfiguraci snímkování lze dosáhnout kvalitních fotogrammetrických výsledků i s využitím nízkonákladových kamer. The aim of the article was to assess the accuracy of photogrammetric results using images of a low-cost camera, a Xiaomi Mi 10T Pro mobile phone, and a Canon EOS 6D Mark II professional digital reflex camera. A total of 51 control and checkpoints were created at the chapel, and it was scanned by a terrestrial laser scanner. Bundle block adjustment and mesh model generation were performed using Bentley ContextCapture. 2D standard deviations and standard deviations of elevation at checkpoints and deviations from the reference terrestrial laser scanning point cloud were statistically tested. The results show that with a suitably selected imaging configuration, high-quality photogrammetric results can be achieved even with a low-cost camera

Falls represent one of the most serious clinical problems in the elderly population. This risk is even more important in people suffering from neurodegenerative problems. This work aims to instrumentally assess the balance performance of elderly people and specifically those suffering from neurodegenerative diseases, to obtain an objective evaluation of their risk of falls. This paper presents a vision-based system made of three low-cost cameras, able to automatically infer important mobility parameters by observing the execution of well-established tests for stability assessment. This result is achieved by a dedicated image processing pipeline, which processes videos to get dynamic user skeletons, and the following strategy for information management, which targets to feature extraction. This information finally feeds a classifier, namely a decision tree, trained to predict the risk of fall of patients within 5 classes of interest. Actual experiments performed on actual video recordings prove a good agreement of results with those expected, labeled by expert therapists, with final prediction accuracy of 79.1%.

In recent years, the scientific community has found increasing interest in technological systems for the evaluation of the mobility performance of the elderly population. The reduced quantity of dataset for gait and balance analysis of elderly people is a serious issue in studying the link between cognitive impairment and motor dysfunction, particularly in people suffering from neurodegenerative diseases. In this context, this work aims to provide a dataset with skeletal information of people aged 60 years and older, while they perform well-established tests for stability assessment. 27 healthy people and 20 patients affected by neurodegenerative diseases, housed at two different nursing institutes, have been selected for the stability analysis. Subjects have been observed and evaluated by clinical therapists while executing three motion tests, namely balance, sit-to-stand and walking. The stability postural and gait control of each subject has been analyzed using a video-based system, made of three low-cost cameras, without the need for wearable and invasive sensors. The dataset provided in this work contains the skeletal information and highly-discriminant features of the balance, sit-to-stand and walking tests performed by each subject. To evaluate the efficiency of the balance dataset, the estimated risk of fall of the subjects has been processed considering the extracted features, and compared with the expected one. Final results have proven a good estimation of the risk of fall of the people under analysis, underlining the effectiveness of the dataset.

This paper presents the latest outcomes proposed by the authors within the context of an industrial research project aimed to the analysis of behaviors of individuals suffering from neurodegenerative diseases. It presents the experimental setup used to monitor subjects during standard exercises. A set of low-cost cameras for video surveillance, together with dedicated processing for exact people skeletonization, are used to collect information about subjects’ motor skills. These steps are the main basis for the next investigations which will be aimed to semantic analysis for the estimation of disease progress.

This paper presents the latest outcomes proposed by the authors within the context of an industrial research project aimed to the analysis of behaviors of individuals suffering from neurodegenerative diseases. It presents the experimental setup used to monitor subjects during standard exercises. A set of low-cost cameras for video surveillance, together with dedicated processing for exact people skeletonization, are used to collect information about subjects' motor skills. These steps are the main basis for the next investigations which will be aimed to semantic analysis for the estimation of disease progress.

Nowadays, there are several strong motivation to replace some dangerous human activities with the use of small unmanned system, both terrestrial and aerial. An interesting example is the use of ground unmanned rover in emergency, to realize an early mapping or to distribute the help. In this context, the Authors have investigated and developed an innovative method for terrestrial rover navigation considering low-cost sensors. The algorithms, implemented in Matlab, start to the acquisition up to the processing phase. The results have shown an impressive performance in terms of positioning accuracies: the maximum difference between the developed solution with respect to the reference coordinates is 60 cm, with a mean value of 38 cm. These results will have a great impact especially for autonomous navigation solutions.