UAV Landing Platform Recognition Using Cognitive Computation Combining Geometric Analysis and Computer Vision Techniques

Unmanned aerial vehicles (UAVs) are excellent tools with extensive demand. During the last phase of landing, they require additional support to that of GPS. This can be achieved through the UAV’s perception system based on its on-board camera and intelligence, and with which decisions can be made as to how to land on a platform (target). A cognitive computation approach is proposed to recognize this target that has been specifically designed to translate human reasoning into computational procedures by computing two probabilities of detection which are combined considering the fuzzy set theory for proper decision-making. The platform design is based on: (1) spectral information in the visible range which are uncommon colors in the UAV’s operating environments (indoors and outdoors) and (2) specific figures in the foreground, which allow partial perception of each figure. We exploit color image properties from specific-colored figures embedded on the platform and which are identified by applying image processing and pattern recognition techniques, including Euclidean Distance Smart Geometric Analysis, to identify the platform in a very efficient and reliable manner. The test strategy uses 800 images captured with a smartphone onboard a quad-rotor UAV. The results verify the proposed method outperforms existing strategies, especially those that do not use color information. Platform recognition is also possible even with only a partial view of the target, due to image capture under adverse conditions. This demonstrates the effectiveness and robustness of the proposed cognitive computing-based perception system.

Hypoderma actaeon: an emerging myiasis in roe deer (Capreolus capreolus)

Subcutaneous larvae of Hypoderma spp. (Diptera: Oestridae) were detected in the dorsal region in 10 roe deer, Capreolus capreolus (Artiodactyla: Cervidae), hunted in central Spain between January and March 2016. All larvae were found in the inner side of the hide during the skinning of the animals. The study of the morphological features of eight larvae of different stages collected from two animals allowed the identification of Hypoderma actaeon Brauer. The small size (4-5 mm) of some of the first instars suggests that the internal lifecycle of H. actaeon may be exclusively subcutaneous. This is the first confirmation of H. actaeon in roe deer; however, further studies to assess the spread of the parasite and to follow the evolution of this myiasis in roe deer are needed.

Antigen characterization from second instars of oestrid bot flies for the detection of anti-Cephenemyia stimulator antibodies by ELISA in roe deer (Capreolus capreolus)

A study to determine the most appropriate antigen for use in the serodiagnosis of Cephenemyia (Diptera: Oestridae) infestation in roe deer (Capreolus capreolus) was carried out using immunoenzymatic tests. Serum samples from 43 roe deer from northern Spain were obtained post-mortem and corresponding numbers of bot fly larvae established. Three antigen complexes were tested, including Cephenemyia stimulator Clark excretory/secretory antigens (CsES), C. stimulator somatic antigens (CsSA) and Oestrus ovis L. (Diptera: Oestridae) excretory/secretory antigens (OoES). In addition, the composition of each antigen was analysed using an electrophoresis system. Cephenemyia stimulator larvae were found in 25% of roe deer; the mean intensity of infection was 24.3 larvae per infested animal. In the antigen analysis, CsSA showed four exclusive bands of molecular weight (17-19, 62, 65 and 67-70 kDa). A positive correlation between immunoglobulin G (IgG) values and total number of larvae was found with CsES and CsSA. The highest sensitivity value, negative predictive value and negative likelihood ratio were obtained using CsES. The highest specificity value, positive likelihood ratio and kappa value were achieved with CsSA. The predictive values of the enzyme-linked immunosorbent assay (ELISA) using CsES and CsSA reached statistical significance and seroprevalence values were 26-44%. The use of ELISA with CsES and CsSA seems promising in the non-invasive diagnosis of Cephenemyia infestation in roe deer.

Crop row detection in maize fields inspired on the human visual perception

This paper proposes a new method, oriented to image real-time processing, for identifying crop rows in maize fields in the images. The vision system is designed to be installed onboard a mobile agricultural vehicle, that is, submitted to gyros, vibrations, and undesired movements. The images are captured under image perspective, being affected by the above undesired effects. The image processing consists of two main processes: image segmentation and crop row detection. The first one applies a threshold to separate green plants or pixels (crops and weeds) from the rest (soil, stones, and others). It is based on a fuzzy clustering process, which allows obtaining the threshold to be applied during the normal operation process. The crop row detection applies a method based on image perspective projection that searches for maximum accumulation of segmented green pixels along straight alignments. They determine the expected crop lines in the images. The method is robust enough to work under the above-mentioned undesired effects. It is favorably compared against the well-tested Hough transformation for line detection.

A sexing protocol for wild ruminants based on PCR amplification of amelogenin genes AMELX and AMELY (short communication)

Abstract. Based on the sequences of the bovine amelogenin genes, we have designed a protocol for sexing DNA samples of wild ruminants. Basically the protocol consists on the co-amplification of two specific fragments, one from Y-chromosome and one for the X chromosome, making the use of a PCR control unnecessary. It has been demonstrated to be useful for sex identification in a total of 164 samples belonging to six different wild ruminant species. We propose adding to the census procedure commonly based in faecal groups counting, the faecal sampling and application of the protocol design here, to estimate the sex ratio.

Machine Learning as an aid to management decisions on high somatic cell counts in dairy farms

Abstract. High somatic cell counts (SCC) is associated with mastitis infection, in dairy herds, worldwide. This work describes Machine Learning (ML) techniques designed to improve the information offered to farmers on animals producing high SCCs according to particular herd profiles. The analysed population included 71 dairy farms in Asturias (Northern Spain) and a total of 2,407 lactating cows. Four sources of information were available: a) a questionnaire survey describing facilities, milking routines and management practices of the farms studied; b) dairy recording information; c) classification of the cows suspected of being healthy or subclinical mastitic according to farmers’ expertise; and d) positive or negative scores with respect to the California Mastitis Test (CMT). The decimal logarithm of the SCC (linear score), lactation number, herd size, lactating cows per milker, milk urea concentration, number of clusters per milker and actual SCC are shown to be the most informative attributes for mimicking both farmers’ expertise or CMT performance in order to identify animals producing persistently high SCCs in dairy herds. However, to improve the identification of cows suspected of being non-healthy, the system uses other information related to management and milking routines. Decision rules to predict CMT performance can provide useful, additional information to farmers to improve the management of dairy herds included in milk recording programs.

190 A PROCEDURE TO OBTAIN FIBROBLASTS FROM WILD ANIMALS

The number of wild animals threatened or at risk of extinction constantly increases and, as a result, biodiversity decreases. Therefore, it is necessary to set in motion proceedings to preserve the genetic variability and to overcome factors leading to this situation. Banks of cryopreserved cells, such as skin fibroblasts, from wild animals could be used both for genetic studies and as a cell source for technologies able to reproduce individuals. In this study we report that a single basic protocol provides a method for obtaining, culturing, and cryopreserving skin fibroblasts from a wide range of wild animals. Skin biopsies were taken in Cantabria (Spain) from live, anesthetized brown bear (Ursus arctos, n = 4), and in Asturias (Spain) from carcasses of accidentally killed individuals from the following species: grey wolf (Canis lupus, n = 1), red fox (Vulpes vulpes, n = 1), eurasian badger (Meles meles, n = 1), ermine (Mustela erminea, n = 1), fallow deer (Dama dama, n = 7), pyrenean chamois (Rupicapra pyrenaica, n = 1), western roe deer (Capreolus capreolus, n = 1), wild boar (Sus scrofa, n = 1), striped dolphin (Stenella coeruleoalba, n = 1) and one avian species, capercaillie (Tetrao urogallus, n = 1). Once obtained and transported to the laboratory, all samples were processed identically. Tissue samples were manually cut into small pieces and enzymatically digested with 0.05% trypsin-EDTA (Sigma-Aldrich, Madrid, Spain) for 30 min, and then with collagenase (300 units/mL) (Sigma) for 14 h at 38°C. Disaggregated cells were centrifuged at 1600 rpm for 10 min and the pellet was diluted with D-MEM (Sigma) containing 10% FBS. Cells were counted and a minimum of 3 × 105 cells were placed in a 25 cm2 flask for culture under 5% CO2 in air and high humidity at 37°C (red fox, badger, ermine, western roe deer) or 38°C (brown bear, grey wolf, fallow deer, pyrenean chamois, wild boar, striped dolphin, capercaillie). Confluent fibroblast monolayers were obtained after 5–7 days in culture except for the striped dolphin whose sample was contaminated. Two to three passages were performed using 75 cm2 flasks before freezing fibroblasts in D-MEM containing 10% DMSO (Sigma) and 10% FBS. Total cell yield from a confluent flask was 5–11 × 106 cells, depending on the animal species. Fibroblasts recovered from all thawed samples grew to confluence, and karyotypes were performed at this step. It was possible to obtain, culture, freeze, and thaw skin fibroblasts successfully from all the above-mentioned land species. Although more research is needed, preliminary data suggest that the above-described procedure can be applied to mammals and birds, thus helping to preserve genetic material of wild animals. Grant Support: Consejería de Medio Ambiente, Ordenación del Territorios e Infraestructuras, Asturias, SPAIN. The authors acknowledge CEPESMA, Luarca, Asturias, SPAIN.

The non-parametric Parzen's window in stereo vision matching

This paper presents an approach to the local stereovision matching problem using edge segments as features with four attributes. From these attributes we compute a matching probability between pairs of features of the stereo images. A correspondence is said true when such a probability is maximum. We introduce a nonparametric strategy based on Parzen's window (1962) to estimate a probability density function (PDF) which is used to obtain the matching probability. This is the main finding of the paper. A comparative analysis of other recent matching methods is included to show that this finding can be justified theoretically. A generalization of the proposed method is made in order to give guidelines about its use with the similarity constraint and also in different environments where other features and attributes are more suitable.