Search

Oriented object detection is an important research topic in remote sensing. The detection of oriented objects in remote sensing images remains a daunting challenge due to their complex backgrounds, various sizes, diverse aspect ratios, and especially arbitrary orientations. In recent years, keypoint-based anchor-free object detectors have demonstrated outstanding performance in this field. However, in current anchor-free detectors, object keypoints are primarily generated using the Gaussian kernel function, which assumes a circular form. This representation falls short in accurately conveying an object’s size and orientation. To address the aforementioned issue, this article proposes a keypoint-based oriented object detector called MRSDet, which innovatively adopts the Tricube kernel, scales, and rotates it, to better generate the center keypoint heatmap of the object. Besides, to improve the model’s detection performance on oriented objects and improve its ability to perceive object keypoints and boundary boxes, we also design a large receptive field mask (LRFM) module, which is based on large convolution kernel decomposition and semantic segmentation masks. Taking the box boundary-aware vectors (BBAVectors) method as a baseline, we conduct experiments on multiple types of remote sensing datasets such as HRSC2016, UCAS-AOD, and SSDD+ datasets to verify the effectiveness and generalizability of the proposed method.

Constrained by the performance of edge devices and real time (RT) processing technology, the existing hyperspectral target detection algorithms often struggle to rapidly distinguish targets from complex background pixels during real-time detection. To address this issue, this article proposes a new real-time cloud-edge selective background energy constrained (CE-SBEC) hyperspectral target detection algorithm. This algorithm aims to obtain detection results in real-time after capturing new data. Moreover, it conducts in-depth analysis based on existing detection results and updates the algorithm’s internal data to enhance its capabilities in terms of global background annihilation (GBA) and complex background suppression (CBS). Consequently, it improves the accuracy of subsequent real-time detection results. To enhance the resource utilization, this article deploys various task nodes of the algorithm separately on both the cloud and the edge, enabling collaborative execution of the CE-SBEC algorithm. In our context, edge devices are airborne equipment designed for the rapid acquisition and processing of data at the site of data collection, while cloud computing devices refer to high-performance computing clusters situated at a significant distance from the data collection site. Experimental results demonstrate that compared with existing detection algorithms, our newly proposed method achieves more accurate detection results while ensuring real-time performance.

Presently, there has been a noticeable rise in the consumption of poultry meat within the general population, particularly focusing on poultry sourced from alternative rearing systems as opposed to intensive ones. This study evaluated the impact of incorporating house cricket (Acheta domesticus,AD) larvae meal into the diet of 2 slow-growing chicken strains on their carcass traits and meat quality. A total of 256 one-day-old male chicks were utilized, with 128 belonging to the Red (R) strain and 128 to the Naked Neck (NN) strain. Chicks from each strain were randomly assigned to 16 replicates of 8 chicks each. Eight replicates were allocated to 2 distinct treatments (n=64chicks/treatment) based on the diet employed: the control treatments for the Red (R-C) and Naked Neck (NN-C) strains were fed soybean meal, while the other 2 treatments were fed AD meal (R-AD and NN-AD). Three different rations were used throughout the growth cycle of the animals, tailored to meet the nutritional needs of the birds. All chickens were slaughtered at 95 d of age, and eight chickens per treatment were randomly chosen to assess carcass traits and meat quality. Near-infrared reflectance spectroscopy (NIRS) was employed to classify meat based on the feed and the chick strain, achieving a correct discrimination of 100% of the samples. The carcass traits exhibited significant alterations due to the inclusion of insect larval meal in the diet, resulting in reduced values across all parameters for chickens consuming AD meal, irrespective of genotype. The pH and cooking losses were generally higher for chicks fed cricket meal, as occurred with moisture. However, protein content was lower in the meat of chicks consuming cricket meal. Fat content showed lower values for NN chickens. There were minimal differences in the fatty acid profile, with lower C18:3n-3 values for chickens fed cricket meal. Therefore, including Acheta domesticusmeal in the diets of slow-growing chick strains is a viable alternative to replace soybean meal. It provides meat quality characteristics comparable to those obtained in conventional systems.

This paper proposes a novel end-to-end learning model, called skip-connected covariance (SCCov) network, for remote sensing scene classification (RSSC). The innovative contribution of this paper is to embed two novel modules into the traditional convolutional neural network (CNN) model, i.e., skip connections and covariance pooling. The advantages of newly developed SCCov are twofold. First, by means of the skip connections, the multi-resolution feature maps produced by the CNN are combined together, which provides important benefits to address the presence of large-scale variance in RSSC data sets. Second, by using covariance pooling, we can fully exploit the second-order information contained in such multi-resolution feature maps. This allows the CNN to achieve more representative feature learning when dealing with RSSC problems. Experimental results, conducted using three large-scale benchmark data sets, demonstrate that our newly proposed SCCov network exhibits very competitive or superior classification performance when compared with the current state-of-the-art RSSC techniques, using a much lower amount of parameters. Specifically, our SCCov only needs 10% of the parameters used by its counterparts. [ABSTRACT FROM AUTHOR]

Context Forage cultivation plays a pivotal role in sustaining ruminants in resource-limited ecosystems such as the hot-summer Mediterranean agroforestry systems of the Iberian Peninsula comprising oak trees (Quercus spp.) and grassland species. Intercropping techniques can enhance forage yields and nutritional quality. Aims This study assessed the yield and nutritional quality of organic forage mixtures in an Iberian oak grassland ecosystem. Methods Six forage associations were assessed over two growing seasons: vetch (Vicia sativa L.)–triticale (Triticum ×Secale ), vetch–rye (Secale cereale ), vetch–oat (Avena sativa ), pea (Pisum sativum L.)–triticale, pea–rye, and pea–oat. The data were analysed using a multivariate procedure. Key results Differences in forage composition influenced nutritional quality but not yield. Vetch-based associations exhibited higher crude protein, calcium, phosphorus, potassium, zinc, magnesium, manganese and sulfur contents, along with lower proportions of neutral-detergent fibre and ether extract. The vetch–oat mixture emerged as the highest quality association. Interannual variations in precipitation and temperature caused differences in forage yield, with greater values observed in 2020 than in 2019. Forage associations also had significantly higher nutritional quality in 2020 (increased protein and mineral content, and decreased neutral detergent fibre and lignin). Conclusions All forages demonstrated satisfactory performance and quality, even in the drier conditions of 2019, suggesting high resilience and adaptability to hot-summer Mediterranean oak grassland ecosystems. Implications The findings of this study are relevant for organic farmers in resource-limited ecosystems. This information empowers them to select the most suitable forage species based on the specific agroclimatic conditions of each growing season.

Sustainable poultry meat production involves the use of slow-growing chick strains and the utilization of new protein sources as an alternative to the current monopoly of soybean meal. In this scenario, a study was conducted to assess the effect of replacing soybean meal with domestic cricket (Acheta domesticus) meal on the developing cycle of slow-growing chicks. To this end, a total of 128 one-day-old male chicks (Colorield) were randomly assigned into 16 experimental units, each consisting of eight chicks, which in turn were grouped into two groups fed isoproteic and isoenergetic diets in which the protein source differed: the control group (C) fed soybean meal and the Acheta group (AD) fed Acheta domesticusinsect meal as the main protein source. Chicks were slaughtered at 95 days of age. Three different diets (F1, F2 and F3) were used for each experimental group according to the nutritional needs of the birds during their growth. The F1 diet (1-29 d) resulted in higher feed and water intake and higher body weight gain for group C, but a lower feed conversion rate. On the contrary, during F2 (29-60 d) no differences in productive performances were observed between the two groups, except for a higher water intake for group C. Finally, during the period corresponding to diet F3 (60-95 d) there were only differences in feed intake, which was higher for the AD group. In conclusion, the substitution of soybean meal for Acheta domesticusmeal caused a decrease in feed intake during the first month and consequently a lower body weight. During the first four weeks of life of the chicks, a partial replacement of soybean meal may be recommended, since high inclusions of A. domesticusmeal in this period seem to be detrimental in young chicks. Given the absence of relevant differences in productive performances between both groups, it could be concluded that the use of A. domesticuscricket meal can be a potential protein alternative to soybean meal.

A 12-year-old boy presented to our emergency department complaining of pain and functional limitation on his right ankle after an indirect trauma. Plain radiographs were taken identifying a type II epiphysiolysis of the distal tibia and a proximal fibula fracture. An open reduction and internal fixation was performed without transyndesmal fixation. Maisonneuve fractures are an uncommon injury in the pediatric population. This fracture pattern has not been described by the Dias–Tachdjian classification. It is important to bear in mind that, based on the need for osteosynthesis for the epiphysiolysis, the treatment of these fractures in children usually differs from that in the adults as no transyndesmal screw fixation is required.

Hyperspectral unmixing is a very important task for remotely sensed hyperspectral data exploitation. It addresses the (possibly) mixed nature of pixels collected by instruments for Earth observation, which are due to several phenomena including limited spatial resolution, presence of mixing effects at different scales, etc. Spectral unmixing involves the separation of a mixed pixel spectrum into its pure component spectra (called endmembers) and the estimation of the proportion (abundance) of endmember in the pixel. Two models have been widely used in the literature in order to address the mixture problem in hyperspectral data. The linear model assumes that the endmember substances are sitting side-by-side within the field of view of the imaging instrument. On the other hand, the nonlinear mixture model assumes nonlinear interactions between endmember substances. Both techniques can be computationally expensive, in particular, for high-dimensional hyperspectral data sets. In this paper, we develop and compare parallel implementations of linear and nonlinear unmixing techniques for remotely sensed hyperspectral data. For the linear model, we adopt a parallel unsupervised processing chain made up of two steps: i) identification of pure spectral materials or endmembers, and ii) estimation of the abundance of each endmember in each pixel of the scene. For the nonlinear model, we adopt a supervised procedure based on the training of a parallel multi-layer perceptron neural network using intelligently selected training samples also derived in parallel fashion. The compared techniques are experimentally validated using hyperspectral data collected at different altitudes over a so-called Dehesa (semi-arid environment) in Extremadura, Spain, and evaluated in terms of computational performance using high performance computing systems such as commodity Beowulf clusters.