Search

In recent times, video inpainting techniques have intended to fill the missing areas or gaps in a video by utilizing known pixels. The variety in brightness or difference of the patches causes the state-of-the-art video inpainting techniques to exhibit high computation complexity and create seams in the target areas. To resolve these issues, this paper introduces a novel video inpainting technique that employs the Morphological Haar Wavelet Transform combined with the Krill Herd based Criminisi algorithm (MHWT-KHCA) to address the challenges of high computational demand and visible seam artifacts in current inpainting practices. The proposed MHWT-KHCA algorithm strategically reduces computation times and enhances the seamlessness of the inpainting process in videos. Through a series of experiments, the technique is validated against standard metrics such as peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM), where it demonstrates superior performance compared to existing methods. Additionally, the paper outlines potential real-world applications ranging from video restoration to real-time surveillance enhancement, highlighting the technique's versatility and effectiveness. Future research directions include optimizing the algorithm for diverse video formats and integrating machine learning models to advance its capabilities further. [ABSTRACT FROM AUTHOR]

The most common life-threatening disease, acute lymphoblastic leukemia (ALL), can be lethal within a few weeks if untreated. The early detection and analysis of leukemia is a key dilemma in the field of disease diagnosis, and the methods available for the classification process are time-consuming. To overcome the issues, this paper develops a robust classification technique named Horse Herd Whale Optimization-enabled Deep Neuro-Fuzzy Network (HHWO-enabled DNFN method) for ALL classification and severity analysis using the MapReduce framework. The input image is first preprocessed and segmented, and the useful features necessary for improving the classification performance are extracted during the mapper phase, known as HHWO, which incorporates Horse Herd Optimization Algorithm (HOA) and Whale Optimization Algorithm (WOA). Finally, severity analysis of ALL is done to classify the levels of leukemia to offer optimal treatment. As a result, the developed method performed better than other existing methods, achieving superior performance with a greater testing accuracy of 0.959, sensitivity of 0.965, and specificity of 0.966, respectively. [ABSTRACT FROM AUTHOR]

Simple Summary: Spontaneous humeral fractures in first- and second-lactation dairy cows are recognized as a serious welfare problem in New Zealand. However, the condition is sporadic, which means that simple epidemiological descriptions and estimates of the extent of the problem are lacking. By combining the data from four independent studies using a multi-method approach, we found that their occurrence is more common than previously thought, with potentially up to 12% of farms and 4,620 dairy cattle affected in the 2013/2014 lactation season. Furthermore, the condition exclusively affects first- and second-lactation spring calving dairy cows, up to 4 months post-partum, and may affect multiple animals on the same farm, in the same season, and over multiple seasons, which are not always consecutive. We suggest that the evidence presented in this paper places an urgent requirement on the New Zealand dairy industry to undertake prompt action to understand the determinants of this epidemic. A multi-method approach integrating data from four independent sources was used to describe some key features of the epidemiology and estimate the herd and within-herd incidence of fractured humeri in New Zealand dairy cattle for the period 2007–2015. The first dataset was from a national case series where cases of humeral fractures in dairy cattle were identified by veterinarians across New Zealand between the 2007/2008 and 2011/2012 lactation seasons. The second dataset was from a pet food company based in the Waikato region, which collated the number of casualty first- and second-lactation cows found to have a fractured humerus post-slaughter in the 2014/2015 lactation season, and the third dataset was a case series conducted by veterinarians employed in a Waikato veterinary business, also from the 2014/2015 lactation season. For the final dataset, 505 randomly selected New Zealand dairy farmers completed a phone survey on the incidence of non-responsive, non-weight-bearing forelimb lameness in first- and second-lactation cows in the 2014/2015 lactation season. Using the telephone survey results, the within-herd and herd-level incidence of cases for first- and second-lactation dairy animals was calculated. The national case series reported 149 cases of humeral fractures in 22 dairy herds; the pet food case series identified 61 cases from 41 farms; and the practice-based case series found 14 cases from 10 farms. Humeral fractures exclusively affected first- and second-lactation dairy cows and had a peak incidence between calving and early mating. The national telephone survey found that non-weight-bearing forelimb lameness requiring euthanasia of first- or second-lactation cows occurred in 11.7% of herds, with a mean within-herd incidence of 2.6% for first lactation cows and 2.8% for second-lactation cows for affected herds. These combined datasets demonstrate that humeral fractures in young, lactating dairy cattle are more common than previously suspected and that they occur nationally and over multiple years on some farms. Further work on this condition is urgently required in New Zealand to establish cost-effective management practices that will reduce unnecessary animal suffering and waste. [ABSTRACT FROM AUTHOR]

Simple Summary: Dairy cow behavior detection is of great significance for cattle health management. Through the detection of the four behaviors of dairy cows—standing, lying, eating, and drinking—we can gain valuable insights into the well-being of cows. For example, hoof disease can increase the amount of time a cow lies down, and digestive system issues can cause a decrease in food intake. Visual inspection of cow behavior can keep track of changes in cow behavior, and non-invasive detection can reduce cow discomfort and improve animal welfare. In this study, we employed computer vision-based deep learning techniques for the detection of cow behavior, and experimental results demonstrated its promising application in real farm settings. Dairy cow behavior carries important health information. Timely and accurate detection of behaviors such as drinking, feeding, lying, and standing is meaningful for monitoring individual cows and herd management. In this study, a model called Res-DenseYOLO is proposed for accurately detecting the individual behavior of dairy cows living in cowsheds. Specifically, a dense module was integrated into the backbone network of YOLOv5 to strengthen feature extraction for actual cowshed environments. A CoordAtt attention mechanism and SioU loss function were added to enhance feature learning and training convergence. Multi-scale detection heads were designed to improve small target detection. The model was trained and tested on 5516 images collected from monitoring videos of a dairy cowshed. The experimental results showed that the performance of Res-DenseYOLO proposed in this paper is better than that of Fast-RCNN, SSD, YOLOv4, YOLOv7, and other detection models in terms of precision, recall, and mAP metrics. Specifically, Res-DenseYOLO achieved 94.7% precision, 91.2% recall, and 96.3% mAP, outperforming the baseline YOLOv5 model by 0.7%, 4.2%, and 3.7%, respectively. This research developed a useful solution for real-time and accurate detection of dairy cow behaviors with video monitoring only, providing valuable behavioral data for animal welfare and production management. [ABSTRACT FROM AUTHOR]

This paper introduces an approach to the automated measurement and analysis of dairy cows using 3D point cloud technology. The integration of advanced sensing techniques enables the collection of non-intrusive, precise data, facilitating comprehensive monitoring of key parameters related to the health, well-being, and productivity of dairy cows. The proposed system employs 3D imaging sensors to capture detailed information about various parts of dairy cows, generating accurate, high-resolution point clouds. A robust automated algorithm has been developed to process these point clouds and extract relevant metrics such as dairy cow stature height, rump width, rump angle, and front teat length. Based on the measured data combined with expert assessments of dairy cows, the quality indices of dairy cows are automatically evaluated and extracted. By leveraging this technology, dairy farmers can gain real-time insights into the health status of individual cows and the overall herd. Additionally, the automated analysis facilitates efficient management practices and optimizes feeding strategies and resource allocation. The results of field trials and validation studies demonstrate the effectiveness and reliability of the automated 3D point cloud approach in dairy farm environments. The errors between manually measured values of dairy cow height, rump angle, and front teat length, and those calculated by the auto-measurement algorithm were within 0.7 cm, with no observed exceedance of errors in comparison to manual measurements. This research contributes to the burgeoning field of precision livestock farming, offering a technological solution that not only enhances productivity but also aligns with contemporary standards for sustainable and ethical animal husbandry practices. [ABSTRACT FROM AUTHOR]

Survival rate (SR) number of parities and length of productive herd life (LPHL) were evaluated for Holstein Friesian cows that calved beginning January 1, 2000 through May 2021 in a research dairy farm. A total of 870 lactation records were examined. Average Survival Rates (SRs) were 75.8% to parity 2, 49.7% to parity 3, 37.3% to parity 4, 18.6% to parity 5, 11% to parity 6, 6.3% to parity 7 and 3.3% to parity 8. A change for a better survival rate of cows over the span, years 2011-2021 compared with 2000-2010 was found to parity 2 and to parity 3 (significant differences). For the rest of parities (to 4, to 5, to 6, to 7 and to 8) the differences were non-significant. Average number of parities over the spam years 2000 to 2015 was 2.81. Linear regression of average of parities on year of first calving was positive (R=0.2786) and this means that was a weak direct relationship between variables. A change in the year of first calving with 1 impacted a change in the number of parities with 0.006. Average productive herd life (months) over the span years 2000 to 2015 was 33.86. Linear regression of average LPHL by year of first calving was positive (R=0.6513) and this means that was a strong direct relationship between variables. A change in the year of first calving with 1, impacted a change in the number of parities with 0.1889. The results of this study can give important information for economic studies on dairy herd management [ABSTRACT FROM AUTHOR]

The present research captured a series of aspects related to the global pork market, focusing, above all, on the 2015-2021 interval. The main indicators that had to be analysed are: worldwide pig herds, worldwide pork production, global pork consumption, worldwide imports and exports of pork. Regarding pork, it was found that it is part of the food consumption model for part of the world's population, because it presents several characteristics agreed by consumers. The statistical data that were presented and analyzed in the study were provided by the FAOSTAT website. In order to better capture the evolution of the worldwide pork market, numerous specialized materials were consulted. In 2021, Asia achieved 52.4% of the production share of pig meat with the bone, fresh or chilled obtained worldwide. The top three pork consuming countries in 2021 were: Korea (31.6 kg/inhabitant); Vietnam (25.9 kg/inhabitant) and Chile (25.0 kg/inhabitant). [ABSTRACT FROM AUTHOR]