Posture detection targeted towards providing assessments for the monitoring of health and welfare of pigs has been of great interest to researchers from different disciplines. Existing studies applying machine vision techniques are mostly based on methods using three-dimensional imaging systems, or two-dimensional systems with the limitation of monitoring under controlled conditions. Thus, the main goal of this study was to determine whether a two-dimensional imaging system, along with deep learning approaches, could be utilized to detect the standing and lying (belly and side) postures of pigs under commercial farm conditions. Three deep learning-based detector methods, including faster regions with convolutional neural network features (Faster R-CNN), single shot multibox detector (SSD) and region-based fully convolutional network (R-FCN), combined with Inception V2, Residual Network (ResNet) and Inception ResNet V2 feature extractions of RGB images were proposed. Data from different commercial farms were used for training and validation of the proposed models. The experimental results demonstrated that the R-FCN ResNet101 method was able to detect lying and standing postures with higher average precision (AP) of 0.93, 0.95 and 0.92 for standing, lying on side and lying on belly postures, respectively and mean average precision (mAP) of more than 0.93.
The ban of antibiotics as a feed additive requires alternatives to stabilize the health and performance particularly of the young animals. Essential oils obtained from fennel seed (Foeniculi aetheroleum) and caraway seed (Carvi aetheroleum) were tested in diets for weaned piglets in comparison with either a diet without feed additive or with a combination of formic acid and copper (positive control). Four groups of sixteen piglets (live weight 7 kg, age 26 days) received diets without (1) or with supplements of 7.5 g formic acid + 160 mg Cu/kg (2), 100 mg fennel oil/kg (3) or 100 mg caraway oil/kg (4) during 3 weeks after weaning. In the subsequent 4 weeks, all piglets were fed a diet without these additions. Fennel oil contained almost 2/3 anethol, approximately 1/5 fenchon and the remaining part consisting of alpha + beta-pinen, limonen (p-mentha-1,8-dien) and estragol. In the caraway oil, half of the contents was represented by limonen and the other half by carvon. There were no piglet losses and only few cases of diarrhoea. The combination of formic acid and copper increased feed consumption by 27% and daily weight gain by 25%. There were no differences in the performance between the group fed fennel oil and the control without additives. Piglets fed caraway oil tended to consume less feed and to gain approximately 10% less. In feed choice experiments, pigs consumed the same two diets from two troughs with 50% of total feed amount, as expected. The diets containing fennel or caraway oils were consumed at less than 50%. If the diet contained 100 mg fennel oil/kg, the decrease of percentual feed intake was significant. The results of the feeding experiment and of the feed choice experiment question the classification of fennel and caraway oils as flavour additives or as 'appetite promoters' in diets for weaned piglets.
Feed intake behavior was studied between 9 weeks of age and slaughter in a total of 36 gilts, 32 immunocastrates, 33 surgically castrated barrows and 33 boars from 36 litters. Consequences for the concentration of substances contributing to off odor of pork (skatole, indole) were evaluated. Animals were kept in groups of 12 pigs of the same sex and treatment and fed ad libitum (13.4 MJ ME, 17% CP, 1.1% lysine). Individual feed intake behavior was recorded continuously by an electronic feeder. Immunocastration was carried out with two injections of Improvac with at least 4 weeks between both injections (1st: 12 to 17 weeks of age, 2nd: 19 to 21 weeks of age). Feed intake/day increased from an average of 0.91 6 0.02 kg/day up to 3.15 6 0.04 kg/day before slaughter. This increase was associated with a 50% reduction in the number of meals/day (from 15.8 6 0.44 to 7.2 6 0.29 meals/day). The larger meal sizes resulted from an increase in both, the duration of feed intake/meal and the feed intake rate (g/min). In addition, sex and treatment differences were observed: Feed intake in boars was lower than in all other groups due to a reduction in the number of meals/day and in the time spent feeding/day. In females, time spent feeding/day was quite similar to boars, but resulted from a higher number of meals of shorter duration. Barrows had a significantly higher feed intake because of a higher number of meals/day resulting in more time spent feeding/day. The feed intake rate was similar in boars, gilts and barrows and showed an increasing trend during the study, starting from about 15 g/min up to four times the amount. Immunocastration affected feed intake behavior severely, especially the meal size increased dramatically because of higher feed intake rate, which exceeded that of all other groups by 25% at the end of the study. The number of meals/day was not influenced by immunocastration and was almost identical to that of boars. Highest skatole concentrations were measured in fat of boars, whereas indole concentrations were higher in immunocastrates than in all other groups. In gilts and barrows, skatole concentrations were related to growth rate. Additionally, the feeding rate was an important factor explaining the variability in skatole/indole concentrations in adipose tissue. The physiological mechanisms however need further clarification.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.