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.
•Scoring of lateral and sternal lying posture of pigs is presented.•Image processing and SVM were used to monitor lying postures of each pig.•Area and perimeter of boundaries and convex hull were ...used as inputs to the SVM.•High overall accuracies show the possibility of using the SVM.
The behaviour of animals provides information on their health, welfare and environmental situation. In different climatic conditions, pigs adopt different lying postures; at higher temperatures they lie laterally on their side with their limbs extended, while in lower temperatures they will adopt a sternal or belly lying posture. Machine vision has been widely used in recent years to monitor individual and group pig behaviours. So, the aim of this study was to determine whether a two-dimensional imaging system could be used for lateral and sternal lying posture detection in grouped pigs under commercial farm conditions. An image processing algorithm with Support Vector Machine (SVM) classifier was applied in this work. Pigs were monitored by top view RGB cameras and animals were extracted from their background using a background subtracting method. Based on the binary image properties, the boundaries and convex hull of each animal were found. In order to determine their lying posture, the area and perimeter of each boundary and convex hull were calculated in lateral and sternal lying postures as inputs for training of a linear SVM classifier. The trained SVM was then used to detect the target postures in binary images. By means of the image features and the classification technique, it was possible to automatically score the lateral and sternal lying posture in grouped pigs under commercial farm conditions with high accuracy of 94.4% for the classification and 94% for the scoring (detection) phases using two-dimensional images.
•Showers over the slats during warm periods decreased lying of the pigs in this area.•Pen fouling was reduced with showers over the slats during warm periods.•Ammonia emissions were reduced by 45% in ...rooms with showers.•Improved animal environment due to better pen hygiene and lower NH3 concentration.
Growing and finishing pigs kept in insulated buildings are often exposed to high ambient temperature during summer. In high-temperature conditions, pigs in partly slatted pens change their behaviour to increase lying on the slatted area and fouling on the solid floor area, resulting in increased ammonia emissions. One way to cool the animals is to shower/sprinkle water in the slatted area, allowing pigs to wet their skin to increase heat loss. This study examined the effects of providing showers on pig activity and occupation area in pens, pen fouling and ammonia emission from the room. The investigation was performed in a commercial growing-finishing house with 10 identical rooms, each containing 16 pens for 9–13 pigs growing from 25–30 kg to 115–120 kg. Pigs were introduced into two parallel rooms in the house. During two summers and four batches, one room with showers in the slatted area and one room without per batch were compared in terms of concentrations of carbon dioxide (CO2) and ammonia (NH3), pig activity and occupation area in the pen, pen fouling and NH3 emissions, recorded on four measuring occasions (M1–M4) during the growing period. Gas concentrations were measured using a photoacoustic analyser, pig activity and occupation area detected by machine vision techniques and pen fouling was visually investigated. Climate parameters (air temperature and relative humidity) were logged continuously during the entire growing period. Ammonia emission was calculated from ventilation rate (determined by the indirect CO2 tracer gas method) and the difference in ammonia concentration between outlet and inlet air.
The results showed that the pigs spent less time lying on the slats (p < 0.05) and the solid floor was cleaner (p < 0.05) on measuring occasions M2, M3 and M4 in rooms with showers than in control rooms. Mean NH3 emission for the four measurement occasions were 3.0–5.1 g pig−1 day−1 and 4.2–10.0 g pig−1 day−1 for the shower and control rooms, respectively. The differences were significant (p < 0.05) for all measuring occasions. The results also show improved animal environment when using showers to cool pigs at high ambient temperatures.
Overall, providing showers in the slatted area in partly slatted pens encouraged growing/finishing pigs to lie in the lying area, reduced problems with pen fouling and decreased NH3 emissions by 45%. The latter could be partly due to reduced pen fouling and partly to dilution of urine on the slatted area and on the surface of slurry in the pit.
•Increased air velocity in the lying area improved pen conditions during warm periods.•Pigs tended to lie less in the slatted area with increased air velocity in lying area.•Improved pen hygiene with ...increased air velocity during warm periods.•The higher proportion of time with increased air velocity the cleaner pens.•Reduced ammonia emissions during the last part of the growing period.
Partly slatted pens can offer growing/finishing pigs a better house environment than pens with fully slatted floors. Under thermoneutral conditions, pigs prefer to rest on a solid area and some litter can be provided as enrichment. Ammonia emissions are lower in systems with partly slatted pens, provided the pens are kept clean. However, under high-temperature conditions, pigs in partly slatted pens may begin lying on the slatted area and fouling on the solid floor area, resulting in increased ammonia emissions. This study examined the effects of increasing the air velocity (IAV) in the lying area from max 0.5 m s−1 to max 1.0 m s−1 on conditions for pigs in partly slatted pens during warm periods. Air velocity was increased by redirecting the inlet air from the ceiling inlets down into the animal zone.
The study was performed in a commercial growing/finishing house with 10 identical rooms, each containing 16 pens for 9-14 pigs growing from 25-30 kg to 115-120 kg live weight. Pigs were introduced simultaneously into two parallel rooms, one with IAV in the lying area and one without (control treatment). During two summers with six batches, concentrations of carbon dioxide (CO2) and ammonia (NH3), pig activity and choice of lying area in the pen, pen fouling and NH3 emissions were recorded in both rooms on four measuring occasions (M1-M4) during the growing period. Gas concentrations were measured by photoacoustic analyser, pig activity and pig choice of lying area by machine vision techniques, and pen fouling by visual inspection. Climate parameters (air temperature, relative humidity) were logged continuously during the growing period. Ammonia emissions were calculated from the ventilation rate (determined by the indirect CO2 tracer gas method) and the difference in ammonia concentration between outlet and inlet air.
Under high ambient temperatures, pigs in the IAV treatment were observed lying significantly more often (p<0.05) in the part of the lying area with the highest air velocity. Pigs tended to lie less in the slatted area (p=0.052) in the IAV treatment than in the control. Problems with pen fouling were significantly reduced with increased air velocity in the lying area and NH3 emissions were reduced by 21% (p=0.009), from 8.4 to 6.6 g pig−1 day−1, during the late growing period (M4).
In conclusion, increasing air velocity in the lying area of partly slatted pens from max 0.5 to max 1.0 m s−1 influenced pigs´ choice of lying area, improved pen hygiene and reduced ammonia emissions.
The increased frequency of hot days due to climate change can potentially impair the environmental and economic performance of pig-fattening farms. Several pig-cooling strategies have been proposed ...to address these impacts, however their implementation is not always economically viable and the potential environmental-economic trade-offs not well understood. Here, we propose and implement a novel framework for environmental and economic evaluation of pig-cooling strategies in a whole farm context. We also demonstrate through a sensitivity analysis how such models can be integrated with projected climate data to investigate how climate change may affect the assessment of capital investments that are made over significant timescales. We considered two strategies implemented in a pig-fattening farm in south Sweden: pig-cooling with showers and with increased air velocity. Operation of the farm under non-cooling conditions was considered as the baseline system against which the analysis was conducted. We calculated whole-farm annual equivalent values (AEV) with the implementation of each strategy through a discounted cash flow analysis and annualised system environmental impact through a life cycle assessment. Both cooling strategies significantly reduced system environmental impact across all categories except water footprint. Acidification potential was reduced the most, exhibiting a −3.28% reduction with pig showers and −1.51% with increased air velocity. Farm profitability improved by +6.79% with showers and +3.37% with increased air velocity. Ambient temperature increase under non-cooling conditions significantly increased all impact categories with acidification being affected the most (+2.24%), and caused a −4.43% decrease in AEV. Both pig-cooling strategies mitigated these effects on system environmental performance. With increased air velocity we observed a +0.718% increase in acidification, while pig showers were the more resilient option exhibiting a +0.690% increase. The study represents a case-in-point for how to rationalise economically environmental management technologies in pig housing systems based on their cost-effectiveness in mitigating environmental impacts.
Display omitted
•The environmental and economic impacts of two pig-cooling strategies were evaluated.•We considered pig-cooling with showers and increased air velocity at pig lying area.•Both strategies improved farm environmental performance for AP, EP and NRRU.•Both strategies mitigated heat stress, improved pig welfare and farm profitability.•The strategies mitigated the effects of global warming on pig farm sustainability.
In organic pig production, pigs are often provided with concrete areas outdoors. These outdoor areas are frequently used for urination and defecation by the pigs, which results in high nitrogen ...emissions. This is inconsistent with the goal of organic farming to minimise the environmental impact of agricultural production. Introduction of a well-designed rooting yard with an optimal rooting material could possibly be a way to improve the conditions in the outdoor area. In an earlier study, we tested different designs of rooting yards. In the present study, we compared outdoor areas without enrichment (Reference, R) with outdoor areas with rooting yards filled with one of three different kinds of rooting material: wood shavings (W), peat (P) or peat + a small amount of pelleted feed (PF).
In total, three batches (batch 1: Dec-April (winter/spring); batch 2: May-Sept (summer); batch 3: Oct-Jan (autumn/winter), in a research facility with eight pens of 16 pigs each, were studied. Data on performance and activity, hygiene and ammonia emission in the outdoor area were used for the evaluation.
No significant differences in performance were seen between treatments. The pigs found the rooting yards with rooting material outdoors attractive and pigs with rooting material outdoors tended to be outdoors more often than pigs in the reference pen. However, these differences were generally not significant, due to large variations. Hygiene outdoors was significantly better in the pens with rooting yards and rooting material than in the reference pen, but there were no significant differences depending on whether the rooting yards were filled with wood shavings, peat or peat with feed pellets. However, while the visual hygiene evaluations showed positive results for all rooting materials tested, the ammonia measurements did not show matching results. Instead, the ammonia emission from the outdoor area was higher in pens with wood shavings in the rooting yards than in the reference pen. Thus introduction of a rooting yard with rooting material in the outdoor area in organic pig production can have positive results in terms of improved hygiene and reduced ammonia emission if the rooting material consists of peat. Addition of small amounts of feed pellets in the peat, to make the rooting material more attractive to the pigs, did not give any great positive effect.
•Hygiene outdoors was improved in pens with rooting yards and rooting material.•Wood shavings in the rooting yards increased ammonia emission.•Peat in the rooting yards was attractive and reduced ammonia emission.
Large fouled concrete areas outdoors and high nitrogen emissions are a problem in organic pig production. This is not consistent with the goal of organic farming to minimise the environmental impact ...of agricultural production. Introduction of a special rooting yard with rooting material in the outdoor concrete area could possibly be a way to create more activity in one part of the outdoor area, in which the pigs do not want to excrete. In the present study, the aim was to find an optimal design for such a rooting yard in the outdoor area. Four different designs of rooting yards, with varying sizes and wall heights ((LH=large (8.4m2) with one high wall (1.0m); LL=large (8.4m2) with low walls (0.3m); SH=small (5.3m2) with one high wall (1.0m) and SL=small (5.3m2) with low walls (0.3m)), were tested in parallel and compared with a reference pen (R) without a rooting yard. Peat was used as rooting material in all the outdoor rooting yards. In total, two batches, in a research facility with eight pens of 16 pigs each, were studied. Data on performance, location and activity in the pen and hygiene and ammonia emissions in the outdoor area were used for evaluation of the designs. No significant differences were seen in performance, total activity and total rooting activity between treatments. However, the pigs in the pens with rooting yards were observed rooting outdoors significantly more than those in the reference pens. Significantly better hygiene and a tendency for lower ammonia emissions from the area with rooting material were recorded in the pens with rooting yards compared with the same area in the reference treatment.
It was concluded that use of a rooting yard in the outdoor area in organic pig production allows the excretory behaviour of the pigs to be steered in the desired direction, improving hygiene and the appearance of the outdoor area. A large rooting yard with one high wall was found to be the best design, giving a 14% reduction in chamber NH3 emissions (ECH) from the total outdoor area compared with the reference pen.
•The excretory behaviour of pigs can be steered by introducing a rooting yard.•Hygiene studies showed advantages with a rooting yard with one high wall.•A rooting yard with peat in the outdoor area tended to lower NH3 emissions.
The effects of two housing systems (deep litter and straw-flow), with and without access to pasture during the summer period, were studied in an organic growing–finishing pig herd. Pen hygiene ...studies, N, P and K budgets and estimations of nitrogen emission were made for two batches (8pens/batch and 16pigs/pen) one during the winter period and one during the summer period. It was concluded that there were no significant differences in overall pen hygiene between the housing systems. During the growing period in the summer, the pen hygiene on the outdoor concrete area was significantly better (P<0.05) when the pigs had access to pasture. In addition, the total pen hygiene (indoors+concrete area outdoors) tended (P=0.09) to be cleaner with access to pasture during the summer period. The N-losses of the amount of N excreted were the same (26–27%) during the winter period as during the summer period. The amount of N excreted was on average 6.0kg N per pig during the winter, and 4.2kg N per pig during the summer; this was equivalent to an N-emission of 1.5–1.6kg N/pig during winter and 1.1–1.2kg N/pig during summer. The difference was mainly due to a higher feed consumption and more straw usage during the winter. In comparison to the calculated N-emissions from a non-organic pig, this was approximately 3–4 times greater. In the present study, a 10% larger feed usage explained the differences in N-emission by a factor of 1.2, a 15% higher crude protein level explained the differences by a factor of 1.3 and finally a larger fouled area explained the differences by a factor of 2.3. Differences in temperature and airflow were not taken into account in these calculations.
•N excreted was 6.0 and 4.2kg Npig−1 during winter and summer, respectively.•N-losses of N excreted were the same (26–27%) during winter and summer.•N emitted from organic pigs was 3–4 times greater than that from non-organic pigs.•Larger fouled areas, less optimized feed and higher usage explained the differences.
The effect of using different binding agents in combination with hemp shives and fibres in Lime–Hemp Concrete (LHC) building material was examined. LHC is a light composite building material with ...building lime as binding agents and hemp (
Cannabis sativa) as a renewable raw material from agriculture. Contemporary LHC only uses the woody core part of the hemp, the shive. However, using both hemp shives and fibres may improve the mechanical strength, eliminating the need for a fibre separation process.
The aim was to elucidate the feasibility of using the entire fragmented hemp stalk in an LHC, and to determine some important material properties such as compressive strength, splitting tensile strength, water sorption and frost resistance. LHC with varying inclusions of the lime-based binders were tested, as were five mixes using the binding agents hydrated lime, hydraulic lime, and cement.
Specimens were cured for 12 weeks at room temperature and 40 days in a carbonation room (4.5
vol% CO
2), and tested for mechanical properties, water sorption and frost resistance. Using both shives and fibres in LHC may be advantageous for countries such as Sweden where facilities for separating hemp from shives are not commercially available.
The Swedish animal production sector has potential for saving electric lighting of €4-9 million per year using efficient daylight utilisation. To demonstrate this, two light pipe systems, Velux® ...(house 1) and Solatube® (house 2), are installed in two identical pig houses to determine if the required light intensity, daylight autonomy (DA), and reduced electricity use for illumination can be achieved. In each house, three light sensors continuously measure the indoor daylight relative to an outdoor sensor. If the horizontal illuminance at pig height decreases below 40 lux between 08.00 and 16.00 hours, an automatic control system activates the lights, and electricity use is measured.. The daylight factor (DF) and DA are determined for each house, based on annual climate data. The mean annual DA of 48% and 55% is achieved for house 1 and house 2, respectively. Light pipes in house 2 have delivered significantly more DA than those in house 1. The most common illuminance range between 0 and 160 lux is recorded in both houses, corresponding to approximately 82% and 83% of daylight time for house 1 and house 2, respectively. Further, the daylighting system for house 2 has produced a uniform DF distribution between 0.05 and 0.59. The results demonstrate that considerable electric energy savings can be achieved in the animal production sector using light pipes. Saving 50% of electric lighting would correspond to 36 GWh or 2520 t CO2 per year for Sweden, but currently the energy savings are not making the investment profitable.