Browsing by Subject "Monitoring"

Now showing 1 - 5 of 5

AI-based planting and monitoring of cabbage with a robotic platform
(2024) Lüling, Nils; Griepentrog, Hans W.
Labour shortages, price pressure and changes in legislation are just a few of the drivers of automation and digitalization in field vegetable cultivation. Due to its high-value crops and its high demands on crop maintenance, field vegetable cultivation is the ideal working area for agricultural robotics. However, the versatile and rapid establishment of agricultural robotics systems has so far failed due to the limited adaptivity to the complex working environment under outdoor conditions, the process chain and the applications that an agricultural robot has to carry out in a field. Only through the developing possibilities of using cameras and artificial intelligence can complex automated applications be implemented. The overall aim of this cumulative dissertation was the development and analysis of systems for AI-based crop establishment and crop maintenance of white cabbage with a robotic platform. Three aspects were analysed: (1) Design, prototyping and evaluation of a planting unit for an autonomous planting process of cabbage with a robotic platform. By using AI-based image classification, a camera at the end of the planting unit was used to evaluate the planting quality and dynamically adjust individual planting parameters. (2) Development of a camera-based vegetation monitoring system for determining the fruit volume and leaf area of white cabbage across several growth stages. (3) Analysis of a method for unsupervised image translation for automated exposure adjustment. By reducing the exposure variation, a lower implementation effort and a higher robustness of the detection and segmentation of white cabbage are aimed for. As part of the autonomous crop establishment, a planting unit was developed and constructed that can carry out an automated crop stand establishment process using a robot platform. The analysis of the quality of the planting process showed a comparable planting performance and planting accuracy to conventional systems of automated field vegetable planting. During the development of the planting unit, the focus was placed on an adaptive design of the unit so that machine parameters can be dynamically adjusted during the planting process. It was possible to reduce the energy requirement of the overall system by dynamically opening and closing the planting furrow during the planting process in order to minimize the draft force. It also creates the basis for an autonomous planting process. Using an attached camera and an AI for image classification, the planting quality can also be recorded and planting parameters such as the planting depth and furrow width can then be adjusted in order to influence the plant placement. At the same time, the AI-based image classification can also be used to control the planting process itself. If the planting tape tears or the separation is blocked, no seedlings are planted. The AI recognizes this and can instruct the robot to suspend the planting process. For automated crop monitoring, the camera, in cooperation with a neural network for instance segmentation, offers the possibility of a contact-free and high-resolution recording of plant parameters. Using instance segmentation of the cabbage head, the cabbage plant and the individual cabbage leaves, as well as a depth image generation using structure-from-motion, it was possible to determine plant parameters such as the absolute leaf area, the number of leaves or the fruit volume of the cabbage head across several growth stages. This offers farmers new opportunities in crop management, which can be tailored even more specifically to individual plants using the information collected. As many possibilities as the use of cameras in combination with neural network-based image analysis offers, there are still some challenges. One of the fundamental challenges lies in the provision and annotation of image data to ensure robust image analysis. The more complex the use case, the more varying images the data set must contain in order to provide the neural network with a basis of information with which it can learn the necessary features. To reduce the complexity of the use case of detecting and segmenting cabbage plants, an AI-based image translation was used to standardize the exposure variations. No annotation is required to train the AI-based image translation, which is trained unsupervised. By standardizing the exposure, the complexity of the images can be reduced, which means that fewer images need to be annotated for a robust use of instance segmentation. This method was also tested for varying growth stages and varieties.
Behavioral economic impact on animal health surveillance system in Thailand
(2021) Kewprasopsak, Tossapond; Reiner, Doluschitz
Zoonotic diseases are a continuously significant threat to global human and livestock health (causing millions of deaths yearly). Zoonotic diseases are not only a human health threat, but also a threat to animal health and welfare. Moreover, they have a high impact on national economies and food security due to productivity and production reduction. Expanding worldwide travel and global trade increases the importance of the threat of zoonotic diseases. The increase in global meat consumption contrasts with the escalating instability of the global meat market, which is affected by the increase of livestock densities, changes in production intensity, and slaughtering systems, causing animal disease outbreaks to spread widely. This study focuses on the animal disease surveillance system in Thailand as an important world meat exporter. In 2014, the Participatory One Health Disease Detection project, or PODD was set up by the veterinary inspection authorities to test animal epidemic control systems using smartphone applications in the Chiang Mai province in northern Thailand The main objectives of this study are (i) to evaluate the economic impact of the PODD system on farmers by impact assessment (n = 177) (ii) to demonstrate the impact of monetary and non-monetary incentives on the PODD reporters by the experimental approach (n = 17), (iii) and to present the effect of the socioeconomic factors and behavioral bias on farmers animal disease reporting behavior with the logit model (n = 467). Focusing on the first objective, the results of this study concluded that there is an impact on the farmers. The technology alone cannot improve animal health security in the short-term. In the second objective, the results concluded that, in the case of the PODD reporters, the decision of using monetary incentives to motivate most of the PODD reporters has a negative impact in the long-term. Losing reporter motivation and effort reflected to the low efficiency of the digital surveillance system of PODD and no impact on farmers. Concerning In the last objective, the results concluded that the optimistic bias of farmers has a very high impact on their decision making about reporting animal diseases on their farm. Just one infected farm in the case of dairy milk farmers can spread the foot-and-mouth disease to other farms. The new digital animal health surveillance system alone is not enough to reduce the impact of animal diseases of farmers. Suitable motivation for the reports and awareness of farmers optimistic bias in animal disease reporting cannot be neglected in digital animal disease surveillance system improvement. Overall, it can be concluded that the digital animal disease surveillance system is a powerful instrument for reducing the impact of animal diseases and increasing food safety and security. However, application of this advanced technology still needs time to demonstrate the impact and to be broadly adopted by users. In terms of motivation, the monetary incentive can increase the effort of report in the short run but it comes at a high cost and has a negative impact in the long-term. While the social incentive costs less and is more effective in the long-term. Where farmers’ animal disease reporting behavior is concerned, the optimistic bias is the highest influential factor on the farmers reporting decisions, in an inverse correlation.
Behavioral economic impact on animal health surveillance system in Thailand (correct version of the dissertation)
(2021) Kewprasopsak, Tossapond
Zoonotic diseases are a continuously significant threat to global human and livestock health (causing millions of deaths yearly). Zoonotic diseases are not only a human health threat, but also a threat to animal health and welfare. Moreover, they have a high impact on national economies and food security due to productivity and production reduction. Expanding worldwide travel and global trade increases the importance of the threat of zoonotic diseases. The increase in global meat consumption contrasts with the escalating instability of the global meat market, which is affected by the increase of livestock densities, changes in production intensity, and slaughtering systems, causing animal disease outbreaks to spread widely. This study focuses on the animal disease surveillance system in Thailand as an important world meat exporter. In 2014, the Participatory One Health Disease Detection project, or PODD was set up by the veterinary inspection authorities to test animal epidemic control systems using smartphone applications in the Chiang Mai province in northern Thailand The main objectives of this study are (i) to evaluate the economic impact of the PODD system on farmers by impact assessment (n = 177) (ii) to demonstrate the impact of monetary and non-monetary incentives on the PODD reporters by the experimental approach (n = 17), (iii) and to present the effect of the socioeconomic factors and behavioral bias on farmers animal disease reporting behavior with the logit model (n = 467). Focusing on the first objective, the results of this study concluded that there is an impact on the farmers. The technology alone cannot improve animal health security in the short-term. In the second objective, the results concluded that, in the case of the PODD reporters, the decision of using monetary incentives to motivate most of the PODD reporters has a negative impact in the long-term. Losing reporter motivation and effort reflected to the low efficiency of the digital surveillance system of PODD and no impact on farmers. Concerning In the last objective, the results concluded that the optimistic bias of farmers has a very high impact on their decision making about reporting animal diseases on their farm. Just one infected farm in the case of dairy milk farmers can spread the foot-and-mouth disease to other farms. The new digital animal health surveillance system alone is not enough to reduce the impact of animal diseases of farmers. Suitable motivation for the reports and awareness of farmers optimistic bias in animal disease reporting cannot be neglected in digital animal disease surveillance system improvement. Overall, it can be concluded that the digital animal disease surveillance system is a powerful instrument for reducing the impact of animal diseases and increasing food safety and security. However, application of this advanced technology still needs time to demonstrate the impact and to be broadly adopted by users. In terms of motivation, the monetary incentive can increase the effort of report in the short run but it comes at a high cost and has a negative impact in the long-term. While the social incentive costs less and is more effective in the long-term. Where farmers animal disease reporting behavior is concerned, the optimistic bias is the highest influential factor on the farmers’ reporting decisions, in an inverse correlation.
Sustainable food consumption and Sustainable Development Goal 12: conceptual challenges for monitoring and implementation
(2024) Mensah, Kristina; Wieck, Christine; Rudloff, Bettina
In recent years, policy initiatives have been developed to promote sustainability. Although sustainable food production is an integral part of many national agricultural policies, this is not the case for sustainable food consumption. This article systematically reviews key elements of sustainable food consumption and evaluates how they align with existing policy indicators, specifically SDG 12, within the context of the agricultural policy of the European Union. Through a cross-referencing approach, this article identifies gaps and possible improvements in policy indicator frameworks to better capture elements of sustainable food consumption. We find that SDG 12 targets are not suitable to assess progress to sustainable food consumption. While targets are closely linked to environmental and economic issues, they are insufficient to monitor sustainable food consumption. Our findings suggest the necessity for enhanced or modified policy indicators that encompass the key elements of sustainable food consumption as well as a comprehensive definition of the latter to effectively design and evaluate polices on this matter.
Verhaltens- und Gesundheitsmonitoring für die Gruppenhaltung tragender Sauen
(2015) Junge, Melanie; Jungbluth, Thomas
The number of pig farmers in Germany with breeding sow herds has continually re-duced over the past 15 years. Simultaneously, herd size has increased. This trend is intensified through the introduction of mandatory group housing for gestating sows. While larger herds represent high demands on management and monitoring of indi-vidual animal health, the situation also offers potential for automation of work proce-dures or in data recording as part of indicator-based systems. The primary objective of this work was conception, implementation and evaluation of a monitoring system for determining health and behaviour deviations of gestating sows in group housing. Hereby, sensor and data technology infrastructure was to be designed for recording animal-individual indicators as feeding or drinking events as well as minimum distances travelled within a sow gestation stable for a large dynamic group. Materials used were the available RFID technology of two electronic feeding stations (EFS) and a boar recognition system. These were supplemented by the mounting of additional RFID antennae besides drinkers and on the two doors between exercise and indoor areas. For determining volumes of water metered out, flowmeters were fitted in the supply pipelines for all eight drinkers. The EFS data protocols were used for assessment of feeding events and calculation of relative eating ranks. Over the combined time-related sequencing of registration of the 13 RFID antennae within the sow gestation stable, the animal-individual minimum distances travelled were calculated on a daily basis. Animal-individual assessment of health status and changes in behaviour of the sows was conducted as part of an observation study. Examined were relationships between the automatically recorded indicators feeding events, drinking events and distances travelled, in addition to changes in health and behaviour were examined. The potential for implementation of a monitoring or prediction model was then assessed. From 13.04.2012 to 31.05.2013, recorded and analysed were 29,552 day data sets from 199 gestating sows (parity 2 to 11). In this period, only a few effects on sow health through cases of disease were documented. However, during the twice-weekly gait assessment of the sows via locomotion scoring, some cases of medium to serious lameness were identified. During 372 days, 69,577 drinking events with water volumes of from 2 ml to 11.45 l were recorded. On average, the sows drank 0.53 l water 2.4 times per day although, for 25% of the daily data sets, no drinking events were determined. In addition, a clear 24-hour cycle of water consumption was established with maxima during morning and afternoon. Where sows did not take feed from the EFS, they then tended to drink less water from the drinkers. Parity and temperature differences appeared to have only a limited influence on water consumption. Contrary to this, the sows identified as lame showed a highly significant reduced count of animal-individual drinking events, metered amounts of water at the drinkers, lower calculated distances travelled and time spent at the boar recognition in comparison with sows showing no symptoms of lameness. Detection of sows returning to heat via observation of animal-individual periods of attendance at the boar recognition and then applying a threshold value model proved very effective. Comparing standard-behaviour sows and those returning to heat also led to identifying a tendency towards reduction in metered drinking water consumption and number of drinking events for the latter. The assessments of feeding sequences at the EFS and calculation of relative eating ranks gave no significant differences between non-standard behaviour and standard behaviour animals. A tendency for influences of age, lameness and return to heat on EFS feeding sequence, or on relative eating ranks, was observed. For locomotion behaviour of gestating sows kept in large groups, reference values for possible distances travelled could be collected. Up to now, only very little literature was available on this subject. Management-associated measures such as the integration of new animals in the group appeared to have very little influence on the investigated indicators. The feasibility of animal-individual monitoring through real time processing of sensor data recorded from a group of gestating sows and of integration with a management software program, could be demonstrated. In total, however, the very large animal intra and inter variability for the parameters drinking events, feeding events and minimum distances travelled complicated the definition of the individual-animal monitoring models for indicator-based early identification of health problems. Conceivable here are further follow-up investigations regarding indicators, sensors and assessment algorithms.