Staff Publications

Staff Publications

  • external user (warningwarning)
  • Log in as
  • language uk
  • About

    'Staff publications' is the digital repository of Wageningen University & Research

    'Staff publications' contains references to publications authored by Wageningen University staff from 1976 onward.

    Publications authored by the staff of the Research Institutes are available from 1995 onwards.

    Full text documents are added when available. The database is updated daily and currently holds about 240,000 items, of which 72,000 in open access.

    We have a manual that explains all the features 

    Records 1 - 20 / 78

    • help
    • print

      Print search results

    • export

      Export search results

    Check title to add to marked list
    The effect of data augmentation and network simplification on the image-based detection of broccoli heads with Mask R-CNN
    Blok, Pieter M. ; Evert, Frits K. van; Tielen, Antonius P.M. ; Henten, Eldert J. van; Kootstra, Gert - \ 2020
    Journal of Field Robotics (2020). - ISSN 1556-4959
    agriculture - computer vision - learning - perception - sensors

    In current practice, broccoli heads are selectively harvested by hand. The goal of our work is to develop a robot that can selectively harvest broccoli heads, thereby reducing labor costs. An essential element of such a robot is an image-processing algorithm that can detect broccoli heads. In this study, we developed a deep learning algorithm for this purpose, using the Mask Region-based Convolutional Neural Network. To be applied on a robot, the algorithm must detect broccoli heads from any cultivar, meaning that it can generalize on the broccoli images. We hypothesized that our algorithm can be generalized through network simplification and data augmentation. We found that network simplification decreased the generalization performance, whereas data augmentation increased the generalization performance. In data augmentation, the geometric transformations (rotation, cropping, and scaling) led to a better image generalization than the photometric transformations (light, color, and texture). Furthermore, the algorithm was generalized on a broccoli cultivar when 5% of the training images were images of that cultivar. Our algorithm detected 229 of the 232 harvestable broccoli heads from three cultivars. We also tested our algorithm on an online broccoli data set, which our algorithm was not previously trained on. On this data set, our algorithm detected 175 of the 176 harvestable broccoli heads, proving that the algorithm was successfully generalized. Finally, we performed a cost-benefit analysis for a robot equipped with our algorithm. We concluded that the robot was more profitable than the human harvest and that our algorithm provided a sufficient basis for robot commercialization.

    Development of a sweet pepper harvesting robot
    Arad, Boaz ; Balendonck, Jos ; Barth, Ruud ; Ben-Shahar, Ohad ; Edan, Yael ; Hellström, Thomas ; Hemming, Jochen ; Kurtser, Polina ; Ringdahl, Ola ; Tielen, Toon ; Tuijl, Bart van - \ 2020
    Journal of Field Robotics (2020). - ISSN 1556-4959
    agriculture - computer vision - field test - motion control - real-world conditions - robotics

    This paper presents the development, testing and validation of SWEEPER, a robot for harvesting sweet pepper fruit in greenhouses. The robotic system includes a six degrees of freedom industrial arm equipped with a specially designed end effector, RGB-D camera, high-end computer with graphics processing unit, programmable logic controllers, other electronic equipment, and a small container to store harvested fruit. All is mounted on a cart that autonomously drives on pipe rails and concrete floor in the end-user environment. The overall operation of the harvesting robot is described along with details of the algorithms for fruit detection and localization, grasp pose estimation, and motion control. The main contributions of this paper are the integrated system design and its validation and extensive field testing in a commercial greenhouse for different varieties and growing conditions. A total of 262 fruits were involved in a 4-week long testing period. The average cycle time to harvest a fruit was 24 s. Logistics took approximately 50% of this time (7.8 s for discharge of fruit and 4.7 s for platform movements). Laboratory experiments have proven that the cycle time can be reduced to 15 s by running the robot manipulator at a higher speed. The harvest success rates were 61% for the best fit crop conditions and 18% in current crop conditions. This reveals the importance of finding the best fit crop conditions and crop varieties for successful robotic harvesting. The SWEEPER robot is the first sweet pepper harvesting robot to demonstrate this kind of performance in a commercial greenhouse.

    Harvesting device
    Tuijl, B.A.J. van; Karruppannan, E.W. ; Tielen, A.P.M. ; Barth, R. - \ 2020
    Octrooinummer: WO2020005064, gepubliceerd: 2020-01-02.
    The current invention provides a harvesting device for harvesting crop having a target with a peduncle, the harvesting device comprising: a main frame; a cutting device connected to the main frame and configured to cut the peduncle, an imaging system to determine a position of the target with respect to the main frame, a guide system connected to the main frame for guiding the target towards a cutting position with respect to the main frame; - wherein the guide system comprises a forward guide member configured to be the first contact of the harvesting device with the crop.
    Structured Design of a Novel End-Effector for a Bush Trimming Robot
    Tuijl, B.A.J. van; Tielen, A.P.M. ; Mencarelli, A. ; Hemming, J. - \ 2018
    In: Proceedings of the European Conference on Agricultural Engineering AgEng2018. - Wageningen : Wageningen University & Research - p. 188 - 196.
    The European TrimBot 2020 project researches the robotics and vision technologies to prototype the first autonomous outdoor garden trimming robot. The robot navigates over different terrains, approaches boxwood plants and trims them to a desired shape. The robot platform is based on a modified Bosch robot lawnmower,which navigates autonomously using 3D-based vision scene analysis. During trimming a robotic arm is controlled by visual servo in order to trim the bush. A novel end-effector had to be designed to guarantee flexibility of the manipulator, precision of trimming and smoothness of the trimmed bush surface. This paper describes the structured design of this bush trimmer. When faced with a design problem with many interconnecting system elements, structured design is a tool to be used to iteratively and step by step guide the designers in making the right design choices at the right moment during the different design phases. First, preliminary research is done to analyse the problem and to assess the goals of the end-effector. Second, the functions are determined and working principles are found and put into a coherent structure. Finally, this leads to a composition of several preliminary designs of which the most promising one is determined. This design is built as a working prototype. Next to this, 3D-Computer Aided Design (CAD) tools and rapid prototyping is used to test ideas along the design process. The final design, based on contra-rotating blades, was discussed in terms of how and to what extent it has met the requirements, objectives and functions found during the structured design process. Moreover, the results of lab and field tests have shown the first functional results and points of improvements have been identified. A novel trimming method, by contra-rotating blades, has been found using structured design which meets the demands and limitations of other system components of the robot.
    Trimbot cutting tools and manipulator
    Hemming, Jochen ; Tuijl, Bart Van; Tielen, Toon ; Kaljaca, Dejan ; IJsselmuiden, Joris ; Henten, Eldert Van; Mencarelli, Angelo ; Visser, Pieter De - \ 2018
    In: Applications of Intelligent Systems - Proceedings of the 1st International APPIS Conference 2018, APPIS 2018. - IOS Press (Frontiers in Artificial Intelligence and Applications ) - ISBN 9781614999287 - p. 89 - 93.
    Agriculture - End-effector - Path planning - Pruning - Robot - Trimming

    This article describes the tasks and first results of the work package "Manipulator and Control" of the EU project Trimbot2020. This project develops a mobile robot for outdoor hedge, rose and bush trimming. The Kinova Jaco 2 robotic arm was selected as manipulator. Two different types of robotic end-effectors have been developed. The tool for trimming topiaries uses two custom designed circular contra-rotating blades. The tool for single stem cutting is based on a commercial electrical pruner. The arm and the tools can all be controlled by using the Robot Operating System (ROS). The motion planning algorithm of the arm for the bush trimming action is divided into the planning setup module, the coverage planning module and the trajectory planning module. The path planning is modelled as a traveling salesman problem. In the first phase of the project the trimming control is performed open loop. A positioning genetic algorithm was developed that minimizes the needed number of vehicle poses for one target object. In the next phase of the project a vision feedback mechanism will be implemented.

    Oogstvoorspelling met behulp van cameratechnieken
    Tielen, A.P.M. - \ 2018
    Onder Glas 15 (2018)12. - p. 43 - 43.
    Ontwikkeling en validatie van computer vision technologie ten behoeve van een broccoli oogstrobot
    Blok, Pieter M. ; Tielen, Antonius P.M. - \ 2018
    Wageningen : Stichting Wageningen Research, Wageningen Plant Research, Business unit Agrosysteemkunde (Rapport WPR 799) - 19
    De selectieve en handmatige oogst van broccoli is arbeidsintensief en omvat ongeveer 35% van de totale productiekosten. Dit onderzoek is uitgevoerd om te bepalen of computer vision kan worden gebruikt om broccoli kronen te detecteren, als eerste stap in de ontwikkeling van een autonome selectieve broccoli oogstrobot. Een op textuur en kleur gebaseerde beeld detectie is gebruikt om de broccoli kronen van de achtergrond te scheiden. De computer vision is gevalideerd met een ground truth dataset van 200 afbeeldingen. In deze beelden zijn 228 werkelijke broccoli kronen van verschillende groottes aangewezen door twee menselijke experts gebruikmakend van het GrabCut-algoritme. De broccoli detectie van de computer vision is op twee verschillende manieren beoordeeld. De eerste was een pixel-gebaseerde overlap tussen de computer vision en de werkelijke broccoli objecten, wat resulteerde in een gemiddelde overlap van 93.8%. De tweede waarde was op basis van de detectie van de individuele broccoli kronen. Deze toonde een precisie van 99.5%, met een slechts één onterecht aangemerkte broccoli. De specificiteit was 97.9%, de negative predictive value was 69.7% en de gemiddelde nauwkeurigheid was 92.4%. In het totaal zijn 208 broccoli kronen gedetecteerd door de computer vision, wat wijst op een sensitiviteit van 91.2%. De gemiddelde grootte van de
    gemiste kronen was kleiner dan de gemiddelde grootte van de gedetecteerde kronen. Indien de broccoli kronen slechter zichtbaar zijn of overschaduwd worden door omringende bladeren is het mogelijk dat de computer vision misclassificaties levert.
    Trimbot Cutting Tools and Manipulator
    Hemming, J. ; Tuijl, B.A.J. van; Tielen, A.P.M. ; Kaljaca, D. ; Ijsselmuiden, J.M.M. ; Henten, E.J. van; Mencarelli, A. ; Visser, P.H.B. de - \ 2018
    Terugdringen ketenverliezen in de varkenshouderij. Rapport van de VarKel werkgroep
    Bondt, N. ; Backus, G.B.C. ; Hoste, R. ; Puister-Jansen, L.F. ; Tielen, J. - \ 2005
    Den Haag : LEI (Rapport / LEI : Domein 5, Ketens ) - ISBN 9789052429724 - 53
    agrarische economie - varkenshouderij - dierveredeling - slachthuizen - kosten - prijzen - planning - productiekosten - marktconcurrentie - nederland - ketenmanagement - varkensfokkerij - agricultural economics - pig farming - animal breeding - abattoirs - costs - prices - planning - production costs - market competition - netherlands - supply chain management - pig breeding
    In het Varkenshouderij Ketenproject Limburg (VarKeL) hebben deelnemers uit de fokkerij (Topigs), varkenshouders (LLTB) en slachterijen (Dumeco en HMG) zich onder begeleiding vanuit onderzoeksinstelling LEI en adviesbureau Area Advies gericht op het bepalen van de mogelijkheden om ketenverliezen in de varkenshouderij terug te dringen. Dit rapport geeft concrete verbetermogelijkheden aan op het gebied van informatie en communicatie, alternatief prijs-/planningssysteem, marktgerichte productie en ketenkosten. Hiermee kan de doelstelling worden bereikt, namelijk om door ketenoptimalisatie te komen tot een kostenreductie van € 0,05 per kilogram geslacht gewicht. Reduction of economic losses in the pig chain In the Limburg Pork Supply Chain Project (VarKeL) participants from pig breeding (Topigs), pig farmers (LLTB) and slaughterhouses (Dumeco and HMG), under the supervision of the LEI research institution and the Area Advies advisory bureau, have joined together to determine the possibilities for reducing chain losses in pig farming. This report gives concrete points for improvement in the field of information and communication, alternative price/planning system, market-oriented production and chain costs. With those improvements the aim of the project can be achieved, namely a cost reduction of € 0.05 per kg of slaughter weight through chain optimisation.
    Neighbourhood infections of classical swine fever during the 1997-1998 epidemic in the Netherlands
    Crauwels, A.P.P. ; Nielen, M. ; Elbers, A.R.W. ; Stegeman, J.A. ; Tielen, M.J.M. - \ 2003
    Preventive Veterinary Medicine 61 (2003). - ISSN 0167-5877 - p. 263 - 277.
    hog-cholera virus - antibody-response - transmission - disease - herds - diptera - pigs - area
    Data of the 1997-1998 epidemic of classical swine fever (CSF) in The Netherlands were analysed in survival analysis to identify risk factors that were associated with the rate of neighbourhood infections. The study population consisted of herds within 1000 m of exclusively one previously infected herd. Dates of virus introduction into herds were drawn randomly from estimated probability distributions per herd of possible weeks of virus introduction. (To confirm the insensitivity of the results for this random data-selection procedure, the procedure was repeated 9 times (resulting in 10 different datasets).) The dataset had 906 non-infected and 59 infected neighbour herds, which were distributed over 215 different neighbourhoods. Neighbour herds that never became infected were right-censored at the last date of the infectious period of the infected source herd. Neighbour herds that became empty within the infectious period or within the following 21 days due to preventive depopulation or due to the implemented buying-out programme were right-censored 21 days before the moment of becoming empty. This was done as a correction for the time a herd could be infected without being noticed as such. The median time to identified infection of neighbour herds was 2 weeks, whereas the median time to right censoring of non-infected neighbour herds was 3 weeks. The risk factors, radial distance less than or equal to500 m, cattle present on source herd and increasing herd size of the neighbour herd were associated multivariably with the hazard for neighbour herds to become infected. We did not find an association between time down wind and-infection risk for neighbour herds. Radial dispersion of CSFV seemed more important in neighbourhood infections than dispersion along the road on which the infected source herd is situated. The results of this study support the strategy of preventive depopulation in the neighbourhood of an infected herd. Recommendations are presented to adapt the applied control strategy for neighbourhood infections. (C) 2003 Elsevier B.V. All rights reserved.
    Can we predict behaviour in pigs? Searching for consistency in behaviour over time and across situations
    Kooij, E.V. van der; Kuijpers, A.H. ; Schrama, J.W. ; Eerdenburg, F.J.C.M. van; Schouten, W.G.P. ; Tielen, M.J.M. - \ 2002
    Applied Animal Behaviour Science 75 (2002). - ISSN 0168-1591 - p. 293 - 305.
    Individual differences in animal behaviour could elucidate the differences in stress coping style, which have consequences for production, health and welfare. Therefore, individual behavioural differences in pigs and consistency of responses in different test situations were studied. If differences in behaviour reflect coping characteristics, then behaviour in one situation should predict behavioural reactions in other situations and at other times. In this study, a backtest was performed on 315 Great Yorkshire* Dutch Landrace piglets at 3, 10 and 17 days of age. On day 3, groups of approximately 10 piglets per sow were formed, based on escape behaviour in the first backtest (backtest score): high resisting (HR, all scores >3), low resisting (LR, all scores <3), miscellaneous (MISC, various scores between 0 and 10) or original (OR) litters to determine if group composition would influence coping behaviour. In weeks 5–7 and/or 10–12, a human approach test (HAT), a novel object test (NOT), and an open door test (ODT) were performed with all pigs simultaneously, in the home pen. Pearson correlation coefficients were calculated between the test results and a factor analysis was performed. Furthermore, data were analysed on pen level, and within MISC- and OR-pens on animal level, using multivariate linear models. Significant correlations were found between the backtests and between HAT, NOT and ODT. Backtest results on three ages loaded on the same factor, and HAT, NOT and ODT at one age also loaded on one factor. No differences were found in HAT, NOT and ODT for the different pens (HR, LR, MISC and OR). On animal level, animals with higher backtest scores also had higher HAT scores at 5–7 weeks (P<0.05) within the MISC-pens. At 10–12 weeks, no differences were found. This study suggests that there are consistencies in behaviour of pigs over time and across situations, so coping can be regarded as a trait variable. However, since correlations are well below one, we suggest that other factors such as time (development) and (test) situation may also play an important role in determining an individual's behavioural reaction. The absence of correlations between backtest and the group tests is explained by the theory that these different tests measure different aspects of the coping style.
    Administration of acidified drinking water to finishing pigs in order to prevent Salmonella infections
    Wolf, P.J. van der; Schie, F.W. van; Elbers, A.R.W. ; Engel, B. ; Heijden, H. van der; Hunneman, W.A. ; Tielen, M.J.M. - \ 2001
    Veterinary Quarterly 23 (2001). - ISSN 0165-2176 - p. 121 - 125.
    The aim of the study was to test whether acidified drinking water, with two millilitres of an acid mixture per litre, was able to reduce the number of Salmonella infections in finishing pig herds. In each compartment, half of the pens were supplied with acidified water and the other pens served as negative control. In three herds the required dose was not applied to the pigs as a result of various practical problems. In another herd, all pigs remained seronegative throughout the study. Analysis of the remaining three herds showed a large and significant treatment effect in one herd (P<0.001). As a result of the small number of observations and the overall lower seroprevalence in the control groups, the other two herds only showed a statistical trend to a treatment effect (0.10
    A note on the influence of starting position, time and testing and test order on the backtest in pigs
    Erp-Van der Kooij, E. ; Kuipers, A.H. ; Eerdenburg, F.J.C.M. van; Tielen, M.J.M. - \ 2001
    Applied Animal Behaviour Science 73 (2001)4. - ISSN 0168-1591 - p. 263 - 266.
    The backtest determines the coping behaviour of a piglet in a standardised stress situation, which might be a measure for the coping style of that animal. Backtest results are related to other parameters such as immune responses and production. In this study, the backtest was standardised and it was studied if time of testing or the order in which animals were tested influenced backtest results. One hundred and eight-four piglets from 18 sows were tested at 3, 10 and 17 days of age. Before testing, the sow was disturbed to ensure that all piglets were awake. This standardisation of the starting position before testing did not improve the correlations between backtest results in the successive tests. No relations were found between backtest results and time of testing or test order
    Neighbourhood infections of classical swine fever during the 1997-1998 epidemic in The Netherlands
    Crauwels, A.P.P. ; Nielen, M. ; Elbers, A.R.W. ; Stegeman, J.A. ; Tielen, M.J.M. - \ 2001
    In: Proceedings of the 14th annual meeting : Proceedings of the 14th annual meeting: Dutch Society for Veterinary Epidemiology and Economics (VEEC), Wageningen, December 2001 / E.A.M. Graat and K. Frankena. - Wageningen : Wageningen University, 2001. - ISBN 90-6754-656-9 - p. 69 - 76.
    A concept for a decision support system based on practical experiences from a national disease emergency : The Dutch experience
    Crauwels, A.P.P. ; Koning, R. de; Nielen, M. ; Elbers, A.R.W. ; Dijkhuizen, A.A. ; Tielen, M.J.M. - \ 2001
    Acta Veterinaria Scandinavica Suppl. 94 (2001). - ISSN 0044-605X - p. 61 - 69.
    Welfare model to assess housing systems for pregnant sows
    Bracke, M.B.M. ; Metz, J.H.M. ; Spruijt, B.M. - \ 2000
    In: Proceedings of the 10th International Congress on Animal Hygiene, Vol. 1, Animal Health Service, Maastricht (NL), 2-6 July / Tielen, M.J.M., Voets, M.Th., - p. 377 - 380.
    Individuele gedragskarakteristieken van varkens en de relatie met productieresultaten
    Erp-van der Kooij, E. van; Kuypers, A.H. ; Schrama, J.W. ; Ekkel, E.D. ; Tielen, M.J.M. - \ 2000
    Tijdschrift voor Diergeneeskunde 125 (2000). - ISSN 0040-7453 - p. 649 - 652.
    Evaluation of national safeguarding strategies by simulation : case study for IBR
    Vonk Noordegraaf, A. ; Jalvingh, A.W. ; Nielen, M. ; Jong, M.C.M. de; Franken, P. ; Dijkhuizen, A.A. - \ 2000
    In: Proceedings of the Xth congress on animal hygiene : Xth Congress on animal hygiene, Maastricht, 2000 / Tielen, M.J.M., Voets, M.Th., Maastricht : - p. 338 - 341.
    Erratum to "Individual behavioural characteristics in pigs and their impact on production"
    Erp-van, E. van; Kuijpers, A.H. ; Schrama, J.W. ; Ekkel, E.D. ; Tielen, M.J.M. - \ 2000
    Applied Animal Behaviour Science 66 (2000). - ISSN 0168-1591 - p. 165 - 166.
    Individual behavioural characteristics in pigs and their impact on production
    Erp -, E. van; Kuijpers, A.H. ; Schrama, J.W. ; Ekkel, E.D. ; Tielen, M.J.M. - \ 2000
    Applied Animal Behaviour Science 66 (2000)3. - ISSN 0168-1591 - p. 171 - 185.
    Two studies have been carried out in pigs to determine the relation between escape behaviour and production parameters and between escape behaviour and other factors. In the first, 823 piglets were tested with the backtest at 10 and 17 days of age. Production parameters, such as average daily weight gain and lean meat percentage, were recorded. In the second, the backtest was performed on 566 piglets at 3, 10 and 17 days of age. Escape behaviour in the backtest (backtest score) of the mother was known for 364 piglets. Parameters concerning the health of sow and piglets were recorded, as well as the sow's reaction on piglet removal for testing. Relations between production parameters and backtest scores of the animals were calculated, as well as the influence of birth weight, gender (all males were castrated), parents and health parameters on backtest scores. Backtest scores were fairly consistent over successive tests. Males had higher backtest scores than females, and piglets from sows with low backtest scores had low scores themselves. Finally, a higher backtest score gave a higher lean meat percentage and a better carcass grading at slaughter. No relation with daily weight gain was found. It is concluded that there are individual differences between the ways in which pigs cope with a stressful situation, as is measured with the backtest, and that this coping behaviour is consistent. A positive relation exists between backtest scores and lean meat percentage, and a heritability of backtest scores is assumed.
    Check title to add to marked list
    << previous | next >>

    Show 20 50 100 records per page

    Please log in to use this service. Login as Wageningen University & Research user or guest user in upper right hand corner of this page.