The Experts below are selected from a list of 2598 Experts worldwide ranked by ideXlab platform
Guoping Lian - One of the best experts on this subject based on the ideXlab platform.
-
recognition and localization methods for vision based Fruit Picking robots a review
Frontiers in Plant Science, 2020Co-Authors: Yunchao Tang, Mingyou Chen, Chenglin Wang, Jinhui Li, Guoping LianAbstract:The utilization of machine vision and its associated algorithms improves the efficiency, functionality, intelligence and remote interactivity of harvesting robots in complex agricultural environments. Machine vision and its associated emerging technology promise huge potential in advanced agricultural applications. However, machine vision and its precise positioning still have many technical difficulties, making it difficult for most harvesting robots to achieve true commercial applications. In this paper, this article reports the application and research progress of harvesting robots and vision technology in Fruit Picking. The potential applications of vision and quantitative methods of localization, target recognition, 3D reconstruction and fault tolerance of complex agricultural environment are focused, and fault-tolerant technology designed for utilization with machine vision and robotic systems are also explored. The two main methods used in Fruit recognition and localization are reviewed, including digital image processing technology and deep learning-based algorithms. The future challenges brought about by recognition and localization success rates are identified: target recognition in the presence of illumination changes and occlusion environments; target tracking in dynamic interference-laden environments, 3D target reconstruction and fault tolerance of the vision system for agricultural robots. In the end, several open research problems specific to recognition and localization applications for Fruit harvesting robots are mentioned, and the latest development and future development trends of machine vision are described.
-
recognition and localization methods for vision based Fruit Picking robots a review
Frontiers in Plant Science, 2020Co-Authors: Yunchao Tang, Lufeng Luo, Mingyou Chen, Chenglin Wang, Guoping Lian, Xiangjun ZouAbstract:The utilization of machine vision and its associated algorithms improves the efficiency, functionality, intelligence, and remote interactivity of harvesting robots in complex agricultural environments. Machine vision and its associated emerging technology promise huge potential in advanced agricultural applications. However, machine vision and its precise positioning still have many technical difficulties, making it difficult for most harvesting robots to achieve true commercial applications. This article reports the application and research progress of harvesting robots and vision technology in Fruit Picking. The potential applications of vision and quantitative methods of localization, target recognition, 3D reconstruction, and fault tolerance of complex agricultural environment are focused, and fault-tolerant technology designed for utilization with machine vision and robotic systems are also explored. The two main methods used in Fruit recognition and localization are reviewed, including digital image processing technology and deep learning-based algorithms. The future challenges brought about by recognition and localization success rates are identified: target recognition in the presence of illumination changes and occlusion environments; target tracking in dynamic interference-laden environments, 3D target reconstruction, and fault tolerance of the vision system for agricultural robots. In the end, several open research problems specific to recognition and localization applications for Fruit harvesting robots are mentioned, and the latest development and future development trends of machine vision are described.
Yunchao Tang - One of the best experts on this subject based on the ideXlab platform.
-
recognition and localization methods for vision based Fruit Picking robots a review
Frontiers in Plant Science, 2020Co-Authors: Yunchao Tang, Mingyou Chen, Chenglin Wang, Jinhui Li, Guoping LianAbstract:The utilization of machine vision and its associated algorithms improves the efficiency, functionality, intelligence and remote interactivity of harvesting robots in complex agricultural environments. Machine vision and its associated emerging technology promise huge potential in advanced agricultural applications. However, machine vision and its precise positioning still have many technical difficulties, making it difficult for most harvesting robots to achieve true commercial applications. In this paper, this article reports the application and research progress of harvesting robots and vision technology in Fruit Picking. The potential applications of vision and quantitative methods of localization, target recognition, 3D reconstruction and fault tolerance of complex agricultural environment are focused, and fault-tolerant technology designed for utilization with machine vision and robotic systems are also explored. The two main methods used in Fruit recognition and localization are reviewed, including digital image processing technology and deep learning-based algorithms. The future challenges brought about by recognition and localization success rates are identified: target recognition in the presence of illumination changes and occlusion environments; target tracking in dynamic interference-laden environments, 3D target reconstruction and fault tolerance of the vision system for agricultural robots. In the end, several open research problems specific to recognition and localization applications for Fruit harvesting robots are mentioned, and the latest development and future development trends of machine vision are described.
-
recognition and localization methods for vision based Fruit Picking robots a review
Frontiers in Plant Science, 2020Co-Authors: Yunchao Tang, Lufeng Luo, Mingyou Chen, Chenglin Wang, Guoping Lian, Xiangjun ZouAbstract:The utilization of machine vision and its associated algorithms improves the efficiency, functionality, intelligence, and remote interactivity of harvesting robots in complex agricultural environments. Machine vision and its associated emerging technology promise huge potential in advanced agricultural applications. However, machine vision and its precise positioning still have many technical difficulties, making it difficult for most harvesting robots to achieve true commercial applications. This article reports the application and research progress of harvesting robots and vision technology in Fruit Picking. The potential applications of vision and quantitative methods of localization, target recognition, 3D reconstruction, and fault tolerance of complex agricultural environment are focused, and fault-tolerant technology designed for utilization with machine vision and robotic systems are also explored. The two main methods used in Fruit recognition and localization are reviewed, including digital image processing technology and deep learning-based algorithms. The future challenges brought about by recognition and localization success rates are identified: target recognition in the presence of illumination changes and occlusion environments; target tracking in dynamic interference-laden environments, 3D target reconstruction, and fault tolerance of the vision system for agricultural robots. In the end, several open research problems specific to recognition and localization applications for Fruit harvesting robots are mentioned, and the latest development and future development trends of machine vision are described.
Xiangjun Zou - One of the best experts on this subject based on the ideXlab platform.
-
recognition and localization methods for vision based Fruit Picking robots a review
Frontiers in Plant Science, 2020Co-Authors: Yunchao Tang, Lufeng Luo, Mingyou Chen, Chenglin Wang, Guoping Lian, Xiangjun ZouAbstract:The utilization of machine vision and its associated algorithms improves the efficiency, functionality, intelligence, and remote interactivity of harvesting robots in complex agricultural environments. Machine vision and its associated emerging technology promise huge potential in advanced agricultural applications. However, machine vision and its precise positioning still have many technical difficulties, making it difficult for most harvesting robots to achieve true commercial applications. This article reports the application and research progress of harvesting robots and vision technology in Fruit Picking. The potential applications of vision and quantitative methods of localization, target recognition, 3D reconstruction, and fault tolerance of complex agricultural environment are focused, and fault-tolerant technology designed for utilization with machine vision and robotic systems are also explored. The two main methods used in Fruit recognition and localization are reviewed, including digital image processing technology and deep learning-based algorithms. The future challenges brought about by recognition and localization success rates are identified: target recognition in the presence of illumination changes and occlusion environments; target tracking in dynamic interference-laden environments, 3D target reconstruction, and fault tolerance of the vision system for agricultural robots. In the end, several open research problems specific to recognition and localization applications for Fruit harvesting robots are mentioned, and the latest development and future development trends of machine vision are described.
-
Research progress on visual perception and end-effecter of undamaged operation for Fruit-Picking robot
Hebei University of Science and Technology, 2018Co-Authors: Lufeng Luo, Yuanliang Tan, Xiangjun ZouAbstract:Research and development of Fruit-Picking robot is of great significance for improving harvest efficiency, guaranteeing Fruit quality and reducing labor intensity. However, Picking-robot under the effect of non-structural factors including over lapping, adhesion and occlusion between bunched Fruits may damage the Fruits very easily due to inaccurate target positioning, incorrect clamping-cutting sequence and improper clamping-cutting gesture. The main cause of the damage is that the coupling mechanism between visual cognition and clamping-cutting actuators for undamaged Picking has not been well settled. In order to comb the latest research progress on anti damage operation of Fruit-Picking robot, this paper makes a comprehensive review and analysis on undamaged harvesting from three aspects: the multi-dimensional information of targets by visual perception, such as Picking point, peduncle position, bounding volume of grape for undamaged Fruit-Picking and so on; visual cognition and intelligent anti damage Picking planning of Fruit-Picking robots; anti damage Picking mechanism design and its behavior control. Moreover, the key problems that need to be solved in the future are summarized and prospected. This paper may provide reference and views for further research on the problems of Fruit intelligent undamaged Picking in unstructured environment
-
fault tolerant design of a limited universal Fruit Picking end effector based on vision positioning error
Applied Engineering in Agriculture, 2016Co-Authors: Xiangjun Zou, Lufeng Luo, Chengyu Luo, Juntao Xiong, Hongjun Wang, Yan ChenAbstract:Difficulties lie in the study and application of Fruit-Picking robots. In particular, large random positioning errors can occur due to disturbance, which is difficult to compensate for using control methods. Existing end-effectors cannot conduct fault tolerance for these errors and are not widely applied. Therefore, a limited universal and fault-tolerant end-effector was designed to address binocular vision-positioning errors. The theory underlying the design of the new mechanism was also proposed based on institutions and vision positioning, in which random positioning errors are regarded as systematic “fault errors†of the end-effector, enabling the mechanism to complete operations within the error range. The relationship between the gripper and the cutter was modeled, and a mathematical model of error tolerance was established. Moreover, a new limited universal end-effector was designed. The binocular vision-positioning errors (including original and random positioning errors) were analyzed, and static and dynamic positioning experiments were conducted using a mechanism and a vision-positioning experimental platform based on binocular vision. The maximum positioning errors obtained were 60.1 mm in the z-direction and 17.2 mm in the x-direction, which were within the fault-tolerance range. Moreover, indoor and outdoor Picking experiments were conducted for litchi and citrus using the Picking manipulator based on binocular vision. The Picking success rates were over 84% and 78% in indoor and outdoor tests, respectively. Finally, the favorable fault-tolerant capacity of the end-effector was validated with a comparison experiment that showed that the limited universal Picking manipulator based on binocular vision could achieve litchi and citrus Pickings within an acceptable error range. The results verified the applicability of the fault-tolerant design.
Mahamane Ali - One of the best experts on this subject based on the ideXlab platform.
-
Étude floristique des formations naturelles à Acacia tortilis subsp. raddiana (Savi) Brenan en zone sahélienne du Niger
IAV Hassan II, 2021Co-Authors: Bio Yandou Ismael, Rabiou Habou, Soumana Idrissa, Moussa Mamoudou Boubacar, Mahamane AliAbstract:This study was conducted in the departments of Maine-Sorao and Goudoumaria located in the region of Diffa, in the extreme south-east of Niger. The objective of the study is to analyse the ecological and floristic indicators of natural formations of Acacia tortilis subsp. raddiana (Savi) Brenan. Phytosociological data were collected using the sigmatist method of Braun-Blanquet and the quadrat point method of Daget and Poissonet. A total of 80 plots were delimited. The data collected are related to the coverage of plant species and environmental variables. The spectra of biological and phytogeographic types were calculated. Hierarchical Ascending Classification (AHC), Canonical Defined Analysis (CDA) and Canonical Correspondence Analysis (CCA) were used to determine plant groupings and their ecological and floristic characteristics. The results revealed a total species richness of 61 plant species divided into 25 families and 51 genera. The most represented families are Poaceae (19.7%) and Leguminosae-Mimosoideae (11.5%). The Therophytes are the most represented biological type (59.0%). Paleotropical species is the dominant phytogeographic type (37.7%). The hierarchical ascending classification (CHA) and the Canonical Correspondence Analysis (CCA) made it possible to discriminate three (3) plant groups with A. tortilis. These are the group with A. tortilis and Echinochloa colona (G1) observed in the lowlands; the group with A. tortilis and Alysicarpus ovalifolius (G2) on the dune slopes and the group with A. tortilis and Chloris barbata (G3) on the dune flats. Analysis of diameter class structures shows a dominance of small-diameter individuals in all groups with shape c parameters of the theoretical Weibull distribution greater than 1, suggesting that A. tortilis stands are characterized by a lack of regeneration, the causes of which include Fruit Picking by shepherds and overgrazing. These results reveal the state of degradation and disturbance of steppe vegetation in the study areas. This study constitutes a reference state that can serve as a basis for sustainable management of the ecosystems of these areas, whose main uses are essentially pastoral. Keywords: Acacia tortilis, Biological types, Phytogeographic types, Floristic diversity, NigerLa présente étude a été conduite dans les départements de Maine-Sorao et Goudoumaria situés dans la région de Diffa, à l’extrême sud-est du Niger. L’objectif de l’étude est d’analyser les indicateurs écologique et floristique des formations naturelles à Acacia tortilis subsp. raddiana (Savi) Brenan. Les données phytosociologiques ont été collectées à l’aide de la méthode sigmatiste de Braun-Blanquet et celle de point quadrat de Daget et Poissonet. Au total, 80 placettes ont été délimitées. Les données collectées sont relatives au recouvrement des espèces végétales et les variables environnementales. Les spectres des types biologiques et phytogéographiques ont été calculés. La classification hiérarchique ascendante (CHA), l’Analyse Canonique Detendancée (DCA) et l’Analyse Canonique des Correspondances (CCA) ont été utilisées pour déterminer les groupements végétaux et leurs caractéristiques écologique et floristique. Les résultats ont révélé une richesse spécifique totale de 61 espèces végétales reparties en 25 familles et 51 genres. Les familles les plus représentées sont les Poaceae (19,7%) et les Leguminosae-Mimosoideae (11,5 %). Les Thérophytes constituent le type biologique le plus représenté (59,0%). Les espèces Paléotropicales est le type phytogéographique dominant (37,7%). La classification hiérarchique ascendante (CHA) et l’Analyse Canonique des Correspondances (CCA) ont permis de discriminer trois (3) groupements végétaux à A. tortilis. Il s’agit du groupement à Acacia tortilis et Echinochloa colona (G1) observé dans les bas-fonds ; du groupement à Acacia tortilis et Alysicarpus ovalifolius (G2) sur les versants dunaires et du groupement à Acacia tortilis et Chloris barbata (G3) sur les replats dunaires. L’analyse des structures en classe de diamètres montre une dominance des individus de faible diamètre au niveau de tous les groupements avec des paramètres de forme c de la distribution théorique de Weibull supérieur à 1. Cela suggère que les peuplements de A. tortilis sont caractérisés par un manque de régénération dont les causes sont entre autres le ramassage des Fruits par les bergers et le surpâturage. Ces résultats révèlent l’état de dégradation et de perturbation de végétation steppique des zones d’étude. Cette étude constitue un état de référence pouvant servir de base pour une gestion durable des écosystèmes de ces zones dont les principales utilisations sont essentiellement pastorales. Mots clés: Acacia tortilis, Types biologiques, Types phytogéographiques, Diversité floristique, Nige
-
Étude floristique des formations naturelles à Vachellia tortilis subsp. raddiana en zone sahélienne du Niger
IAV Hassan II, 2021Co-Authors: Bio Ismael, Rabiou Habou, Soumana Idrissa, Moussa Mamoudou Boubacar, Mahamane AliAbstract:This study was conducted in the departments of Maine-Sorao and Goudoumaria located in the region of Diffa, in the extreme south-east of Niger. The objective of the study is to analyse the ecological and floristic indicators of natural formations of Acacia tortilis subsp. raddiana (Savi) Brenan. Phytosociological data were collected using the sigmatist method of Braun-Blanquet and the quadrat point method of Daget and Poissonet. A total of 80 plots were delimited. The data collected are related to the coverage of plant species and environmental variables. The spectra of biological and phytogeographic types were calculated. Hierarchical Ascending Classification (AHC), Canonical Defined Analysis (CDA) and Canonical Correspondence Analysis (CCA) were used to determine plant groupings and their ecological and floristic characteristics. The results revealed a total species richness of 61 plant species divided into 25 families and 51 genera. The most represented families are Poaceae (19.7%) and Leguminosae-Mimosoideae (11.5%). The Therophytes are the most represented biological type (59.0%). Paleotropical species is the dominant phytogeographic type (37.7%). The hierarchical ascending classification (CHA) and the Canonical Correspondence Analysis (CCA) made it possible to discriminate three (3) plant groups with A. tortilis. These are the group with A. tortilis and Echinochloa colona (G1) observed in the lowlands; the group with A. tortilis and Alysicarpus ovalifolius (G2) on the dune slopes and the group with A. tortilis and Chloris barbata (G3) on the dune flats. Analysis of diameter class structures shows a dominance of small-diameter individuals in all groups with shape c parameters of the theoretical Weibull distribution greater than 1, suggesting that A. tortilis stands are characterized by a lack of regeneration, the causes of which include Fruit Picking by shepherds and overgrazing. These results reveal the state of degradation and disturbance of steppe vegetation in the study areas. This study constitutes a reference state that can serve as a basis for sustainable management of the ecosystems of these areas, whose main uses are essentially pastoral. Keywords: Acacia tortilis, Biological types, Phytogeographic types, Floristic diversity, NigerLa présente étude a été conduite dans les départements de Maine-Sorao et Goudoumaria situés dans la région de Diffa, à l’extrême sud-est du Niger. L’objectif de l’étude est d’analyser les indicateurs écologique et floristique des formations naturelles à Acacia tortilis subsp. raddiana (Savi) Brenan. Les données phytosociologiques ont été collectées à l’aide de la méthode sigmatiste de Braun-Blanquet et celle de point quadrat de Daget et Poissonet. Au total, 80 placettes ont été délimitées. Les données collectées sont relatives au recouvrement des espèces végétales et les variables environnementales. Les spectres des types biologiques et phytogéographiques ont été calculés. La classification hiérarchique ascendante (CHA), l’Analyse Canonique Detendancée (DCA) et l’Analyse Canonique des Correspondances (CCA) ont été utilisées pour déterminer les groupements végétaux et leurs caractéristiques écologique et floristique. Les résultats ont révélé une richesse spécifique totale de 61 espèces végétales reparties en 25 familles et 51 genres. Les familles les plus représentées sont les Poaceae (19,7%) et les Leguminosae-Mimosoideae (11,5 %). Les Thérophytes constituent le type biologique le plus représenté (59,0%). Les espèces Paléotropicales est le type phytogéographique dominant (37,7%). La classification hiérarchique ascendante (CHA) et l’Analyse Canonique des Correspondances (CCA) ont permis de discriminer trois (3) groupements végétaux à A. tortilis. Il s’agit du groupement à Acacia tortilis et Echinochloa colona (G1) observé dans les bas-fonds ; du groupement à Acacia tortilis et Alysicarpus ovalifolius (G2) sur les versants dunaires et du groupement à Acacia tortilis et Chloris barbata (G3) sur les replats dunaires. L’analyse des structures en classe de diamètres montre une dominance des individus de faible diamètre au niveau de tous les groupements avec des paramètres de forme c de la distribution théorique de Weibull supérieur à 1. Cela suggère que les peuplements de A. tortilis sont caractérisés par un manque de régénération dont les causes sont entre autres le ramassage des Fruits par les bergers et le surpâturage. Ces résultats révèlent l’état de dégradation et de perturbation de végétation steppique des zones d’étude. Cette étude constitue un état de référence pouvant servir de base pour une gestion durable des écosystèmes de ces zones dont les principales utilisations sont essentiellement pastorales. Mots clés: Acacia tortilis, Types biologiques, Types phytogéographiques, Diversité floristique, Nige
Mingyou Chen - One of the best experts on this subject based on the ideXlab platform.
-
recognition and localization methods for vision based Fruit Picking robots a review
Frontiers in Plant Science, 2020Co-Authors: Yunchao Tang, Mingyou Chen, Chenglin Wang, Jinhui Li, Guoping LianAbstract:The utilization of machine vision and its associated algorithms improves the efficiency, functionality, intelligence and remote interactivity of harvesting robots in complex agricultural environments. Machine vision and its associated emerging technology promise huge potential in advanced agricultural applications. However, machine vision and its precise positioning still have many technical difficulties, making it difficult for most harvesting robots to achieve true commercial applications. In this paper, this article reports the application and research progress of harvesting robots and vision technology in Fruit Picking. The potential applications of vision and quantitative methods of localization, target recognition, 3D reconstruction and fault tolerance of complex agricultural environment are focused, and fault-tolerant technology designed for utilization with machine vision and robotic systems are also explored. The two main methods used in Fruit recognition and localization are reviewed, including digital image processing technology and deep learning-based algorithms. The future challenges brought about by recognition and localization success rates are identified: target recognition in the presence of illumination changes and occlusion environments; target tracking in dynamic interference-laden environments, 3D target reconstruction and fault tolerance of the vision system for agricultural robots. In the end, several open research problems specific to recognition and localization applications for Fruit harvesting robots are mentioned, and the latest development and future development trends of machine vision are described.
-
recognition and localization methods for vision based Fruit Picking robots a review
Frontiers in Plant Science, 2020Co-Authors: Yunchao Tang, Lufeng Luo, Mingyou Chen, Chenglin Wang, Guoping Lian, Xiangjun ZouAbstract:The utilization of machine vision and its associated algorithms improves the efficiency, functionality, intelligence, and remote interactivity of harvesting robots in complex agricultural environments. Machine vision and its associated emerging technology promise huge potential in advanced agricultural applications. However, machine vision and its precise positioning still have many technical difficulties, making it difficult for most harvesting robots to achieve true commercial applications. This article reports the application and research progress of harvesting robots and vision technology in Fruit Picking. The potential applications of vision and quantitative methods of localization, target recognition, 3D reconstruction, and fault tolerance of complex agricultural environment are focused, and fault-tolerant technology designed for utilization with machine vision and robotic systems are also explored. The two main methods used in Fruit recognition and localization are reviewed, including digital image processing technology and deep learning-based algorithms. The future challenges brought about by recognition and localization success rates are identified: target recognition in the presence of illumination changes and occlusion environments; target tracking in dynamic interference-laden environments, 3D target reconstruction, and fault tolerance of the vision system for agricultural robots. In the end, several open research problems specific to recognition and localization applications for Fruit harvesting robots are mentioned, and the latest development and future development trends of machine vision are described.
