公开(公告)号：PL3754543T3

公开(公告)日：2022-08-01

申请号：PL20174784

申请日：2020-05-14

Applicant: BASF SE

Inventor： PICON ARTZAI ,  NACHTMANN MATTHIAS ,  SEITZ MAXIMILIAN ,  MOHNKE PATRICK ,  NAVARRA-MESTRE RAMON ,  JOHANNES ALEXANDER ,  EGGERS TILL ,  ORTIZ BARREDO AMAIA MARIA ,  ALVAREZ-GILA AITOR ,  ECHAZARRA HUGUET JONE

IPC: G06V10/764

公开(公告)号：CA3140489A1

公开(公告)日：2020-11-19

申请号：CA3140489

申请日：2020-05-14

Applicant: BASF SE

Inventor： PICON ARTZAI ,  NACHTMANN MATTHIAS ,  SEITZ MAXIMILIAN ,  MOHNKE PATRICK ,  NAVARRA-MESTRE RAMON ,  JOHANNES ALEXANDER ,  EGGERS TILL ,  ORTIZ BARREDO AMAIA MARIA ,  ALVAREZ-GILA AITOR ,  ECHAZARRA HUGUET JONE

IPC: G06V10/764

Abstract: A computer-implemented method, computer program product and computer system (100) for detecting plant diseases. The system stores a convolutional neural network (120) trained with a multi-crop dataset. The convolutional neural network (120) has an extended topology comprising an image branch (121) based on a classification convolutional neural network for classifying the input images according to plant disease specific features, a crop identification branch (122) for adding plant species information, and a branch integrator for integrating the plant species information with each input image. The plant species information (20) specifies the crop on the respective input image (10). The system receives a test input comprising an image (10) of a particular crop (1) showing one or more particular plant disease symptoms, and further receives a respective crop identifier (20) associated with the test input via an interface (110). A classifier module (130) of the system applies the trained convolutional network (120) to the received test input, and provides a classification result (CR1) according to the output vector of the convolutional neural network (120). The classification result (CR1) indicates the one or more plant diseases associated with the one or more particular plant disease symptoms.

公开(公告)号：BR112021022829A2

公开(公告)日：2021-12-28

申请号：BR112021022829

申请日：2020-05-14

Applicant: BASF SE

Inventor： ALVAREZ-GILA AITOR ,  JOHANNES ALEXANDER ,  AMAIA MARIA ORTIZ BARREDO ,  PICON ARTZAI ,  JONE ECHAZARRA HUGUET ,  NACHTMANN MATTHIAS ,  SEITZ MAXIMILIAN ,  MOHNKE PATRICK ,  NAVARRA-MESTRE RAMON ,  EGGERS TILL

IPC: G06K9/00 ,  G06K9/62

Abstract: método implementado por computador, produto de programa de computador e sistema de computador. um método implementado por computador, produto de programa de computador e sistema de computador (100) para detectar doenças em plantas. o sistema armazena uma rede neural convolucional (120) treinada com um conjunto de dados de múltiplas colheitas. a rede neural convolucional (120) tem uma topologia estendida que compreende uma ramificação de imagem (121) com base em uma rede neural convolucional de classificação para classificar as imagens de entrada de acordo com características específicas de doenças de plantas, uma ramificação de identificação de colheita (122) para adicionar informação de espécies de plantas, e um integrador de ramificação para integrar a informação das espécies de plantas com cada imagem de entrada. a informação das espécies de plantas (20) especifica a colheita na respectiva imagem de entrada (10). o sistema recebe uma entrada de teste que compreende uma imagem (10) de uma colheita específica (1) mostrando um ou mais sintomas de doenças de plantas particulares e recebe ainda um identificador de colheita respectivo (20) associado à entrada de teste por meio de uma interface (110). um módulo classificador (130) do sistema aplica a rede convolucional treinada (120) à entrada de teste recebida e fornece um resultado de classificação (cr1) de acordo com o vetor de saída da rede neural convolucional (120). o resultado de classificação (cr1) indica uma ou mais doenças de plantas associadas a um ou mais sintomas específicos de doenças de plantas.

公开(公告)号：AU2017264371A1

公开(公告)日：2018-11-01

申请号：AU2017264371

申请日：2017-04-19

Applicant: BASF SE

Inventor： ALEXANDER JOHANNES ,  EGGERS TILL ,  PICON ARTZAI ,  ALVAREZ-GILA AITOR ,  ORTIZ BARREDO AMAYA MARIA ,  DÍEZ-NAVAJAS ANA MARÍA

IPC: G06K9/00

Abstract: A system (100), method and computer program product for determining plant diseases. The system includes an interface module (110) configured to receive an image (10) of a plant, the image (10) including a visual representation (11)of at least one plant element (1). A color normalization module (120) is configured to apply a color constancy method to the received image (10) to generate a color-normalized image. An extractor module (130) is configured to extract one or more image portions (11e) from the color-normalized image wherein the extracted image portions (11e) correspond to the at least one plant element (1). A filtering module (140) configured: to identify one or more clusters (C1 to Cn) by one or more visual features within the extracted image portions (11e) wherein each cluster is associated with a plant element portion showing characteristics of a plant disease; and to filter one or more candidate regions from the identified one or more clusters (C1 to Cn) according to a predefined threshold, by using a Bayes classifier that models visual feature statistics which are always present on a diseased plant image. A plant disease diagnosis module (150) configured to extract, by using a statistical inference method, from each candidate region (C4, C5, C6, Cn) one or more visual features to determine for each candidate region one or more probabilities indicating a particular disease; and to compute a confidence score (CS1) for the particular disease by evaluating all determined probabilities of the candidate regions (C4, C5, C6, Cn).

公开(公告)号：CA3021795A1

公开(公告)日：2017-11-16

申请号：CA3021795

申请日：2017-04-19

Applicant: BASF SE

Inventor： ALEXANDER JOHANNES ,  EGGERS TILL ,  PICON ARTZAI ,  ALVAREZ-GILA AITOR ,  ORTIZ BARREDO AMAYA MARIA ,  DIEZ-NAVAJAS ANA MARIA

IPC: G06K9/00

Abstract: A system (100), method and computer program product for determining plant diseases. The system includes an interface module (110) configured to receive an image (10) of a plant, the image (10) including a visual representation (11)of at least one plant element (1). A color normalization module (120) is configured to apply a color constancy method to the received image (10) to generate a color-normalized image. An extractor module (130) is configured to extract one or more image portions (11e) from the color-normalized image wherein the extracted image portions (11e) correspond to the at least one plant element (1). A filtering module (140) configured: to identify one or more clusters (C1 to Cn) by one or more visual features within the extracted image portions (11e) wherein each cluster is associated with a plant element portion showing characteristics of a plant disease; and to filter one or more candidate regions from the identified one or more clusters (C1 to Cn) according to a predefined threshold, by using a Bayes classifier that models visual feature statistics which are always present on a diseased plant image. A plant disease diagnosis module (150) configured to extract, by using a statistical inference method, from each candidate region (C4, C5, C6, Cn) one or more visual features to determine for each candidate region one or more probabilities indicating a particular disease; and to compute a confidence score (CS1) for the particular disease by evaluating all determined probabilities of the candidate regions (C4, C5, C6, Cn).