公开(公告)号：US07929731B2

公开(公告)日：2011-04-19

申请号：US11574142

申请日：2005-09-17

Applicant: Peter Schimitzek

Inventor： Peter Schimitzek

IPC: G06K9/00 ,  A22C18/00

CPC classification number: A22B5/007

Abstract: A non-invasive method is described for identifying contours with complex structures having an error recognition rate tending towards zero, which method can be used to distinguish and identify features of a slaughtered animal body with respect to each other, said method being utilized on the basis of a characteristic piece in particular to determine, by means of image processing, data for calculating the muscle-meat percentage, the trade classification and the associated trade value and market value, and also to rate the quality of slaughtered animal bodies, taking into account legal requirements.In accordance with the invention, during error recognition of contours of a slaughtered animal body which have complex structures and which are to be distinguished and identified with respect to each other, an operator at a workstation in the form of a PC interacts with the computer and provides sufficient indications relating to the unidentified or incorrectly identified contour to be sought, in that by employing an image reproduction device at least one support point is in each case set in the illustration of an image of the region of interest of the slaughtered animal body in one or several regions, in which data is to be determined from measurements.

Abstract translation: 描述了用于识别具有趋向于零的误差识别率的复杂结构的轮廓的非侵入性方法，该方法可以用于区分和识别屠宰动物身体相对于彼此的特征，所述方法基于 特别是通过图像处理确定计算肌肉百分比，贸易分类和相关贸易价值和市场价值的数据，并考虑到屠宰动物体质量的评估 法律要求。 根据本发明，在具有复杂结构并且要相互区分和识别的屠宰动物身体轮廓的误差识别期间，以PC形式的工作站的操作者与计算机相互作用，并且 通过采用图像再现装置提供与未识别或不正确识别的轮廓有关的充分指示，在每种情况下至少一个支持点设置在屠宰动物身体的感兴趣区域的图像的图示中 一个或几个区域，其中数据将从测量确定。

公开(公告)号：US10285408B2

公开(公告)日：2019-05-14

申请号：US15321876

申请日：2015-07-02

Applicant: CSB-SYSTEM AG

Inventor： Peter Schimitzek

IPC: A22B5/00 ,  G06K9/20 ,  H04N7/18

Abstract: A method to capture data for animals to be slaughtered with an image capture unit that has an image capture range in which a surface of an animal to be slaughtered is captured visually and in which image points on the surface of the animal are captured. The capture unit provides image point data from the image points in transmittable form. An evaluation unit captures the point data and uses the point data to capture markings on the rear surface of the animal. The evaluation unit provides the markings as a storable capture result. Image points on the surface of the animal are captured in the image capture range. The points contain the markings. The capture unit transmits the point data. The evaluation unit captures the image point data. The method makes an association of an identification code for an animal with the point data. The evaluation unit provides the markings as a storable capture result with the code for the animal.

公开(公告)号：US07547247B2

公开(公告)日：2009-06-16

申请号：US10579925

申请日：2004-11-06

Applicant: Peter Schimitzek

Inventor： Peter Schimitzek

IPC: A22C25/00

CPC classification number: A22B5/007 ,  G01N33/12

Abstract: In a method for the non-invasive determination of the grade, trade value, market value and the quality of a slaughtered animal carcass; based on optical image processing; the method fulfills the conditions of the pertinent official regulations and acts and is rapid and cost-effective to implement; results data of weight percentages from single joint yields that have been obtained during the cutting tests of a sufficient number of slaughtered carcasses are correlated with the characteristic measured values and parameters determined from the ham and loin regions of both sides of a slaughtered animal carcass, taking into consideration the total weight, in order to obtain relationship data; during the slaughter operation, a simulation calculation is then carried out using the existing relationship data to estimate the single joint yields, taking into consideration the total weight of the two sides of a slaughtered animal carcass and the characteristic measured values and parameters that have been determined specifically in the ham and loin regions for said carcass.

Abstract translation: 一种用于非侵入式确定屠宰动物屠体的等级，贸易价值，市场价值和质量的方法; 基于光学图像处理; 该方法符合有关官方规定和行为的条件，执行速度快，成本效益好; 在屠宰屠体数量足够数量的切割试验过程中获得的单一关节产量的重量百分比的结果数据与从被屠宰的动物屠体两侧的火腿和腰部区域确定的特征测量值和参数相关， 考虑总重量，以获得关系数据; 在屠宰操作期间，使用现有的关系数据进行模拟计算，以估计单个关节产量，同时考虑到被屠宰的动物屠体的两侧的总重量和已经确定的特征测量值和参数 特别是在用于所述屠体的火腿和腰部区域中。

公开(公告)号：US10420350B2

公开(公告)日：2019-09-24

申请号：US14776847

申请日：2014-03-14

Applicant: CSB-SYSTEM AG

Inventor： Peter Schmitzek

IPC: H04N9/47 ,  H04N7/18 ,  A22B5/00 ,  G01B11/14 ,  G01B11/245 ,  G01B11/22 ,  G01B11/28 ,  H04N9/04 ,  G06T7/50

Abstract: A device for measuring a slaughter animal body object includes an image camera having an image-camera recording region, a depth camera having a depth-camera recording region, and an evaluation unit. The cameras are positioned in relation to one another by a positioning device in such a manner that the camera recording regions of the image camera and of the depth camera overlap in a common camera recording region at least in certain sections. The evaluation unit identifies measurement points in the common camera recording region and determines the distances thereof from one another.

公开(公告)号：US10165782B2

公开(公告)日：2019-01-01

申请号：US15328154

申请日：2015-07-16

Applicant: CSB-SYSTEM AG

Inventor： Peter Schimitzek

IPC: G06K9/00 ,  A22B5/00

Abstract: The invention relates to a device for optically identifying the sex of a slaughter pig with a depth camera that has a depth camera acquisition region in which a genital region of the pig and spatial coordinates of pixels are acquired. The spatial coordinates are provided in a transmittable manner and include a positioning device to position the depth camera relative to the genital region of the pig. The device includes an evaluation unit connected to the depth camera. The spatial coordinates are acquired by the evaluation unit to determine a phenotypic sex of the pig.

公开(公告)号：US08016649B2

公开(公告)日：2011-09-13

申请号：US13000217

申请日：2009-07-15

Applicant: Peter Schimitzek

Inventor： Peter Schimitzek

IPC: A22B7/00

CPC classification number: A22B5/007 ,  A22B7/003

Abstract: A positioning apparatus for animal carcass halves, particularly slaughtered pig halves, arranges a cleaving plane to be aligned in parallel with an imaging plane of a camera. The positioning apparatus includes a rear guide element disposed movably at a level of an upper guide. In a region of an imaging position of a slaughtered pig half, the positioning apparatus includes rollers operating as pressure elements.

Abstract translation: 用于动物尸体半部的定位装置，特别是屠宰的猪半部，将与待照相机的成像平面平行排列的切割平面布置。 定位装置包括可移动地设置在上引导件的水平面处的后引导元件。 在屠宰猪半身的成像位置的区域中，定位装置包括作为压力元件操作的辊。

公开(公告)号：US20080310684A1

公开(公告)日：2008-12-18

申请号：US11574142

申请日：2005-09-17

Applicant: Peter Schimitzek

Inventor： Peter Schimitzek

IPC: G06K9/00

CPC classification number: A22B5/007

Abstract: A non-invasive method is described for identifying contours with complex structures having an error recognition rate tending towards zero, which method can be used to distinguish and identify features of a slaughtered animal body with respect to each other, said method being utilised on the basis of a characteristic piece in particular to determine, by means of image processing, data for calculating the muscle-meat percentage, the trade classification and the associated trade value and market value, and also to rate the quality of slaughtered animal bodies, taking into account legal requirements.In accordance with the invention, during error recognition of contours of a slaughtered animal body which have complex structures and which are to be distinguished and identified with respect to each other, an operator at a workstation in the form of a PC interacts with the computer and provides sufficient indications relating to the unidentified or incorrectly identified contour to be sought, in that by employing an image reproduction device at least one support point is in each case set in the illustration of an image of the region of interest of the slaughtered animal body in one or several regions, in which data is to be determined from measurements.

Abstract translation: 描述了用于识别具有趋向于零的误差识别率的复杂结构的轮廓的非侵入性方法，该方法可用于区分并识别屠宰动物身体相对于彼此的特征，所述方法基于 特别是通过图像处理确定计算肌肉百分比，贸易分类和相关贸易价值和市场价值的数据，并考虑到屠宰动物体质量的评估 法律要求。 根据本发明，在具有复杂结构并且要相互区分和识别的屠宰动物身体轮廓的误差识别期间，以PC形式的工作站的操作者与计算机相互作用，并且 通过采用图像再现装置提供与未识别或不正确识别的轮廓有关的充分指示，在每种情况下至少一个支持点设置在屠宰动物身体的感兴趣区域的图像的图示中 一个或几个区域，其中数据将从测量确定。

公开(公告)号：US10368553B2

公开(公告)日：2019-08-06

申请号：US15507262

申请日：2015-08-12

Applicant: CSB-SYSTEM AG

Inventor： Peter Schimitzek

IPC: A22B5/00 ,  A22B3/00

Abstract: An apparatus for assessing compliance with animal welfare on an animal for slaughter. The apparatus has an image capture unit with a capture region in which a section of a surface of the animal is optically captured and in which pixels are captured. The capture unit provides pixel data in a transmittable manner. The apparatus has an evaluation unit connected to the capture unit to capture the pixel data. A normative model of the animal is stored in the evaluation unit and represents a formation of animal-related features conforming to animal welfare. The evaluation unit relates the pixel data to the model and determines a deviation of the pixel data from the model and provides the deviation as a deviation of the animal from the model in a form that can be output. A method for assessing compliance with animal welfare is carried out on the apparatus.

公开(公告)号：US09977988B2

公开(公告)日：2018-05-22

申请号：US14888849

申请日：2014-04-30

Applicant: CSB-SYSTEM AG

Inventor： Peter Schimitzek

IPC: G06K9/00 ,  G06K9/46 ,  G01B11/24 ,  A22B5/00 ,  G01N33/12 ,  G06K9/62 ,  H04N5/232

CPC classification number: G06K9/4671 ,  A22B5/007 ,  G01B11/24 ,  G01N33/12 ,  G06K9/6267 ,  G06K2209/17 ,  H04N5/23229

Abstract: An apparatus for classifying a food item of organic or irregular structure includes an image capture unit, a data input unit, and a data output unit. An evaluation unit is connected to said image capture unit, to said data input unit and to said data output unit. The image capture unit captures the food item as optical data and provides the optical data in transmittable form for transmission to the evaluation unit. The evaluation unit extracts feature values of the food item from the optical data. The feature values are combined to form a feature value tuple for the food item. The feature value tuple is automatically assignable to a feature value tuple range. The feature value tuple range is formed by one or more feature value tuples. The feature value tuple range is assigned a class. The data input unit is used to perform an assignment of the class to the feature value tuple range.

公开(公告)号：US09786060B2

公开(公告)日：2017-10-10

申请号：US15503457

申请日：2015-08-11

Applicant: CSB-SYSTEM AG

Inventor： Peter Schimitzek

IPC: A22B3/00 ,  G06T7/20 ,  G01S17/89 ,  A61D7/04 ,  A61B5/00 ,  A61B5/11

CPC classification number: G06T7/20 ,  A22B3/00 ,  A61B5/0077 ,  A61B5/1128 ,  A61D7/04 ,  G01S17/89 ,  G06T2207/10028

Abstract: A device for controlling the anesthetization of an animal to be slaughtered. The device includes a stimulation unit via which a stimulation stimulus is given to the animal. The device includes an image capturing unit that has an image capturing range. The image capturing unit is constructed as a 3D-camera. One part of a surface of the animal is optically detected in the image capturing range and range pixels are collected in the area of the surface. The range pixels are provided and transmitted as pixel data. An evaluation unit is connected to the image capturing unit and collects the pixel data provided by the image capturing unit. The evaluation unit determines an active movement of the animal from the detected pixel data and provides and transmits the control result in the event of a determined movement of the animal.