Abstract: Method for domain-specific person detection, wherein a monitoring area (1) is monitored by means of one or a plurality of cameras (2a, b, c, d), wherein the cameras (2a, b, c, d) each provide image data for a respective monitoring area section (3a, b, c, d), wherein a person detector can be operated in a detection mode and in an adaptation mode, wherein the person detector has a machine learning algorithm based on an original model for analyzing the image data and for detecting persons in the monitoring area (1), wherein, for the adaptation mode, the monitoring area (1) is temporarily restricted to a limited monitoring area (4), wherein the image data from the limited monitoring area (4) are recorded, wherein, based on the image data of the limited monitoring area (4), a domain adaptation of the original model to an application model takes place, wherein, in the detection mode, the machine learning algorithm adapted to the application model is used for analysis of the image data, for person detection and/or f

Abstract: A surveillance system having an interface to a camera network for video surveillance of a surveillance area. The camera network includes a plurality of cameras each for capturing a surveillance subarea. The cameras are designed to provide surveillance images of the surveillance subareas. The surveillance system also includes a surveillance device for re-identifying people in the surveillance images. The surveillance device includes a person detection module for detecting people and an object detection module 10 for detecting objects. The surveillance device 5 includes an assignment module 12 designed to assign at least one item of object information to a person 4, and an action detection module 11 designed to detect an action of the person 4 on one of the objects 8.

Abstract: A method for generating a monitoring image. The method includes: providing an image sequence of the surroundings to be monitored with the aid of an imaging system; determining at least one monitoring area and at least one periphery area of at least one image of the image sequence with the aid of a learning-based semantic segmentation method; compressing the monitoring area of the at least one image of the image sequence with a first compression quality; and compressing the periphery area of the at least one image of the image sequence with a second compression quality to generate the compressed monitoring image, the second compression quality being lower than the first compression quality.

Abstract: The invention relates to a monitoring device (10) for recognizing persons in a monitoring region (2), the monitoring region (2) being video-monitored by means of at least one camera (6) and the camera (6) being designed to provide monitoring images (7) to the monitoring device (10) as video data, the monitoring device comprising: —a feature determination apparatus (13), the feature determination apparatus (13) being designed to determine a feature vector (19) for each object in at least one of the monitoring images (7); —a person recognition apparatus (16), the person recognition apparatus (16) being designed to detect in the monitoring images (7) a person to be recognized (11), on the basis of the determined feature vector and/or the determined feature vectors (19) of the feature determination apparatus (13) and/or a combined feature vector (18); —an association apparatus (14), the association apparatus (14) being designed to determine a feature vector (19) for each person to be recognized (11) and each asso

Abstract: A method for operating a control unit on which multiple applications are executed. The method includes: using a reference stored permanently in the control unit, obtaining a first code block of a first application; using verification information stored permanently in the control unit, checking whether the first code block is in a version corresponding to the verification information; in response to the result of the check being positive, approving the program code in the first code block for execution; using a reference in the first code block, obtaining a transfer block which contains a reference to a further code block of a further application; using verification information stored in the first code block, checking whether the transfer block is in a version corresponding to the verification information; in response to the result of the check being positive, obtaining the further code block using the reference in the transfer block.

Abstract: A monitoring system 1 is proposed, having a camera network 3 for the video-based monitoring of a monitoring region 2, wherein the camera network 3 comprises a plurality of cameras 3a, b for recording a partial monitoring region 2a, b of the monitoring region 2 in each case, wherein the plurality of cameras 2a, b are configured to provide monitoring images 6a, b of the partial monitoring regions 2a, b, having at least one sensor device 7a, b for detecting at least one person-related object information item, having a monitoring device 5 for recognizing persons 4 in the monitoring images 6a, b, wherein the monitoring device 5 comprises a person detection module 10, the person detection module 10 being configured to detect persons 4 in the monitoring images 6a, b, wherein the monitoring device 5 comprises an assignment module 11, the assignment module 11 being configured to assign an item of person-related object information from a partial monitoring region 7a, b to a person 4 in the same partial monitoring regio

Abstract: The invention relates to a method for determining a noteworthy sub-sequence (114a) of a monitoring image sequence (110) of a monitoring area comprising the following steps: providing an audio signal (S1) from the monitoring area, at least partially including a time period of the monitoring image sequence; providing the monitoring image sequence (S1) of the environment to be monitored, which has been generated by an imaging system; determining at least one segment of the audio signal from the provided audio signal, which has unusual noises (S2); determining at least one segment of the monitoring image sequence having unusual movements within the environment to be monitored (S3); determining a correlation between the at least one segment of the audio signal having unusual noises (114a) and the at least one segment of the monitoring image sequence with unusual movements (114a) in order to determine a noteworthy sub-sequence (114) of the monitoring image sequence (110).

Abstract: A method for determining video segments to be transferred of a video, which is recorded in a vehicle using a camera. The method including, for one or for each of multiple video segments of the videos recorded in the vehicle, analyzing the one or one of each of the multiple video segments with respect to its respective content, generating data, which include pieces of information relating to the respective content of a respective video segment, conveying the data to an extra-vehicular processing system, receiving pieces of information about one or about multiple video segments to be transferred from the extra-vehicular processing system and transferring the one or the multiple video segments to be transferred to the extra-vehicular processing system. A method carried out in the processing system, a camera system, and a processing system are also described.

Abstract: An anonymization apparatus 6 is proposed for the generation of anonymized images 9, wherein surveillance images 5 are provided through video surveillance of a surveillance region 3 by means of at least one camera 2, with a recognition module 11, wherein the surveillance images 5 are provided to the recognition module 11, wherein the recognition module 11 is configured to recognize persons 4 contained in the surveillance images 5, with a processing module 13, wherein the processing module 13 is configured to process the surveillance images 5 into the anonymized images 9, wherein at least one person 4 or person segment included in the surveillance images 5 is anonymized in the anonymized images 9, wherein the processing module 13 is configured to replace the recognized person 4 or person segment by an animated person model 14 for the purpose of anonymization.

Abstract: Person recognition device for person re-identification in a monitoring region, having a camera apparatus and an evaluation module, wherein the camera apparatus comprises a first camera unit and a second camera unit, wherein the first camera unit is configured to record a first monitoring image of a portion of the monitoring region, wherein the second camera unit is configured to record a second monitoring image of the portion of the monitoring region, wherein the camera apparatus is configured to feed the first monitoring image and the second monitoring image to the evaluation module, wherein the evaluation module is configured to re-identify a person in the monitoring region based on the first monitoring image and the second monitoring image, wherein the second camera unit has a cut-off filter for wavelength cutting of incident light in a stop band.

Abstract: The invention relates to a monitoring device (10) for recognizing persons in a monitoring region (2), the monitoring region (2) being video-monitored by means of at least one camera (6) and the camera (6) being designed to provide monitoring images (7) to the monitoring device (10) as video data, the monitoring device comprising: —a feature determination apparatus (13), the feature determination apparatus (13) being designed to determine a feature vector (19) for each object in at least one of the monitoring images (7); —a person recognition apparatus (16), the person recognition apparatus (16) being designed to detect in the monitoring images (7) a person to be recognized (11), on the basis of the determined feature vector and/or the determined feature vectors (19) of the feature determination apparatus (13) and/or a combined feature vector (18); —an association apparatus (14), the association apparatus (14) being designed to determine a feature vector (19) for each person to be recognized (11) and each asso

Abstract: A method for generating a monitoring image. The method includes: providing an image sequence of the surroundings to be monitored with the aid of an imaging system; determining at least one monitoring area and at least one periphery area of at least one image of the image sequence with the aid of a learning-based semantic segmentation method; compressing the monitoring area of the at least one image of the image sequence with a first compression quality; and compressing the periphery area of the at least one image of the image sequence with a second compression quality to generate the compressed monitoring image, the second compression quality being lower than the first compression quality.

Abstract: A surveillance system having an interface to a camera network for video surveillance of a surveillance area. The camera network includes a plurality of cameras each for capturing a surveillance subarea. The cameras are designed to provide surveillance images of the surveillance subareas. The surveillance system also includes a surveillance device for re-identifying people in the surveillance images. The surveillance device includes a person detection module for detecting people and an object detection module 10 for detecting objects. The surveillance device 5 includes an assignment module 12 designed to assign at least one item of object information to a person 4, and an action detection module 11 designed to detect an action of the person 4 on one of the objects 8.

Abstract: An anonymization apparatus 6 is proposed for the generation of anonymized images 9, wherein surveillance images 5 are provided through video surveillance of a surveillance region 3 by means of at least one camera 2, with a recognition module 11, wherein the surveillance images 5 are provided to the recognition module 11, wherein the recognition module 11 is configured to recognize persons 4 contained in the surveillance images 5, with a processing module 13, wherein the processing module 13 is configured to process the surveillance images 5 into the anonymized images 9, wherein at least one person 4 or person segment included in the surveillance images 5 is anonymized in the anonymized images 9, wherein the processing module 13 is configured to replace the recognized person 4 or person segment by an animated person model 14 for the purpose of anonymization.

Abstract: A monitoring system 1 is proposed, having a camera network 3 for the video-based monitoring of a monitoring region 2, wherein the camera network 3 comprises a plurality of cameras 3a, b for recording a partial monitoring region 2a, b of the monitoring region 2 in each case, wherein the plurality of cameras 2a, b are configured to provide monitoring images 6a, b of the partial monitoring regions 2a, b, having at least one sensor device 7a, b for detecting at least one person-related object information item, having a monitoring device 5 for recognizing persons 4 in the monitoring images 6a, b, wherein the monitoring device 5 comprises a person detection module 10, the person detection module 10 being configured to detect persons 4 in the monitoring images 6a, b, wherein the monitoring device 5 comprises an assignment module 11, the assignment module 11 being configured to assign an item of person-related object information from a partial monitoring region 7a, b to a person 4 in the same partial monitoring regio

Abstract: A method for training a person recognition model using images from a camera 100, wherein the method has at least a reading-in step in which a detection signal 135 representing a detected person within a monitoring area of at least the camera 100 in a camera network is read in. The method also has at least a collecting step in which a plurality of image signals 140 from the camera 100 are collected using the detection signal 135 which has been read in, wherein the collected image signals 140 represent a recorded image section from each image from the camera 100. Finally, the method has at least an adapting step in which the person recognition model is adapted using the collected image signals 140 in order to recognize the detected person in an image from the camera 100 or from an at least second camera in the camera network.

Abstract: A method for passenger recognition by an autonomous vehicle in which a photograph of the person to be transported is transmitted to a central server, an approximate position of the person to be transported is determined, the autonomous vehicle is brought close to the previously determined position, a precise position of the person to be transported is ascertained by sensor equipment internal to the vehicle on the basis of color and texture features and/or on the basis of a way of walking, the identity of the ascertained person to be transported is verified by a facial recognition system, and the autonomous vehicle is positioned in a boarding area of the person to be transported.

Abstract: Monitoring apparatus 2 for person recognition in a monitoring region 7, having at least one camera 3 for recording an image sequence of a portion 10 of the monitoring region 7, wherein the image sequence comprises a plurality of monitoring images, having a person recognition module 6, wherein the person recognition module 6 has at least one recognition feature of a person that is to be located and is configured to search for the person to be recognized based on the monitoring images and the recognition feature, wherein the camera 3 has a fisheye lens 4.

Abstract: A method for setting a camera, in particular of a monitoring device, comprising a recording of an image of a region to be monitored, an analysis of the recorded image to associate at least one image region of the image with an object, identification of the object on the basis of the acquired image region and ascertainment of a size of the object by access to stored size information of the identified object and a scaling of the image region associated with the object in the recorded image to scale the remaining acquired image and/or to determine a distance of the camera to the acquired object.

Abstract: A method for object identification is described, the method initially including a step of reading in, in which input data signals, as well as a determined camera control parameter for adjusting a recording feature of a camera are read in. The input data signals in this case represent the images of the object to be identified that are recorded by at least one camera. Finally, the method includes a step of identification, in which the object is identified in a neural network using the determined camera control parameter.