公开(公告)号：US20240112468A1

公开(公告)日：2024-04-04

申请号：US18476109

申请日：2023-09-27

Applicant: MILESTONE SYSTEMS A/S

Inventor： Zenjie LI ,  Kamal NASROLLAHI

IPC: G06V20/52 ,  G06T7/70 ,  G06V10/25 ,  G06V10/764 ,  G06V20/40

CPC classification number: G06V20/52 ,  G06T7/70 ,  G06V10/25 ,  G06V10/764 ,  G06V20/44 ,  G06V2201/07

Abstract: A computer implemented method for identifying an event by processing video surveillance data from a video camera having a field of view uses a trained machine learning algorithm to detect a person in the video surveillance data and determine the location of the person in the field of view. A trained machine learning algorithm is used to classify a posture of the detected person and a detection zone within the field of view around the location of the detected person is defined. A trained machine learning algorithm is used to search for an object of a predetermined type overlapping the detection zone. An event is identified based on the posture detection and the result of the object detection.

公开(公告)号：US20240303783A1

公开(公告)日：2024-09-12

申请号：US18595002

申请日：2024-03-04

Applicant: MILESTONE SYSTEMS A/S

Inventor： Andreas AAKERBERG ,  Kamal NASROLLAHI ,  Thomas B. MOESLUND

IPC: G06T5/70 ,  G06N3/0464

CPC classification number: G06T5/70 ,  G06N3/0464 ,  G06T2207/20081

Abstract: Training a neural network to extract a degradation map from a degraded image comprises generating training data comprising pairs of images, each pair of images comprising a clean source image and a degraded source image by, for each clean source image, generating a corresponding noisy image by adding spatially invariant noise to the clean source image, and blending the noisy image with the clean source image according to varying intensity levels defined by a spatially variant mask to obtain the degraded image. The training data is used to train the neural network by inputting each degraded source image to the neural network and extracting a degradation map from the degraded source image such that when the degradation map is applied to its corresponding clean source image the loss between the degraded source image and its corresponding clean source image after the degradation map is applied is minimised.

公开(公告)号：US20230055581A1

公开(公告)日：2023-02-23

申请号：US17498537

申请日：2021-10-11

Applicant: Milestone Systems A/S

Inventor： Michael BIDSTRUP ,  Jacob Velling DUEHOLM ,  Kamal NASROLLAHI

IPC: G06K9/00 ,  G06T7/11 ,  H04N7/18 ,  G06T7/12 ,  H04N5/272 ,  G06K9/36 ,  G06F21/62 ,  G06N3/04

Abstract: A computer implemented method of anonymising video surveillance data of a scene and detecting an object or event of interest in such anonymised video surveillance data, the method comprising segmenting frames of video surveillance data of at least one scene into corresponding frames of segmented data using image segmentation, wherein a mask label is assigned to every pixel of each frame of the segmented data based either on a class of objects or of surfaces or on an instance of such a class that pixel belongs to, and detecting at least one object and/or event of interest based on at least one shape and/or motion in at least one frame of the segmented data.

公开(公告)号：US20230325974A1

公开(公告)日：2023-10-12

申请号：US18069089

申请日：2022-12-20

Applicant: MILESTONE SYSTEMS A/S

Inventor： Kamal NASROLLAHI ,  Thomas B MOESLUND ,  Andreas AAKERBERG

IPC: G06T3/40

CPC classification number: G06T3/4046 ,  G06T3/4053

Abstract: An image processing method including acquiring a first image whose spatial resolution and lightness are to be enhanced; generating a residual image from the first image using a multi-scale hierarchical neural network for joint learning of low-light enhancement and super-resolution, the network comprising an encoder stage and a decoder stage forming a plurality of symmetrical encoder-decoder levels, each encoder and decoder in each level comprising a vision transformer block; generating a reconstructed image based on the first and residual images.

公开(公告)号：US20230008356A1

公开(公告)日：2023-01-12

申请号：US17839283

申请日：2022-06-13

Applicant: MILESTONE SYSTEMS A/S

Inventor： Kamal NASROLLAHI ,  Zenjie LI ,  Carlos FERNANDEZ DE TEJADA QUEMADA

IPC: G06V10/98 ,  G06V20/52 ,  G06F16/783 ,  G06V10/25

Abstract: A video processing apparatus configured to process a stream of video surveillance data, wherein the video surveillance data includes metadata associated with video data, the metadata describing at least one object in the video data. The apparatus comprises means for applying an image assessment algorithm to generate a reliability score for the metadata, and associating the reliability score with the metadata. The image assessment algorithm generates the reliability score based on an assessment of the image quality of the video data to which the metadata relates to indicate a likelihood that the metadata accurately describes the object. An image enhancement module applies image enhancement to video data if the reliability score of metadata associated with the video data indicates a low likelihood that the metadata accurately describes the object.

公开(公告)号：US20240119737A1

公开(公告)日：2024-04-11

申请号：US18483191

申请日：2023-10-09

Applicant: MILESTONE SYSTEMS A/S

Inventor： Zenjie LI ,  Kamal NASROLLAHI

IPC: G06V20/52 ,  G06N5/02 ,  G06V20/40

CPC classification number: G06V20/52 ,  G06N5/02 ,  G06V20/44 ,  G06V2201/07

Abstract: A computer-implemented method of video surveillance comprising the steps of: querying a knowledge graph representing a plurality of video cameras as ontology entities connected by edges, in order to identify, based on a first video camera providing a first video stream that can be fed to at least one first application program to obtain first analytics data, one or more second video cameras which can each provide a respective second video stream; and identifying, based on the first application program and/or based on the first analytics data, at least one second application program that can be fed with at least one second video stream to obtain second analytics data.

公开(公告)号：US20230081908A1

公开(公告)日：2023-03-16

申请号：US17929995

申请日：2022-09-06

Applicant: MILESTONE SYSTEMS A/S

Inventor： Kamal NASROLLAHI

IPC: G06V20/52 ,  G06V10/774 ,  G06T7/194 ,  G06T7/70 ,  G06T17/00 ,  G06N20/00

Abstract: A method of training a machine learning algorithm to identify objects or activities in video surveillance data comprises generating a 3D simulation of a real environment from video surveillance data captured by at least one video surveillance camera installed in the real environment. Objects or activities are synthesized within the simulated 3D environment and the synthesized objects or activities within the simulated 3D environment are used as training data to train the machine learning algorithm to identify objects or activities, wherein the synthesized objects or activities within the simulated 3D environment used as training data are all viewed from the same viewpoint in the simulated 3D environment.