Telefonaktiebolaget Lm Ericsson (publ)

Alfredo Fanghella

Manish Sonal

Volodya Grancharov

Sigurdur Sverrisson

José Araújo

Harald Pobloth

A method performed by an image registration entity includes obtaining a matching between a first set of objects in a first image of a scene and a second set of objects in a second image of the scene, and obtaining a first set of key-points from the first image and a second set of key-points from the second image. Image registration is performed by matching the first set of key-points to the second set of key-points. Those of the first set of key-points that are mapped to objects in the first set of objects and that have matching objects in the second set of objects are restricted to only be matched to those of the second set of key-points that are mapped to any of the matching objects in the second set of objects. The matching between key-points resulting from the image registration is applied when constructing an image representation of the scene.

Image registration based on key-point matching

There is provided mechanisms for visual object detection in a sequence of images. A method is performed by a visual object detector (). The method comprises obtaining (S) a sequence of images of a scene. The sequence of images at least comprises a current image of the scene and a previous image of the scene. The method comprises extracting (S) a set of objects from the sequence of images by performing visual object detection in the sequence of images. Performing the visual object detection in at least part of the current image is conditioned on a set of conditions being fulfilled. The set of conditions at least pertains to an image-wise descriptor classification score computed for at least one of the previous image and the current image and pertaining to which type of content the scene comprises, and an image overlapping score pertaining to how much overlap in image area there is between the previous image and the current image. The method comprises constructing (S) an image representation of the scene using the extracted set of objects.

Visual object detection in a sequence of images

There is provided mechanisms for joint visual object detection and object mapping to a 3D model. A method is performed by an image processing device. The method includes obtaining a first sequence of digital images of a scene as captured by a first image capturing unit, and obtaining a second sequence of digital images of the scene as captured by a second image capturing unit. The second sequence of digital images is time-wise synchronized with the first sequence of digital images by being captured time-wise in parallel with the first sequence of digital images. The first image capturing unit has a narrower field of view than the field of view of the second image capturing unit. The first image capturing unit and the second image capturing unit have a known spatial relation. The method includes performing joint visual object detection and object mapping to the 3D model.

Joint visual object detection and object mapping to a 3D model

Object parts () are detected in a picture using object detector(s) () and part location representations () are generated for the detected object parts (). The size of an object () comprising object parts () is estimated based on a geometric model and the part location representations (). Search locations () in the picture for a search window () having a size based on the estimated size are determined based on the part location representations (). The search locations () are then processed by identifying any detected object part () that is within the search window () positioned at the search location (). A homography is estimated by minimizing an error between mapped object part(s) from the geometric model and the identified detected object part(s) (). If the error is smaller than a threshold value, an object location representation is determined for the object ().

Object location determination

An object locating method comprises deciding, for at least one frame of a video stream and based on at least one parameter representative of a change between a scene represented by the at least one frame and a scene represented by a reference frame of the video stream, whether determination of a location of at least one object () in the at least one frame is based on object detection applied to the at least one frame, or is based on a transformation of a location of the at least one object () detected in the reference frame.

Object location determination in frames of a video stream

A method for detecting a change in an area of interest. The method includes: 1) forming a pointcloud that comprises: i) a first set of points derived from a first set of one or more images and ii) a second set of points derived from a second set of one or more images; 2) for each point included in the pointcloud, assigning a similarity score to the point; 3) for at least each point from the pointcloud that is included in a particular set of points (e.g., for each point in the pointcloud that is assigned a similarity score that exceeds a threshold (e.g. 0)), determining a value Nt and a value Nnew and adjusting the similarity score assigned to the point based on Nt and Nnew; and 4) using the adjusted similarity scores to determine whether the area of interest has changed.

Growing community of inventors

Stockholm, Sweden

Alfredo Fanghella