Axis Patente

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

In a method for tracking an object in video-monitoring scenes, multiple feature vectors are extracted (722) and assembled (724) in point clouds, wherein a point cloud may be assembled for each tracklet, i.e. for each separate part of a track. In order to determine if different tracklets relate to the same or different objects the point clouds of each tracklet is compared (734). Based on the outcome of the comparison it is deduced if the first object and the second object may be considered to be the same object and, if so, the first object is associated (738) with the second object.

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

The present disclosure relates to a system for action recognition in a video sequence. The system comprises a camera (100) configured to capture the video sequence and a server (200) configured to perform action recognition. The camera comprises an object identifier (124) configured to identify an object of interest in an object image frame of the video sequence; an action candidate recognizer (126) configured to apply a first action recognition algorithm to the object image frame and thereby detecting presence of an action candidate; an video extractor (127) configured to produce action image frames of an action video sequence by extracting video data pertaining to a plurality of image frames from the video sequence, wherein one or more of the plurality of image frames from which the video data is extracted comprises the object of interest; and a network interface (130) configured to transfer the action video sequence to the server. The server comprises an action verifier (210) configured to apply a second action recognition algorithm to the action video sequence and thereby verify or reject that the action candidate is an action. Also a method for action recognition in a video sequence is presented.

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

The present invention relates to a method, device and system for generating a transformation function, mapping position detections of objects in a scene, detected with a positioning device, to a graphical representation of the scene. The invention enables the detected positions by the positioning device to be mapped to the graphical representation of the monitored scene without the need of previous references to geographical coordinate systems for the positioning device and the graphical representation of the scene. Virtually any type of image may hence be used as a graphical representation of the scene, even hand-drawn sketches.

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

A monitoring camera having a compound window arranged in a frame of a camera housing, and a camera head arranged inside the housing, is disclosed. The compound window has an inner translucent plate, closest to the camera head, and an outer protective window, arranged in a plane parallel to the translucent plate, on an outside thereof, and the compound window further comprises a heating arrangement arranged and configured to supply thermal energy to peripheral areas of the translucent plate. The translucent plate has a greater heat conductivity than the protective window and is arranged in close proximity to the protective window, so thermal energy will be transferred from the heating arrangement to the translucent plate and then efficiently transferred to the protective window.

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

The present inventive concept relates to a tiltable system (10) for panoramic imaging of a scene. The tiltable system (10) comprising: a central camera (110), a first and a second lateral camera (120, 130) arranged to image the scene in different directions (112, 122, 132) relative to a rotation axis (102), wherein the first and the second lateral camera (120, 130) are arranged on opposing lateral sides of the central camera (110), wherein the central camera (110), the first lateral camera (120), and the second lateral camera (130) each having an imaging system comprising a lens assembly (114, 124, 134) and an image sensor (116, 126, 136); a tilting mechanism (140) enabling the tiltable system (10) for panoramic imaging to tilt about the rotation axis (102); and an image processing unit (150) comprising a stitching function (152) configured to stitch together images (310, 320, 330) captured by the central camera (110), the first lateral camera (120), and the second lateral camera (130) to form a panoramic image of the scene, the panoramic image having a virtual horizon, and to, upon tilting of the tiltable system (10) for panoramic imaging, maintain the position of the virtual horizon of the panoramic image in the scene; wherein the imaging systems of the first and second lateral cameras (120, 130) have a larger field of view (204) in a direction (104) perpendicular to the rotation axis (102) than the imaging system of the central camera (110).

There is provided a method and a controller for controlling a video processing unit to facilitate detection of newcomers in a first environment. The method comprises: capturing a thermal image of a human object in the first environment, the first environment being associated with a first climate; calculating, based on the thermal image, a thermal signature of a portion of the human object; determining that the human object has entered the first environment from a second environment when the thermal signature of the portion of the human object deviates from a predetermined thermal signature associated with the first environment, wherein the second environment is associated with a second, different, climate; and controlling the video processing unit to prioritize the human object over other human objects when processing video frames depicting the human object together with the other human objects.

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

A method (1300) and a system (1000) for filtering thermal image data is provided. The method (1300) comprises: capturing (1302) thermal image data by a thermal image detector (1110); forming (1304) a signal distribution of intensity values; identifying (1306) a first part (220) in the signal distribution of intensity values, the first part being a peak having an intensity width (222) equal to or smaller than a predetermined intensity span being based on a resolution parameter of the thermal image detector; identifying (1307) a second part (210) having an intensity width larger than the predetermined intensity span; determining (1308) an intensity range between the first part and the second part; and filtering (1310), if the intensity range is larger than a predetermined minimum intensity range, the thermal image data by excluding thermal image data forming part of the first part.

The present invention relates to video encoding using periodic intra refresh, and specifically to a method and an encoder which can adapt padding of an intra encoding region between image frames based on motion in the image frame.