Abstract: A method of configuring a camera comprising: collecting a video data with the camera, providing a plurality of imaging profiles, each imaging profile being associated with a set of scene characteristics, for each imaging profile, generating a spatial output data in dependence on the video data and the set of scene characteristics of the imaging profile, wherein the spatial output data is indicative of spatial locations of events detected in the video data matching one or more of the scene characteristics, performing a comparison of the spatial output data of each of the plurality of imaging profiles, selecting a preferred imaging profile in dependence on the comparison, configuring the camera to operate according to the preferred imaging profile.

Abstract: A first image is captured by the camera, using a first focus setting and a first aperture size. A first protrusion focus measure in a protrusion area of an object in the first image and a first recess focus measure in a recess area of the object in the first image are determined. A second image is captured by the camera, using the first focus setting and a second aperture size, and the object is detected. A second protrusion focus measure and a second recess focus measure are determined in the second image. A protrusion focus difference between the first and second protrusion focus measures, and a recess focus difference between the first and second recess focus measures are calculated. The protrusion focus difference and the recess focus difference are compared and if they differ by less than a predetermined threshold amount, it is determined that the object is fake.

Abstract: A method of configuring a camera comprising: collecting a video data with the camera, providing a plurality of imaging profiles, each imaging profile being associated with a set of scene characteristics, for each imaging profile, generating a spatial output data in dependence on the video data and the set of scene characteristics of the imaging profile, wherein the spatial output data is indicative of spatial locations of events detected in the video data matching one or more of the scene characteristics, performing a comparison of the spatial output data of each of the plurality of imaging profiles, selecting a preferred imaging profile in dependence on the comparison, configuring the camera to operate according to the preferred imaging profile.

Abstract: A method for determining whether a video camera is out-of-focus comprises: capturing image data; setting a focus setting difference threshold based on a filter function configured to filter the image data; adjusting a focus setting between a present focus setting and an altered focus setting such that a first subset of the image data is captured with the video camera being set in the present focus setting and such that a second subset of the image data is captured with the video camera being set in the altered focus setting, wherein the adjusting is performed such that a difference between the present and altered focus settings is below the threshold; forming the video stream by applying the filter function on the image data; determining first and second focus metrics of the image data; and determining whether the video camera is out-of-focus by comparing the first and second focus metrics.

Abstract: Methods and apparatus, including computer program products, for processing images recorded by a camera (202) monitoring a scene (200). A set of images (204, 206, 208) is received. The set of images (204, 206, 208) includes differently exposed images of the scene (200) recorded by the camera (202). The set of images (204, 206, 208) is processed by a trained neural network (210) configured to perform object detection, object classification and/or object recognition in image data, wherein the neural network (210) uses image data from at least two differently exposed images in the set of images (204, 206, 208) to detect objects in the set of images (204, 206, 208).

Abstract: A method for determining whether a video camera is out-of-focus comprises: capturing image data; setting a focus setting difference threshold based on a filter function configured to filter the image data; adjusting a focus setting between a present focus setting and an altered focus setting such that a first subset of the image data is captured with the video camera being set in the present focus setting and such that a second subset of the image data is captured with the video camera being set in the altered focus setting, wherein the adjusting is performed such that a difference between the present and altered focus settings is below the threshold; forming the video stream by applying the filter function on the image data; determining first and second focus metrics of the image data; and determining whether the video camera is out-of-focus by comparing the first and second focus metrics.

Abstract: A method for controlling a video camera which is configured to capture and process image frames prior to encoding. The method comprises determining whether the video camera is going to encode an image frame as an intra-frame or an inter-frame. If the image frame is going to be encoded as an inter-frame, the video camera is controlled to capture and process the image frame using first settings prior to encoding. If the image frame is going to be encoded as an intra-frame, the video camera is controlled to capture and process the image frame using second settings prior to encoding, wherein the second settings are modified in relation to the first settings to further reduce a level of noise in the image frame.

Abstract: A method of encoding a video stream comprising receiving a frame of a video stream to be encoded, performing motion detection in the frame to identify steady regions, and temporally filtering the frame so as to provide temporally filtered pixel values. For a pixel in the steady regions of the frame, the temporally filtered pixel value is used when encoding the pixel, on a condition that the pixel belongs to a block of pixels of the frame that will be intra-coded. On a condition that the pixel instead belongs to a block of pixels of the frame that will be inter-coded, a value that was used when encoding a corresponding pixel of the immediately preceding frame is used when encoding the pixel.

Abstract: A method of encoding a video stream comprising receiving a frame of a video stream to be encoded, performing motion detection in the frame to identify steady regions, and temporally filtering the frame so as to provide temporally filtered pixel values. For a pixel in the steady regions of the frame, the temporally filtered pixel value is used when encoding the pixel, on a condition that the pixel belongs to a block of pixels of the frame that will be intra-coded. On a condition that the pixel instead belongs to a block of pixels of the frame that will be inter-coded, a value that was used when encoding a corresponding pixel of the immediately preceding frame is used when encoding the pixel.

Abstract: A method for controlling a video camera which is configured to capture and process image frames prior to encoding. The method comprises determining whether the video camera is going to encode an image frame as an intra-frame or an inter-frame. If the image frame is going to be encoded as an inter-frame, the video camera is controlled to capture and process the image frame using first settings prior to encoding. If the image frame is going to be encoded as an intra-frame, the video camera is controlled to capture and process the image frame using second settings prior to encoding, wherein the second settings are modified in relation to the first settings to further reduce a level of noise in the image frame.

Abstract: A method and system for luminescence molecular imaging or tomography of a region of interest in a scattering medium is disclosed. The system comprises a non-linear luminescent marker material arranged in the scattering medium. Contrast and resolution of the imaging or tomography is thus improved. The non-linear marker is for instance configured to upconvert incoming light of an illumination wavelength. The non-linear power dependence of the marker enables further improvement of the imaging by using images taken with two or more excitation beams simultaneously.

Abstract: A method and system for luminescence molecular imaging or tomography of a region of interest in a scattering medium is disclosed. The system comprises a non-linear luminescent marker material arranged in the scattering medium. Contrast and resolution of the imaging or tomography is thus improved. The non-linear marker is for instance configured to upconvert incoming light of an illumination wavelength. The non-linear power dependence of the marker enables further improvement of the imaging by using images taken with two or more excitation beams simultaneously.