Abstract: A device for monitoring a heap of material, comprises circuitry for executing a plurality of functions. A region of interest function, in a thermal video stream captured by a thermal video camera, defines a region of interest covering the heap of material. A reference spatial property setting function, from pixels within a video frame of the thermal video stream, determines a spatial property of the heap of material; and sets the determined spatial property as a reference spatial property. A region of interest adjusting function determines a respective sample spatial property for regions in the thermal video stream; and adjusts the region of interest such that regions exhibiting a sample spatial property above a threshold are included by the region of interest. A temperature monitoring function over time and within the region of interest, monitors a temperature measure; and if it exceeds a predetermined threshold, generates an alarm event.

Abstract: A method of controlling a guard tour of a thermal camera, wherein the thermal camera is a pan-tilt camera or a pan-tilt-zoom camera, comprises the steps of: obtaining a guard tour comprising a plurality of views of an area or facility and a sequence of movements and/or view times of the thermal camera for traversing the plurality of views; controlling the thermal camera to traverse the plurality of views according to the sequence of movements and view times of the guard tour; for each view: extracting a temperature profile based on thermal images from the thermal camera; based on the temperature profile, estimating whether an increased risk of overheating or overcooling exists for the view; and if so, adjusting the sequence of movements and view times of the thermal camera to show the view having an increased risk of overheating or overcooling more frequently.

Abstract: There is provided a method for capturing a sequence of image frames in a thermal camera having a microbolometer detector comprising: capturing a first sequence and a second sequence of image frames with a shutter of the thermal camera being in a closed state and an open state, respectively. While capturing each of the first and the second sequence, an integration time of the microbolometer detector is switched between a plurality of integration times according to one or more repetitions of a temporal pattern of integration times. The method further comprises correcting image frames in the second sequence that are captured when the integration time is switched to a particular position within the temporal pattern of integration times using image frames in the first sequence that are captured when the integration time is switched to the same particular position within the temporal pattern of integration times.

Abstract: The present disclosure relates to a method performed by a people distinguishing system (1) for in an image distinguishing human beings in a crowd. The people distinguishing system identifies (1001) one or more detected objects classified as human beings (2) in an image (3) derived from a thermal camera (10) adapted to capture a scene in an essentially forward-looking angle. The people distinguishing system further identifies at least a first grouping (4) of adjoining pixels in the image, not comprised in the one or more detected human beings, having an intensity within a predeterminable intensity range. Moreover, the people distinguishing system determines (1003) a grouping pixel area (40) of the at least first grouping in the image. Furthermore, the people distinguishing system determines (1004) for at least a first vertical position (yexpected) in the image, based on head size reference data (5), an expected pixel area (xexpected) of a human head at the at least first vertical position.

Abstract: There is provided a method for capturing a sequence of image frames in a thermal camera having a microbolometer detector comprising: capturing a first sequence and a second sequence of image frames with a shutter of the thermal camera being in a closed state and an open state, respectively. While capturing each of the first and the second sequence, an integration time of the microbolometer detector is switched between a plurality of integration times according to one or more repetitions of a temporal pattern of integration times. The method further comprises correcting image frames in the second sequence that are captured when the integration time is switched to a particular position within the temporal pattern of integration times using image frames in the first sequence that are captured when the integration time is switched to the same particular position within the temporal pattern of integration times.

Abstract: Methods and apparatus, including computer program products, for detecting malfunction in a thermal camera. A first average response value is determined for a first shutter image captured by an image sensor in the thermal camera. A second average response value is determined of a second shutter image captured by the image sensor in the thermal camera. The first average response value and the second average response value are compared. In response to determining that the first average response value and the second average response value differ by more than a predetermined value, an indication of a malfunction of the thermal camera is provided.

Abstract: Methods and apparatus, including computer program products, for detecting a problem with a thermal camera. A current contrast value is determined for the thermal camera. It is determined whether the current contrast value deviates from a reference contrast value by more than a predetermined value. In response to determining that the current contrast value deviates from the reference contrast value by more than a predetermined value and for more than a predetermined period of time, an indication of a problem with the thermal camera is provided.

Abstract: A method for updating a fixed pattern noise matrix comprises: calculating a first difference between a target and first different images in a video stream to obtain a first differential matrix; calculating a second difference between the target and second different images in the video stream to obtain a second differential matrix; identifying a set of candidate positions for fixed pattern noise by: locating first and second sets of positions in the first differential matrix at which a difference deviates from predetermined values, finding a set of overlapping positions between the first and second sets of positions, and adjusting the set of overlapping positions. The adjusted set of overlapping positions is used for fixed pattern noise. Furthermore, each position in the set of candidate positions is updated, wherein the updated fixed pattern noise value at each position is based on a value at a corresponding non-adjusted position in the differential matrix.

Abstract: 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.

Abstract: A method of assisting tilt angle adjustment of a thermal camera comprises arranging the thermal camera at an initial tilt angle, acquiring at least one thermal image by the thermal camera, determining, from the at least one thermal image, a series of sharpness indicators of image parts corresponding to vertically spaced parts of the camera view, identifying a maximum in the series of sharpness indicators, based on the identified maximum, determining a target sharpness indicator as a predetermined fraction of the identified maximum, during tilt angle adjustment, assisting by providing a target signal for indicating a target tilt angle of the thermal camera in which a sharpness indicator of a lower part of the camera's field of view equals the determined target sharpness indicator.

Abstract: A method for temperature calibration and determination of a temperature in a scene. At each time point out of a plurality of time points in a first period of time, collecting an ambient temperature representing a temperature at a first part of the scene and collecting thermal image sensor signal values corresponding to the collected ambient temperatures and relating to the first part. Determine a calibration function based on the collected ambient temperatures and the thermal image sensor signal values corresponding to each of the collected ambient temperatures. In a second period of time, capturing a thermal image of the scene comprising thermal image sensor signal values relating to a second part of the scene and determine a temperature at the second part of the scene based on the calibration function and based on thermal image sensor signal values comprised in the thermal image.

Abstract: The present disclosure relates to a method performed by a people distinguishing system (1) for in an image distinguishing human beings in a crowd. The people distinguishing system identifies (1001) one or more detected objects classified as human beings (2) in an image (3) derived from a thermal camera (10) adapted to capture a scene in an essentially forward-looking angle. The people distinguishing system further identifies at least a first grouping (4) of adjoining pixels in the image, not comprised in the one or more detected human beings, having an intensity within a predeterminable intensity range. Moreover, the people distinguishing system determines (1003) a grouping pixel area (40) of the at least first grouping in the image. Furthermore, the people distinguishing system determines (1004) for at least a first vertical position (yexpected) in the image, based on head size reference data (5), an expected pixel area (xexpected) of a human head at the at least first vertical position.

Abstract: Methods and apparatus, including computer program products, for detecting malfunction in a thermal camera. A first average response value is determined for a first shutter image captured by an image sensor in the thermal camera. A second average response value is determined of a second shutter image captured by the image sensor in the thermal camera. The first average response value and the second average response value are compared. In response to determining that the first average response value and the second average response value differ by more than a predetermined value, an indication of a malfunction of the thermal camera is provided.

Abstract: Methods and apparatus, including computer program products, for detecting a problem with a thermal camera. A current contrast value is determined for the thermal camera. It is determined whether the current contrast value deviates from a reference contrast value by more than a predetermined value. In response to determining that the current contrast value deviates from the reference contrast value by more than a predetermined value and for more than a predetermined period of time, an indication of a problem with the thermal camera is provided.

Abstract: A method and a system for filtering thermal image data. The method comprises: capturing thermal image data by a thermal image detector; forming a signal distribution of intensity values; identifying a first part in the signal distribution of intensity values, the first part being a peak having an intensity width equal to or smaller than a predetermined intensity span being based on a resolution parameter of the thermal image detector; identifying a second part having an intensity width larger than the predetermined intensity span; determining an intensity range between the first part and the second part; and filtering, 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.

Abstract: A method for updating a fixed pattern noise matrix comprises: calculating a first difference between a target and first different images in a video stream to obtain a first differential matrix; calculating a second difference between the target and second different images in the video stream to obtain a second differential matrix; identifying a set of candidate positions for fixed pattern noise by: locating first and second sets of positions in the first differential matrix at which a difference deviates from predetermined values, finding a set of overlapping positions between the first and second sets of positions, and adjusting the set of overlapping positions. The adjusted set of overlapping positions is used for fixed pattern noise. Furthermore, each position in the set of candidate positions is updated, wherein the updated fixed pattern noise value at each position is based on a value at a corresponding non-adjusted position in the differential matrix.

Abstract: There is provided a method, a device (104), and a system (100) for enhancing changes in an image (103a) of an image sequence (103) captured by a thermal camera (102). An image (103a) which is part of the image sequence (103) is received (S02) and pixels (408) in the image that have changed in relation to another image (103b) in the sequence are identified (S04). Based on the intensity values of the identified pixels, a function (212, 212a, 212b, 212c, 212d, 212e) which is used to redistribute intensity values of changed as well as non-changed pixels in the image is determined (S06). The function has a maximum (601) for a first intensity value (602) in a range (514) of the intensity values of the identified pixels, and decays with increasing distance from the first intensity value.

Abstract: A method and an alert discriminator for converting alerts in a video monitoring operation. The method comprises: triggering a candidate alert, in response to detecting, in a stream of thermal images of a scene, a stationary foreground object in the scene; evaluating an intensity of the detected stationary foreground object in relation to a background intensity; and in response to the intensity of the detected stationary foreground object being above the background intensity, converting the candidate alert to an actual alert.

Abstract: A method of assisting tilt angle adjustment of a thermal camera comprises arranging the thermal camera at an initial tilt angle, acquiring at least one thermal image by the thermal camera, determining, from the at least one thermal image, a series of sharpness indicators of image parts corresponding to vertically spaced parts of the camera view, identifying a maximum in the series of sharpness indicators, based on the identified maximum, determining a target sharpness indicator as a predetermined fraction of the identified maximum, during tilt angle adjustment, assisting by providing a target signal for indicating a target tilt angle of the thermal camera in which a sharpness indicator of a lower part of the camera's field of view equals the determined target sharpness indicator.

Abstract: There is provided a method, a device (104), and a system (100) for enhancing changes in an image (103a) of an image sequence (103) captured by a thermal camera (102). An image (103a) which is part of the image sequence (103) is received (S02) and pixels (408) in the image that have changed in relation to another image (103b) in the sequence are identified (S04). Based on the intensity values of the identified pixels, a function (212, 212a, 212b, 212c, 212d, 212e) which is used to redistribute intensity values of changed as well as non-changed pixels in the image is determined (S06). The function has a maximum (601) for a first intensity value (602) in a range (514) of the intensity values of the identified pixels, and decays with increasing distance from the first intensity value.