Abstract: Image pair co-registration systems and methods include receiving a pair of multi-modal images, defining a parametric deformation model, defining a loss function that is minimized when the pair of images are aligned, and performing a multi-scale search to determine deformation parameters that minimize the loss function. The optimized deformation parameters define an alignment of the pair of images. The pair of images may include visible spectrum image and an infrared image. The method further includes resizing the visible spectrum image to match the infrared image, applying at least one lens distortion correction model, and normalizing a dynamic range of each of the pair of images. The multi-scale search may further include resizing the pair of images to a current processing scale, applying adaptive histogram equalization to the pair of images to generate equalized images, applying Gaussian Blur to the equalized images, and optimizing the deformation parameters.

Abstract: Image pair co-registration systems and methods include receiving a pair of multi-modal images, defining a parametric deformation model, defining a loss function that is minimized when the pair of images are aligned, and performing a multi-scale search to determine deformation parameters that minimize the loss function. The optimized deformation parameters define an alignment of the pair of images. The pair of images may include visible spectrum image and an infrared image. The method further includes resizing the visible spectrum image to match the infrared image, applying at least one lens distortion correction model, and normalizing a dynamic range of each of the pair of images. The multi-scale search may further include resizing the pair of images to a current processing scale, applying adaptive histogram equalization to the pair of images to generate equalized images, applying Gaussian Blur to the equalized images, and optimizing the deformation parameters.

Abstract: Various techniques are disclosed for calibrating surveillance camera systems with minimal user input. Such surveillance camera calibration techniques may be implemented in accordance with embodiments of the present disclosure to facilitate calibration and parameter configuration such that a surveillance camera can be installed and set up for video analytics with minimal input from a user without technical training or knowledge.

Abstract: Various techniques are provided to process captured thermal images to determine whether the thermal images exhibit degradation associated with environmental effects and/or security conditions. In one example, a method includes capturing a plurality of thermal images of a scene. The thermal images are processed to generate first and second background images associated with first and second time periods to filter out changes in the scene occurring within the associated time periods. The first and second background images are edge filtered to generate first and second edge images. The first and second edge images are compared to determine a change in edges associated with the scene. A device is selectively operated in a fail-safe mode in response to the comparing. Additional methods and related systems are also provided.

Abstract: Techniques are disclosed for detection-based wakeup of detection devices. A method may include generating a mapping that includes entries. Each entry may associate a respective detection result of a first detection device with a respective detection result of a second detection device. The method may further include transitioning the second detection device to a first power mode upon completing the generating. The method may further include determining, by the first detection device, that a first object of a first object type is detected based on the mapping. The method may further include transitioning the second detection device out of the first power mode when the first object of the first object type is determined to be detected. The method may further include performing, by the second detection device, at least one action based on the first object. Related systems and devices are also disclosed.

Abstract: Various embodiments of the methods and systems disclosed herein may be used to provide a surveillance camera that generates native video image frames in the appropriate FOV (orientation) that corresponds to the orientation in which the surveillance camera is installed when the video image frames are captured. The surveillance cameras implemented in accordance with embodiments of the disclosure may facilitate installation that provides a desired FOV in a particular orientation, generate video image frames that natively correspond to the desired FOV, and allow user interaction and video analytics to be performed on the FOV-matched video image frames.

Abstract: Various techniques are provided to process captured thermal images to determine whether the thermal images exhibit degradation associated with environmental effects and/or security conditions. In one example, a method includes capturing a plurality of thermal images of a scene. The thermal images are processed to generate first and second background images associated with first and second time periods to filter out changes in the scene occurring within the associated time periods. The first and second background images are edge filtered to generate first and second edge images. The first and second edge images are compared to determine a change in edges associated with the scene. A device is selectively operated in a fail-safe mode in response to the comparing. Additional methods and related systems are also provided.

Abstract: Various embodiments of the methods and systems disclosed herein may be used to provide a surveillance camera that generates native video image frames in the appropriate FOV (orientation) that corresponds to the orientation in which the surveillance camera is installed when the video image frames are captured. The surveillance cameras implemented in accordance with embodiments of the disclosure may facilitate installation that provides a desired FOV in a particular orientation, generate video image frames that natively correspond to the desired FOV, and allow user interaction and video analytics to be performed on the FOV-matched video image frames.

Abstract: Various embodiments of the present disclosure may include an imaging system. The imaging system may include a controller that is adapted to determine behavior typical of an object within an environment. The imaging system may additionally monitor the object within the environment and detect when the object behaves anomalously within the environment. Upon detection of anomalous behavior, the controller may output an alarm and/or a response message.

Abstract: Techniques are disclosed for detection-based wakeup of detection devices. A method may include generating a mapping that includes entries. Each entry may associate a respective detection result of a first detection device with a respective detection result of a second detection device. The method may further include transitioning the second detection device to a first power mode upon completing the generating. The method may further include determining, by the first detection device, that a first object of a first object type is detected based on the mapping. The method may further include transitioning the second detection device out of the first power mode when the first object of the first object type is determined to be detected. The method may further include performing, by the second detection device, at least one action based on the first object. Related systems and devices are also disclosed.

Abstract: Various techniques are disclosed for calibrating surveillance camera systems with minimal user input. Such surveillance camera calibration techniques may be implemented in accordance with embodiments of the present disclosure to facilitate calibration and parameter configuration such that a surveillance camera can be installed and set up for video analytics with minimal input from a user without technical training or knowledge.

Abstract: Various embodiments of the present disclosure may include an imaging system. The imaging system may include a controller that is adapted to determine behavior typical of an object within an environment. The imaging system may additionally monitor the object within the environment and detect when the object behaves anomalously within the environment. Upon detection of anomalous behavior, the controller may output an alarm and/or a response message.

Abstract: A traffic monitoring device may comprise a radar and a camera, the radar having a radar field of view extending around a radar central axis and the camera having a camera field of view extending around a camera central axis that are both situated in such a manner that the radar field of view is situated within the camera field of view. The radar and the camera may be positioned so that their a central axis of each field of view makes a predetermined angle with respect to the other, the radar being provided for determining coordinates of moving objects within the radar field of view. The device may comprise selecting means a processing unit to provided for selecting within the image an image section or portion, and a data processing unit to for transforming the coordinates of the moving object within the image portion into further coordinates relative to an image reference frame and for to displaying within the image portion an identifier at the further coordinates.

Abstract: A traffic monitoring device may comprise a radar and a camera, said radar having a radar field of view extending around a radar central axis and said camera having a camera field of view extending around a camera central axis in such a manner that said radar field of view is situated within said camera field of view. The radar and the camera may be positioned so that their central axis of their field of view make a predetermined angle with respect to each other, said radar being provided for determining coordinates of moving objects. The device may comprise selecting means for selecting within said image an image section or portion representing at least part of said radar field of view and may also comprise transformation means for transforming said coordinates of said moving object within said image portion into further coordinates relative to an image reference frame for display.