Abstract: A system configured to improve human presence detection and/or localization by generating aggregate confidence values. The system may aggregate confidence values corresponding to overlapping regions of interest. The system may perform human presence detection by comparing the aggregate confidence values to a universal threshold, with aggregate confidence values above the universal threshold indicating that human presence is detected. The system may use the aggregate confidence values to generate a heatmap, may identify a strongest cluster of pixels in the heatmap and determine a bounding box surrounding the strongest cluster. To reduce false positive detections, the system may track the false positive detections as heatmap base data and may remove the heatmap base data from the heatmap. Thus, pixel intensity values corresponding to the false positive detections may be reduced to improve an accuracy of the human presence detection.

Abstract: Systems, methods, and computer-readable media are disclosed for determining a depth or reflectance of objects. Example methods may include causing illumination of a scene within a field of view of a device at a first illuminance value, determining a distance between a first object in the scene and the device, determining a reflected illuminance value, determining a first reflectance value for the first object in the scene based at least in part on the first illuminance value, the distance, and the reflected illuminance value, and adjusting a setting of the device using the first reflectance value.

Abstract: A first device may emit a first modulated signal within an environment that includes a second device that is located close in proximity to an object. The second device may capture the first modulated signal and determine a second modulated signal having a phase that is different from that of the first modulated signal. In response to capturing the second modulated signal, the first device may determine a phase difference corresponding to the first modulated signal and the second modulated signal using time-of-flight (TOF). Using the phase difference, the first device may determine the distance between the first device and the object. In embodiments where the phase difference is zero, the first device may be unable to detect the presence of the object.

Abstract: Systems, methods, and computer-readable media are disclosed for determining a depth or reflectance of objects. Example methods may include illuminating a scene within a field of view of a device at a first illuminance value, detecting a reflected illuminance value, and determining a first reflectance value for a first object in the scene. Example methods may include identifying the first object, determining an orientation of the first object, and determining an estimated distance between the device and the first object based at least in part on the first illuminance value, the reflected illuminance value, and the first reflectance value.

Abstract: Various embodiments provide a method of enhancing images in low lighting conditions wherein a color image is captured with a color camera, a first monochromatic image is captured with a first monochromatic camera, and a second monochromatic image is captured with a second monochromatic camera. Image registration is performed to align the first and second monochromatic images and the luminance information from the registered monochromatic images is fused with chrominance information from the color image.

Abstract: Systems, methods and devices for automatically cropping images taken by an electronic device in order to determine the identity of a product contained in the image are described herein. A number of different techniques may be applied to perform the automatic cropping, including a focus sweep technique in which a first image is analyzed for the presence of a human being and then a second image is taken in a plane closer to the camera than the first image. The two frames are analyzed and a resultant image is provided that avoids the regions in which the human being is present to focus on the product. In other embodiments, a motion vector calculation is made between two images in which an individual is holding a product. The motion vectors related to the human are removed and a bounding box is calculated to reduce the size of the image to include a higher percentage of the product, such that the product can be more easily identified.

Abstract: Provided are systems and methods for smoke and fire detection.

Abstract: A speech recognition computer system uses video input as well as audio input of known speech when the speech recognition computer system is being trained to recognize unknown speech. The video of the speaker can be captured using multiple cameras, from multiple angles. The audio can be captured using multiple microphones. The video and audio can be sampled so that timing of events in the video and audio can be determined from the content independent of an audio or video capture device's clock. Video features, such as a speaker's moving body parts, can be extracted from the video and random sampled, to be used in a speech modeling process. Audio is modeled at the phoneme level, which provides word mapping with minor additional effort. The trained speech recognition computer system can then be used to recognize speech text from video/audio of unknown speech.

Abstract: Various embodiments provide a method of enhancing images in low lighting conditions wherein a color image is captured with a color camera, a first monochromatic image is captured with a first monochromatic camera, and a second monochromatic image is captured with a second monochromatic camera. Image registration is performed to align the first and second monochromatic images and the luminance information from the registered monochromatic images is fused with chrominance information from the color image.

Abstract: Approaches provide for a computing device that includes, for example, a camera assembly, a lens assembly. The camera assembly can include an image sensor that includes, for example, a first region having camera pixels and a second region having photovoltaic cells. The camera pixels can be configured to capture light from the lens assembly for use in generating image data and the photovoltaic cells can be configured to capture light from the lens assembly for use in generating energy. The lens assembly can include a lens and a plurality of lens elements, where each lens element can be configured to direct a portion of light to a portion of the second region that includes the photovoltaic cells and the lens can be configured to direct a portion of the light to the first region that includes the camera pixels.

Abstract: Systems, devices, methods, computer-readable media, techniques, and methodologies are disclosed for generating a template iris pattern using multiple image frames containing image data corresponding to detected light at different wavelengths along the electromagnetic (EM) spectrum including light in the infrared, near-infrared, and/or visible light bands.

Abstract: Methods for hierarchical hole-filling and depth adaptive hierarchical hole-filling and error correcting in 2D images, 3D images, and 3D wrapped images are provided. Hierarchical hole-filling can comprise reducing an image that contains holes, expanding the reduced image, and filling the holes in the image with data obtained from the expanded image. Depth adaptive hierarchical hole-filling can comprise preprocessing the depth map of a 3D wrapped image that contains holes, reducing the preprocessed image, expanding the reduced image, and filling the holes in the 3D wrapped image with data obtained from the expanded image. These methods are can efficiently reduce errors in images and produce 3D images from a 2D images and/or depth map information.

Abstract: Methods for hierarchical hole-filling and depth adaptive hierarchical hole-filling and error correcting in 2D images, 3D images, and 3D wrapped images are provided. Hierarchical hole-filling can comprise reducing an image that contains holes, expanding the reduced image, and filling the holes in the image with data obtained from the expanded image. Depth adaptive hierarchical hole-filling can comprise preprocessing the depth map of a 3D wrapped image that contains holes, reducing the preprocessed image, expanding the reduced image, and filling the holes in the 3D wrapped image with data obtained from the expanded image. These methods are can efficiently reduce errors in images and produce 3D images from a 2D images and/or depth map information.