Abstract: A method, apparatus and computer program product are provided for varying panning speeds of images based on saliency such that 360-degree images, panoramic images, video images and/or other wide view area images may be efficiently displayed by varying the panning speed such that the user focuses on salient portions of the image. A panning speed is determined based on the currently displayed area and its saliency relative to the saliency of non-displayed or peripheral portions. As a user pans from one area to another, while the user pans over a salient portion of the image, the actual reflected panning may occur at a relatively slower speed than when the user pans over an area not including a salient portion, or a less salient portion.

Abstract: Systems and methods are provided to generate an object detection representation of a candidate object based on sensor data representing a captured image of an environment surrounding the vehicle. A determination is made as to whether, whether the candidate object is an outlier based on the object detection representation. In response to determining the candidate object is not an outlier, the candidate object is validated as an object, a proximity distance of the object to the vehicle is determined, and the proximity distance of the object is sent as output.

Abstract: A method, apparatus and computer program products are provided for reducing artifacts in a seam region when stitching overlapping images. One example method includes extracting the seam region from the overlapping images, wherein the overlapping images comprise a first image captured by a first image capturing device and a second image captured by a second image capturing device, the overlapping images sharing the seam region, the seam region being a region of each of the first image and the second images depicting a common captured area, applying a set of convergence values to the seam region generating a plurality of strips corresponding to the seam region, dividing the plurality of strips into multiple vertical segments, and computing an optimal convergence for each of the multiple vertical segments.

Abstract: A method, apparatus and computer program product are provided to combine images captured by multiple cameras into a panoramic image, such as a 360° panorama, in a manner that reduces image defects and other artifacts at or near a seam between images. In some implementations of example embodiments, the overlapping portions of two images are decomposed into a predetermined number of bands. For most of the bands, a laplacian of Gaussian blending mask is applied when blending images associated with the relevant bands. For a final band, a linear blending mask is applied, and the bands are combined into an image that may be used in connection with a panoramic image featuring portions of multiple images captured by an array of cameras. In some example implementations, a bandwidth for the final band may be determined based in part on a selected sharpness factor.

Abstract: An apparatus comprises: a camera module for obtaining a first image, the camera module having at least one port, each of the at least one ports being associated with an attachment position for receiving a second camera module for obtaining a second image; a processor for detecting a position of a second camera module and providing, to an image processing controller, information relating to at least one of the position of the second camera module and the first image obtained by the camera module; and a memory for storing the information relating to at least one of the position of the second camera module and the first image obtained by the camera module.

Abstract: The present invention may be summarized as a hybrid approach for computing the convergence of a seam region of two overlapping images, in particular, segment regions of a seam region, by using (a) convergence estimates from an SSD-based search and (b) convergence estimates from optical flow, to arrive at a final convergence value towards image alignment for stitching.

Abstract: A method, apparatus and computer program products are provided for facilitating stereo vision through the use of multi-layer shifting. One example method includes receiving a first RGB image and a second RGB image, each captured from a different position, generating corresponding depth images, performing a first segmentation on the depth images, performing a second segmentation on the RGB images resulting in a first object mask and a second object mask, stitching of the background layers to form a background layer, generating a series of images comprising a first image representative of a view from the first position and a second image representative of a view from the second position, the series of images demonstrating a shifting of an object layer occurring at a higher speed than a shifting of the background layer.

Abstract: Embodiments herein select first and second panoramic images from respective first and second video streams, each comprising a series of stitched images captured by multiple cameras of respective first and second non-co-located video camera arrays. These arrays may be capturing live video for virtual reality rendering. A rotation is computed between the first and second panoramic images such that, when applied, the first and/or the second panoramic images are rotated relative to one another such that at least one common object is oriented to a common field of view position in both those panoramic images. The output can be variously manifested for different embodiments, for example the output can include a) the first video stream, the second video stream, and an indication of the computed rotation; and/or b) the first video stream and the second video stream with the computed rotation applied thereto.

Abstract: A method, apparatus and computer program product are provided to combine images captured by multiple cameras into a composite panoramic image, such as a 360° panorama, in a manner that reduces image defects and other artifacts at or near a seam between images. In some implementations of example embodiments, the overlapping portions of two images are divided into a plurality of seam regions. Upon selection of a seam region, the seam region is further divided into seam segments. In each seam segment, a depth level associated with the segment is used to calculate convergence value that is applied such that different scaling factors may be applied to image elements at different depths within a given image. Based on the applied convergence values and the resulting stitching at the seam region the image quality at the seam area can be efficiently improved.

Abstract: A method, apparatus and computer program products are provided for reducing artifacts in a seam region when stitching overlapping images. One example method includes extracting the seam region from the overlapping images, wherein the overlapping images comprise a first image captured by a first image capturing device and a second image captured by a second image capturing device, the overlapping images sharing the seam region, the seam region being a region of each of the first image and the second images depicting a common captured area, applying a set of convergence values to the seam region generating a plurality of strips corresponding to the seam region, dividing the plurality of strips into multiple vertical segments, and computing an optimal convergence for each of the multiple vertical segments.

Abstract: A method, apparatus and computer program product are provided for varying panning speeds of images based on saliency such that 360-degree images, panoramic images, video images and/or other wide view area images may be efficiently displayed by varying the panning speed such that the user focuses on salient portions of the image. A panning speed is determined based on the currently displayed area and its saliency relative to the saliency of non-displayed or peripheral portions. As a user pans from one area to another, while the user pans over a salient portion of the image, the actual reflected panning may occur at a relatively slower speed than when the user pans over an area not including a salient portion, or a less salient portion.

Abstract: A method, apparatus and computer program product are provided to combine images captured by multiple cameras into a panoramic image, such as a 360° panorama, in a manner that reduces image defects and other artifacts at or near a seam between images. In some implementations of example embodiments, the overlapping portions of two images are decomposed into a predetermined number of bands. For most of the bands, a laplacian of Gaussian blending mask is applied when blending images associated with the relevant bands. For a final band, a linear blending mask is applied, and the bands are combined into an image that may be used in connection with a panoramic image featuring portions of multiple images captured by an array of cameras. In some example implementations, a bandwidth for the final band may be determined based in part on a selected sharpness factor.

Abstract: A method, apparatus and computer program products are provided for facilitating stereo vision through the use of multi-layer shifting. One example method includes receiving a first RGB image and a second RGB image, each captured from a different position, generating corresponding depth images, performing a first segmentation on the depth images, performing a second segmentation on the RGB images resulting in a first object mask and a second object mask, stitching of the background layers to form a background layer, generating a series of images comprising a first image representative of a view from the first position and a second image representative of a view from the second position, the series of images demonstrating a shifting of an object layer occurring at a higher speed than a shifting of the background layer.

Abstract: An apparatus comprises: a camera module for obtaining a first image, the camera module having at least one port, each of the at least one ports being associated with an attachment position for receiving a second camera module for obtaining a second image; a processor for detecting a position of a second camera module and providing, to an image processing controller, information relating to at least one of the position of the second camera module and the first image obtained by the camera module; and a memory for storing the information relating to at least one of the position of the second camera module and the first image obtained by the camera module.

Abstract: A method, apparatus and computer program product are provided to generate a panoramic view in a computationally efficient manner. In regards to a method, images captured by at least three cameras are received. Each camera has a different, but partially overlapping field of view. The method generates first and second panoramic views. The first and second panoramic views include a first region generated such that pixels are based upon an image captured by one camera. The first and second panoramic views also include a second region that at least partially corresponds with the mutually overlapping portion of the fields of view. The generation of the second region is based upon a combination of images captured by at least two of the cameras and includes combining the images captured by at least two of the cameras utilizing depth information associated with an image captured by at least one of the cameras.

Abstract: Method, device, and computer program product for detecting an object in a digital image are provided. The method includes providing a detection window and determining at least one area of the object in the digital image by traversing the detection window by a first step size onto a set of pixels. Further, at each pixel, presence of at least one portion of the object in the detection window is detected. Upon detection of the presence of the object, the detection window is shifted by a second step size to neighbouring pixels. Further, the detection window is selected as an area of the object if the at least one portion of the object is present in at least a threshold number of detection windows at the neighbouring pixels. Thereafter, an object area representing the object in the digital image is selected based on the at least one area.