Omnivision Technologies, Inc.

Eaglesens Systems Corporation

Qualcomm Incorporated

Weihua Xiong

Jizhang Shan

Guangbin Zhang

Xiaoyun Jiang

Donghui Wu

Chengming Liu

Weiliang Liu

Jiangtao Kuang

Zhipeng Deng

Xianbiao Shu

Jingtao Kuang

An image data processing method includes receiving frame image data of N frames, where N&#x3e;1, detecting a region of interest in one of the N frames, tracking locations of the region of interest in at least one of the N frames, and providing a merged location of the region of interest based on the locations of the region of interest in the N frames. Some embodiments include providing T of the merged locations of the region of interest for T respective groups of N frames, where T&#x3e;1, providing respective statistical data for each of the T merged locations, and providing a final location of the region of interest based on the T merged locations and the statistical data for the T merged locations.

Accurate ROI extraction aided by object tracking

An image data processing method includes receiving, from an image sensor, frame image data of a frame at a first resolution, reducing a resolution of the frame image data to a second resolution, performing image recognition on the frame image data to determine one or more regions of interest (ROI) and a priority level of each of the one or more ROIs, and extracting portions of the frame image data corresponding to the one or more ROIs. The method further includes modifying a resolution of the portions of the frame image data corresponding to the one or more ROIs based on the priority level of the ROIs, and combining the resolution-modified portions of the frame image data corresponding to the one or more ROIs with the frame image data at the second resolution to generate output frame image data.

Artificial intelligence based image data processing method and image processing device

An image data processing method includes receiving, from an image sensor, frame image data of a plurality of frames; receiving a plurality of control rules comprising a respective control rule for each of the frames, wherein each of the control rules identifies one of a plurality of process regions and one of a plurality of object detectors; identifying a region of interest in each frame by a location and a category, comprising applying the object detector identified by the respective control rule to the respective frame image data in the process region identified by the respective control rule; identifying a final region of interest based on the identified regions of interest; and reporting the final region of interest.

Asynchronous object ROI detection in video mode

A method for combining images includes capturing a first image including a subject from a first camera. A second image is captured from a second camera and the second image includes the subject. First pre-processing functions are applied on the first image to produce a first processed image. The first pre-processing functions include applying a distortion component of a rotation matrix to the first image. The rotation matrix defines a corrected relationship between the first and the second image. Second pre-processing functions are applied on the second image to produces a second processed image. The second pre-processing functions include applying the rotation matrix to the second image. The first processed image and the second processed image are blended in a processing unit to form a composite image.

Method for combining images

A system and method for generating an image includes a plurality of imaging units coupled together and a system controller coupled to the plurality of imaging units for providing at least one signal to each of the plurality of imaging units. Each of the imaging units comprises: an image sensing unit for generating an in-situ image, each in-situ image being a portion of the image; an input for receiving the in-situ image; a composition unit for receiving a first composite image and producing a second composite image, the second composite image being a combination of the first composite image and the in-situ image; and an output at which the second composite image is provided.

Image processing system and method using serially coupled cameras for providing extended view

Capturing a target image includes activating a first image sensor for capturing the target image. A sequence of images is captured with a second image sensor while the first image sensor remains activated. A determination is made as to whether the sequence of images captured by the second image sensor includes a shutter gesture while the first image sensor remains activated. If a shutter gesture is included in the sequence of images captured by the second image sensor, the first image sensor captures the target image in response.

Shutter release using secondary camera

Certain aspects relate to systems and techniques for correction of color artifacts including both color aberration and color spot artifacts using a unified framework. For example, both color aberration and color spot artifacts can be corrected using a post-processing method implementing directional median filtering on chroma channels. A pixel-by-pixel correction ratio map can be built by analyzing the luma and chroma components of the image to indicate a type of color artifact associated with each pixel in the image, and a directional median filter can be selected for each pixel based on the corresponding correction ratio map value.

System and method of correcting image artifacts

Image processing system and method using multiple imagers for providing extended view

A method of capturing an image includes activating a first image sensor and capturing a sequence of images with a second image sensor. A determination is made as to whether the sequence of images captured by the second image sensor includes a shutter gesture. If a shutter gesture is included in the sequence of images captured by the second image sensor, the first image sensor captures a target image in response.

Systems and methods resume capture of a base image from an object by a mobile scanner operated by a user. An indication of an overlap area on a base image displayed within a computer display is received. A scan image is received from the mobile scanner positioned on the object at a location corresponding to the overlap area. A match between a segment of the scan image and a corresponding segment of the base image is determined, where the match defines a location and orientation of the mobile scanner relative to the base image. An indication that the scan has resumed is made to the user when the match is found, and images that are subsequently received from the mobile scanner are stitched to the base image based upon the determined location and orientation. The partially formed base image and the scanner image are concurrently displayed to the user.

Systems and methods for resuming capture of a base image of an object by a mobile scanner

An image sensor uses a single row of an array of pixels elements to determine whether a pixel is defective and to recover the defective pixel. The image sensor includes a 'maximum of minimum' filter to remove a 'black' pixel from a raw image. The image sensor also includes a &#x201c;minimum of maximum&#x201d; filter to remove a &#x201c;white&#x201d; pixel from the raw image.

Single row based defective pixel correction

The specification disclosed embodiments of an apparatus comprising an automatic white balance (AWB) circuit coupled to a pixel array to transform red, green, and blue color data obtained from each pixel into x and y chromaticity values for each pixel, determine a distance between the Planckian locus and the x and y chromaticity values for each pixel, determine a weight for each pixel based on the distance between its x and y chromaticity values and the Planckian locus, determine red, green, and blue adjustments for each pixel using its weight, and apply a white balance adjustment to the red, green and blue values obtained from each pixel. Other embodiments are also disclosed and claimed.

Automatic white balance using non-uniform averaging

An image sensing system provide feature tone detection. A feature tone detection module receives illumination compensated pixel data. To perform feature tone identification the illumination compensated pixel data is transformed to a color space having hue and saturation and then compared against pre-selected ranges of hue and saturation. Noise filtering is performed using an erosion-dilation process. A bit code is used to identify pixels having a specified feature tone, such as a skin tone.

Apparatus, system, and method for skin tone detection in a CMOS image sensor

The disclosure describes embodiments of an apparatus comprising an image sensor including a pixel array having a plurality of pixels and an automatic white balance (AWB) circuit coupled to the pixel array. The AWB circuit is used to determine a local white balance component for each pixel, determine a global white balance component for each pixel, and apply a white balance adjustment to each pixel, the applied white balance adjustment comprising a combination of the local white balance component and the global white balance component. The disclosure also describes embodiment of a process including receiving image data from each pixel in a pixel array, determining a local white balance component for the image data from each pixel, determining a global white balance component for the image data from each pixel, and applying a white balance adjustment to the image data from each pixel, the applied white balance adjustment comprising a combination of the local white balance component and the global white balance component. Other embodiments are also disclosed and claimed.

Growing community of inventors

Cupertino, CA, United States of America

Weihua Xiong