Abstract: An image adjustment method, applied to an image sensing system comprising an image sensor, comprising: (a) sensing a target image by the image sensor; (b) dividing the target image to a plurality of image regions; (c) acquiring location information of at least one first target feature in the image regions; (d) computing brightness information of each of the image regions; (e) generating adjustment curves according to the brightness information and according to required brightness values of each of the image regions; and (f) adjusting brightness values of the image regions according to the adjustment curves. The step (d) adjusts the brightness information according to the location information or the step (e) adjusts the adjustment curves according to the location information.

Abstract: An image signal amplifying circuit comprising an amplifier and a gain control circuit. The amplifier respectively amplifies a first image signal and a second image signal, which are generated by a pixel array of an image sensor, by a first analog gain and a second analog gain, wherein each one of pixel circuits of the pixel array comprises a first capacitor for generating the first image signal and a second capacitor for generating the second image signal, wherein a charge storage capacity of the first capacitor is smaller than a charge storage capacity of the second capacitor. The gain control circuit selectively adjusts the first analog gain or the second analog gain. Each one of the pixel circuits has a first conversion gain corresponding to the first capacitor and a second conversion gain corresponding to the second capacitor.

Abstract: A HDR tone mapping system includes several modules. A semantic segmentation module is used to extract semantic information from the input image. An image decomposition module is used to decompose the input image to a high-bit base layer and a detail layer. A statistics module is used to generate statistics of pixels of the input image according to the semantic information. A curve computation module is used to generate a tone curve from the statistics. A compression module is used to compress the high-bit base layer to a low-bit base layer according to the tone curve, the statistics and the semantic information. A detail adjustment module is used to tune the detail layer according to the semantic information and the statistics to generate an adjusted detail layer. An image reconstruction module is used to combine the adjusted detail layer and the low-bit base layer to generate an output image.

Abstract: A method for image alignment is provided. The method for image alignment includes the following stages. A first image with a first property from a first sensor is received. A second image with a second property from a second sensor is received. The first property is similar to the second property. The first feature correspondence between the first image and the second image is calculated. A third image with a third property from the first sensor and a fourth image with a fourth property from the second image sensor are received. The third property is different from the fourth property. Image alignment is performed on the third image and the fourth image based on the first feature correspondence between the first image and the second image.

Abstract: An image processing method is provided. The method includes the step of comparing each of the input pixels in an input image to a corresponding buffered pixel in a buffered image, and computing the difference value between the input pixel value of the input pixel and the buffered pixel value of the buffered pixel. The method further includes the step of generating a blended image based on the input pixel values and the corresponding difference values. The method further includes the step of determining whether a criterion associated with the difference value is met, for each of the difference values. The method further includes the step of updating, for each of the buffered pixels in the buffered image, the buffered pixel value based on the corresponding input pixel value if the criterion is met, and keeping the buffered pixel value unchanged if the criterion is not met.

Abstract: A method for tuning a plurality of image signal processor (ISP) parameters of a camera includes performing a first iteration. The first iteration includes extracting image features from an initial image, arranging a tuning order of the plurality of ISP parameters of the camera according to at least the plurality of ISP parameters and the image features, tuning a first set of the ISP parameters according to the tuning order to generate a first tuned set of the ISP parameters, and replacing the first set of the ISP parameters with the first tuned set of the ISP parameters in the plurality of ISP parameters to generate a plurality of updated ISP parameters.

Abstract: An image processing method is applied to an operation device and includes analyzing an unprocessed image to split the unprocessed image into a first region and a second region, applying a first image processing algorithm to the first region for acquiring a first processed result, applying a second image processing algorithm different from the first image processing algorithm to the second region for acquiring a second processed result, and generating a processed image via the first processed result and the second processed result.

Abstract: An image capturing device comprising an image sensor and a processing circuit. The processing circuit is configured to perform following steps: (a) outputting first sensing frames by the image sensor in a first mode, wherein a first frame time duration is determined between adjacent ones of the first sensing frames; (b) switching from the first mode to a second mode in a transition time interval; (c) setting the transition time interval such that a difference between the transition time interval and the first frame duration is smaller than a predetermined value; and (d) outputting second sensing frames by the image sensor in the second mode.

Abstract: An asymmetric image fusion method is applied to an operation device and includes acquiring a first image stream with a first frame rate, acquiring a second image stream with a second frame rate different from the first frame rate, and fusing a first reused image frame of the first image stream with a set of second image frames of the second image stream respectively for outputting a set of fused image frames.

Abstract: Various schemes pertaining to generating a full-frame color image using a hybrid sensor are described. An apparatus receives sensor data from the hybrid sensor, wherein the sensor data includes partial-frame chromatic data of a plurality of chromatic channels and partial-frame color-insensitive data. The apparatus subsequently generates full-frame color-insensitive data based on the partial-frame color-insensitive data. The apparatus subsequently generates the full-frame color image based on the full-frame color-insensitive data and the partial-frame chromatic data. The apparatus provides benefits of enhancing image quality of the full-frame color image especially under low light conditions.

Abstract: A method for high dynamic range imaging is provided. The method includes the following stages. A first image from a first sensor capable of sensing a first spectrum is received. A second image from a second sensor capable of sensing a second spectrum is received. The second spectrum has a higher wavelength range as compared to the first spectrum. A first image feature from the first image and a second image feature from the second image are retrieved. The first and second images are fused by referencing the first image feature and the second image feature to generate a final image.

Abstract: An image calibration method is applied to an image calibration device includes an image receiver and an operation processor. The image calibration method of providing a motion deblur function includes driving a first camera to capture a first image having a first exposure time, driving a second camera disposed adjacent to the first camera to capture a second image having a second exposure time different from and at least partly overlapped with the first exposure time, and fusing a first feature of the first image and a second feature of the second image to generate a fusion image.

Abstract: An image processing method is provided. The method includes a first MCNR stage and a second MCNR stage. The first MCNR stage includes blending the current frame with either a cached image or a long-term reference image to obtain a fused image. The cached image is loaded from the buffer unit, and the long-term reference image is derived from the static region of each input frame in a sequence of input frames. The second MCNR stage includes blending the fused image with the other of the cached image or the long-term reference image to obtain an output image.

Abstract: Various schemes pertaining to generating an output image using hybrid motion-compensated fusion techniques are described. An apparatus receives multi-frame data comprising a plurality of images consecutively captured. The apparatus subsequently generates a first intermediate image and a second intermediate image by performing temporal fusion on a first part and a second part of the multi-frame data, respectively. The apparatus further generates the output image using motion-compensated fusion based on the first and second intermediate images. The apparatus provides benefits of efficiently reducing noise and blurriness in the output image.

Abstract: An image signal amplifying circuit comprising an amplifier and a gain control circuit. The amplifier respectively amplifies a first image signal and a second image signal, which are generated by a pixel array of an image sensor, by a first analog gain and a second analog gain, wherein each one of pixel circuits of the pixel array comprises a first capacitor for generating the first image signal and a second capacitor for generating the second image signal, wherein a charge storage capacity of the first capacitor is smaller than a charge storage capacity of the second capacitor. The gain control circuit selectively adjusts the first analog gain or the second analog gain. Each one of the pixel circuits has a first conversion gain corresponding to the first capacitor and a second conversion gain corresponding to the second capacitor.

Abstract: An image processing method is provided. The image processing method is applied to an image signal processor. The image processing method includes the stages detailed in the following paragraph. Binned-Bayer raw data and binned-white raw data are received from an image sensor with an RGBW color filter array. The binned-Bayer raw data include information of red, green, and blue channels for a plurality of pixels. The binned-white raw data include luminance information for the pixels. The pixels are rendered based on both the binned-Bayer raw data and the binned-white raw data.

Abstract: A processor or control circuit of an apparatus receives data of an image based on sensing by one or more image sensors. The processor or control circuit also detects a region of interest (ROI) in the image. The processor or control circuit then adaptively controls a light projector with respect to projecting light toward the ROI.

Abstract: Various schemes pertaining to generating a full-frame color image using a hybrid sensor are described. An apparatus receives sensor data from the hybrid sensor, wherein the sensor data includes partial-frame chromatic data of a plurality of chromatic channels and partial-frame color-insensitive data. The apparatus subsequently generates full-frame color-insensitive data based on the partial-frame color-insensitive data. The apparatus subsequently generates the full-frame color image based on the full-frame color-insensitive data and the partial-frame chromatic data. The apparatus provides benefits of enhancing image quality of the full-frame color image especially under low light conditions.

Abstract: An image enhancement method applied to an image enhancement apparatus and includes acquiring a first edge feature from a first spectral image and a second edge feature from a second spectral image, analyzing similarity between the first edge feature and the second edge feature to align the first spectral image with the second spectral image, acquiring at least one first detail feature from the first spectral image and at least one second detail feature from the second spectral image, comparing the first edge feature and the second edge feature to generate a first weight and a second weight, and fusing the first detail feature weighted by the first weight with the second detail feature weighted by the second weight to generate a fused image. The first spectral image and the second spectral image are captured at the same point of time.

Abstract: Various examples with respect to adaptive infrared (IR) projection control for depth estimation in computer vision are described. A processor or control circuit of an apparatus receives data of an image based on sensing by one or more image sensors. The processor or control circuit also detects a region of interest (ROI) in the image. The processor or control circuit then adaptively controls a light projector with respect to projecting light toward the ROI.