Huawei Device Co., Ltd.

Huawei Device (dongguan) Co., Ltd.

Huawei Technologies Co., Limited

Honor Device Co., Ltd.

Shenzhen University

Bin Deng

Wei Luo

Wei Su

Hao Wang

Yu Zhang

Gang Chen

Cheng Du

Congchao Zhu

Landi Li

Kang Qian

Jin Jin Wu

Xiaowei Yang

Yanlin Qian

Yunneng Mo

Sen Jia

Qingquan Li

Meng Jin

Jiasong Zhu

Hua Zhou

Lin Deng

Haitao Fu

Junlin Huang

Changming Cui

Jia Qi

Jin Wu

An electronic device and a method for dynamically adjusting an exposure parameter of a spectral sensor. The method includes: The electronic device determines whether a Clear value is less than or equal to a first threshold; and if the Clear value is less than or equal to the first threshold, the electronic device determines whether an analog gain of the spectral sensor reaches a second threshold; and if the analog gain of the spectral sensor reaches the second threshold, the electronic device extends an exposure time of the spectral sensor; or if the analog gain of the spectral sensor does not reach the second threshold, the electronic device increases the analog gain of the spectral sensor.

Electronic device and method for dynamically adjusting exposure parameter of spectral sensor

A method includes: after a panorama shooting instruction triggered by a user is acquired, shooting a first image, and acquiring a shooting parameter of the first image; determining move guiding information according to a preset move guiding policy, and displaying the move guiding information on a terminal, so as to instruct the user to move the terminal according to the move guiding information; shooting a preset quantity of images according to the shooting parameter of the first image after it is detected that the terminal moves, where the preset quantity of images are background images on both the left and right sides of a background corresponding to the first image; and performing, by using the first image as a center and by using a preset splicing scheme, seamless splicing on the first image and the preset quantity of images, to obtain a panoramic image.

Method and terminal for acquiring panoramic image

Provided are an image fusion classification method and device. The method includes that: a three-dimensional weight matrix of a hyperspectral image is obtained by use of a Support Vector Machine (SVM) classifier (); superpixel segmentation is performed on the hyperspectral image to obtain K superpixel images, K being a positive integer (); the three-dimensional weight matrix is regularized by use of a superpixel-image-based segmentation method to obtain a regular matrix (); and a class that a sample belongs to is determined according to the regular matrix ().

Image classification method and device

Method and terminal for acquire panoramic image

This application provides an image processing method and an electronic device. The method includes: obtaining a first image and a second image that are acquired at a same acquisition moment, where the first image is obtained by using a first photographing unit to acquire an image in a first acquisition region, and the second image is obtained by using a second photographing unit to acquire an image in a second acquisition region, where a parameter of the first photographing unit and a parameter of the second photographing unit are the same, and there is an overlapping acquisition region between the first acquisition region and the second acquisition region; and determining, according to the first image and the second image, whether the first photographing unit and the second photographing unit are normal.

Image processing method and apparatus, and electronic device

An auto-focus method including at a same moment, collecting a first image of a first object using a first image shooting unit, collecting a second image of the first object using a second image shooting unit, calculating M pieces of first depth information of M same feature point pairs in corresponding areas in the first image and the second image, determining whether confidence of the M pieces of first depth information is greater than a threshold, obtaining focusing depth information according to N pieces of first depth information in the IM pieces of first depth information when the confidence of the M pieces of first depth information is greater than the threshold, obtaining a target position of a first lens of the first image shooting unit according to the focusing depth information, and controlling the first lens to move to the target position.

Auto-focus method and apparatus and electronic device

An auto-focus method including at a same moment, collecting a first image of a first object using a first image shooting unit, collecting a second image of the first object using a second image shooting unit, calculating M pieces of first depth information of M same feature point pairs in corresponding areas in the first image and the second image, determining whether confidence of the M pieces of first depth information is greater than a threshold, obtaining focusing depth information according to N pieces of first depth information in the M pieces of first depth information when the confidence of the M pieces of first depth information is greater than the threshold, obtaining a target position of a first lens of the first image shooting unit according to the focusing depth information, and controlling the first lens to move to the target position.

A photographing method for a dual-lens device may include acquiring a first image collected at a first moment by a first image sensor and a second image collected at the first moment by a second image sensor; performing scene recognition on the first image and/or the second image, and performing depth estimation on the first image and the second image to determine a photographing environment; and when an instruction for a photographing operation is received, generating a picture using the multi-frame algorithm. When photographing is performed using a multi-frame algorithm, two frames of images can be collected at the same time using a dual-lens device, which can reduce impact caused by a jitter of the device or a motion of a target object, so that ghost detection and an elimination algorithm are not required, thereby reducing a photographing time.

Photographing for dual-lens device using photographing environment determined using depth estimation

A scene recognition method includes acquiring an image and sensor data corresponding to the image and determining, in accordance with the sensor data, whether a scene of the image is a non-high-dynamic range (HDR) scene. The method also includes extracting an image feature of the image when it is not determined whether the scene of the image is the non-HDR scene and determining, in accordance with the image feature, whether the scene of the image is an HDR scene.

Scene recognition method and apparatus

An image denoising method and terminal, where the method includes acquiring image data of an image, performing wavelet decomposition on at least one component of three components of the image data to obtain a high frequency wavelet coefficient and a low frequency wavelet coefficient of each component, performing recursive denoising on the low frequency wavelet coefficient of each component in at least one direction, to obtain a denoised low frequency wavelet coefficient of each component, performing wavelet reconstruction according to the high frequency wavelet coefficient of each component and the denoised low frequency wavelet coefficient of each component, to obtain at least one denoised component, and obtaining denoised image data.

Image denoising method and terminal

The present invention discloses a terminal. The terminal includes: a first camera, a second camera, a processor, the processor is connected to both the first camera and the second camera, the first camera and the second camera are located on a same side of the terminal, the first camera is configured to acquire an image in a first region; the processor is configured to: analyze the image acquired by the first camera, determine, according to an analysis result, exposure used when the second camera acquires an image in a second region; the second camera acquires the image in the second region according to the exposure that is determined by the processor and is used when the second camera acquires the image in the second region; the processor is configured to synthesize the images into a high dynamic image.

Method and apparatus for acquiring a high dynamic image using multiple cameras

The present invention provides a photographing method for a dual-lens device. The dual-lens device includes a first lens and a second lens that are arranged on a same plane. The photographing method includes acquiring a first image collected by a first image sensor; identifying a scenario of the first image to determine a photographing environment, determining a second image signal processor (ISP) parameter corresponding to the second lens; acquiring a second image that is collected, according to the second ISP parameter, and generating a preview image. According to the present invention, a photographing environment is determined by using an image collected by one lens of the dual-lens device, and then a preview image is generated by using an image collected by the other lens.

Growing community of inventors

Shenzhen, China

Bin Deng