Beijing Xiaomi Mobile Software Co., Ltd.

Nuctech Company Limited

Tsinghua University

Cints Co., Ltd.

Lei Lei

Li Ni Zhang

Qingping Huang

Yunda Sun

Chaoyu Feng

Zhiqiang Chen

Ming Hu

Li Zhang

Qitian Miao

Zhi Tang

Jie Xia

Ming Huang

Yiwei Wang

Yanan Li

Xiaotao Wang

Guangqi Shao

Yu Liang

Yuqian Zhang

Pan Ye

Shilong Ji

A photographing method, including: obtaining a preview stream; detecting a movement speed of a photographed subject according to the preview stream; obtaining a first exposure time by shortening, according to the movement speed, an initial exposure time for preview frames in the preview stream, in response to determining that the movement speed is higher than a preset speed threshold; and capturing a picture based on the first exposure time.

Photographing method and apparatus, medium and chip

A method for processing an image includes first obtaining a media image. The media image has a target scene object at least partially shielded. A target shielding object is determined from the media image. The target shielding object at least partially shields the target scene object. Image inpainting is performed on a first region of the media image corresponding to the target shielding object to generate a target media image.

Method for processing image, related device and storage medium

Provided are a photographing method and device, a mobile terminal and a storage medium. The method includes: responsive to detecting a photographing instruction, continuously acquiring a target number of frames of images meeting a preset photographing parameter, the target number being N and determined by a mobile terminal based on a present photographing scenario and N being a positive integer; and determining a target image according to image quality of the N frames of images and outputting the target image. Through the method, the mobile terminal is more intelligent.

Photographing method and device, mobile terminal and storage medium

An image capturing method includes: displaying an image capturing preview interface of an image capturing program, the image capturing preview interface displaying a preview image; identifying an image capturing scene of the preview image by calling a machine learning model; and activating a moon image capturing mode in the image capturing program when the image capturing scene is a moon image capturing scene, the moon image capturing mode being an image capturing mode configured to capture image of the moon in a night sky.

Image capturing method and apparatus, and terminal

The present disclosure discloses an inspection system for quarantine and a method thereof. The CT technology is applied to the field of quarantine supervision, overcoming a problem of objects in an image of a single-view or a multi-view X-ray machine being overlapped, as well as a problem of organics including contrabands in a conventional CT image being not highlighted, not elaborated, and having bad contrast. Accuracy and efficiency of inspecting an object by human operator for quarantine inspection can be considerably improved, which is of a high application value.

Inspection systems for quarantine and methods thereof

An inspection device for quarantine that includes a dual-energy CT apparatus capable of distinguishing substances, a DR apparatus, a substance identification system capable of enhancing display of an object (plant, animal, meat, etc.) focused for quarantine and automatically so labeling, and an image processing system capable of highlighting a suspect of quarantine and providing a corresponding automatic alarm. Compared to the prior art, the present disclosure can highlight a focused object for quarantine, which may improve accuracy and efficiency of inspection for quarantine at a port.

Inspection devices for quarantine

The present invention discloses recognizing methods of flaky or blocky prohibited articles, explosives or drugs. Specifically, the method for recognizing flaky prohibited articles, explosives or drugs comprises steps of: (1) reading in tomogram data of an object to be inspected for one tomogram; (2) pre-processing the tomogram data; (3) splitting the pre-processed tomogram data into a plurality of regions that have similar physical properties; (4) analyzing whether each of the split regions is a flaky region; (5) determining whether the flaky region recognized in the current tomogram can be merged with the flaky region detected from the previous tomogram, so as to form a flaky target; (6) determining whether each detected flaky target is complete or finished; (7) repeating steps (1)-(6) and processing each tomogram data layer by layer, until all of the tomogram data have been processed.

Recognizing method of flaky or blocky prohibited articles, explosives or drugs

Growing community of inventors

Beijing, China

Lei Lei