# US 2019/0379880 A1 · Image processing method, computer device and readable storage medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0379880 A1 - Document ID: US20190379880A1 - Status: Published application - Kind: A1 - Application number: 16/429,780 - Filed: 2019-06-03 - Published: 2019-12-12 - Earliest claimed: 2018-06-06 - Assignees: Guangdong Oppo Mobile Telecommunications Corp., Ltd. - Applicants: Guangdong Oppo Mobile Telecommunications Corp., Ltd. - Inventors: Xueyong ZHANG - Web page: https://patentgrep.com/patent/US20190379880A1 ## CPC - G06T 1/0007: {Image acquisition} - H04N 13/25: using two or more image sensors with different characteristics other than in their location or field of view, e.g. having different resolutions or colour pickup characteristics; using image signals from one sensor to control the characteristics of another sensor - G06T 5/50: using two or more images, e.g. averaging or subtraction - G06T 7/33: using feature-based methods - G06T 7/55: from multiple images - H04N 13/122: Improving the three-dimensional [3D] impression of stereoscopic images by modifying image signal contents, e.g. by filtering or adding monoscopic depth cues (H04N13/128 takes precedence) - H04N 13/156: Mixing image signals - H04N 13/239: using two two-dimensional [2D] image sensors having a relative position equal to or related to the interocular distance (H04N13/243 takes precedence) - H04N 13/254: in combination with electromagnetic radiation sources for illuminating objects - H04N 23/11: for generating image signals from visible and infrared light wavelengths - H04N 23/20: for generating image signals from infrared radiation only - G06T 7/521: from laser ranging, e.g. using interferometry; from the projection of structured light - G06T 2207/10024: Color image - G06T 2207/10028: Range image; Depth image; 3D point clouds - G06T 2207/10048: Infrared image - G06T 2207/20221: Image fusion; Image merging - H04N 2013/0081: {Depth or disparity estimation from stereoscopic image signals} - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract An image processing method, an image capturing apparatus (100), a computer device (1000) and a non-volatile computer-readable storage medium (200) are provided. The image processing method includes that: a first depth image of a present scene is acquired; a first visible light image of the present scene is acquired; a coincidence region between the first depth image and the first visible light image, a non-coincidence region of the first depth image and a non-coincidence region of the first visible light image are acquired; the non-coincidence region of the first depth image is removed to obtain a second depth image corresponding to the coincidence region; a non-coincidence region of the first visible light image is removed to obtain a second visible light image corresponding to the coincidence region; and a three-dimensional image is synthesized according to the second depth image and the second visible light image. ## Claims ### Claim 1 An image processing method, comprising: acquiring a first depth image and a first visible light image of a present scene; acquiring a coincidence region between the first depth image and the first visible light image, a non-coincidence region of the first depth image and a non-coincidence region of the first visible light image; removing the non-coincidence region of the first depth image from the first depth image to obtain a second depth image corresponding to the coincidence region; removing the non-coincidence region of the first visible light image from the first visible light image to obtain a second visible light image corresponding to the coincidence region; and generating a three-dimensional image according to the second depth image and the second visible light image. ### Claim 2 (depends on 1) The image processing method according to claim 1, wherein the image processing method is applied to an image capturing apparatus, the image capturing apparatus comprises a visible light camera and an Infrared Radiation (IR) camera, the coincidence region between the first depth image and the first visible light image, the non-coincidence region of the first depth image and the first visible light image are acquired according to a field of view of the visible light camera, a field of view of the IR camera and a preset distance between the visible light camera and the IR camera. ### Claim 3 (depends on 1) The image processing method according to claim 1, wherein the operation of acquiring a coincidence region between the first depth image and the first visible light image, a non-coincidence region of the first depth image and a non-coincidence region of the first visible light image comprises: extracting boundary feature points and full image feature points of the first depth image; extracting boundary feature points and full image feature points of the first visible light image; and matching the boundary feature points of the first depth image with the full image feature points of the first visible light image and matching the boundary feature points of the first visible light image with the full image feature points of the first depth image, to acquire the coincidence region between the first depth image and the first visible light image, the non-coincidence region of the first depth image and the non-coincidence region of the first visible light image. ### Claim 4 (depends on 1) The image processing method according to claim 1, wherein the image processing method is applied to an image capturing apparatus, the image capturing apparatus comprises a visible light camera and an IR camera, a field of view of the visible light camera, a field of view of the IR camera and a preset distance between the visible light camera and the IR camera are in one-to-one correspondence with a preset coincidence degree, the coincidence degree being a ratio of a coincidence region between a depth image and a visible light image to the visible light image. ### Claim 5 (depends on 4) The image processing method according to claim 4, wherein the operation of acquiring a coincidence region between the first depth image and the first visible light image, a non-coincidence region of the first depth image and a non-coincidence region of the first visible light image comprises: acquiring a coincidence degree between the first depth image and the first visible light image according to the field of view of the visible light camera, the field of view of the IR camera and the preset distance; and determining the coincidence region between the first depth image and the first visible light image, the non-coincidence region of the first depth image and the non-coincidence region of the first visible light image according to the coincidence degree and a relative position between the visible light camera and the IR camera. ### Claim 6 (depends on 3) The image processing method according to claim 3, wherein the image processing method is applied to an image capturing apparatus, the image capturing apparatus comprises a visible light camera and an IR camera, a field of view of the visible light camera, a field of view of the IR camera and a preset distance between the visible light camera and the IR camera are in one-to-one correspondence with a preset coincidence degree, the coincidence degree is a ratio of a coincidence region between a depth image and a visible light image to the visible light image, and feature matching boundaries of the first depth image and the first visible light image are determined according to the coincidence degree and a relative position between the IR camera and the visible light camera. ### Claim 7 A computer device, comprising a memory and a processor, the memory storing a computer-readable instruction that, when executed by the processor, causes the processor to execute operations for image processing comprising: acquiring a first depth image and a first visible light image of a present scene; acquiring a coincidence region between the first depth image and the first visible light image, a non-coincidence region of the first depth image and a non-coincidence region of the first visible light image; removing the non-coincidence region of the first depth image from the first depth image to obtain a second depth image corresponding to the coincidence region; removing the non-coincidence region of the first visible light image from the first visible light image to obtain a second visible light image corresponding to the coincidence region; and generating a three-dimensional image according to the second depth image and the second visible light image. ### Claim 8 (depends on 7) The computer device according to claim 7, further comprising a visible light camera and an Infrared Radiation (IR) camera, wherein the coincidence region between the first depth image and the first visible light image, the non-coincidence region of the first depth image and the non-coincidence region of the first visible light image are acquired according to a field of view of the visible light camera, a field of view of the IR camera and a preset distance between the visible light camera and the IR camera. ### Claim 9 (depends on 7) The computer device according to claim 7, wherein the computer-readable instruction, when executed by the processor, causes the processor to perform the following operations: extracting boundary feature points and full image feature points of the first depth image; extracting boundary feature points and full image feature points of the first visible light image; and matching the boundary feature points of the first depth image with the full image feature points of the first visible light image and matching the boundary feature points of the first visible light image with the full image feature points of the first depth image, to acquire the coincidence region between the first depth image and the first visible light image, the non-coincidence region of the first depth image and the non-coincidence region of the first visible light image. ### Claim 10 (depends on 7) The computer device according to claim 7, further comprising a visible light camera and an IR camera, wherein a field of view of the visible light camera, a field of view of the IR camera and a preset distance between the visible light camera and the IR camera are in one-to-one correspondence with a preset coincidence degree, the coincidence degree being a ratio of a coincidence region between a depth image and a visible light image to the visible light image. ### Claim 11 (depends on 10) The computer device according to claim 10, wherein the computer-readable instruction, when executed by the processor, causes the processor to perform the following operations: acquiring a coincidence degree between the first depth image and the first visible light image according to the field of view of the visible light camera, the field of view of the IR camera and the preset distance; and determining the coincidence region between the first depth image and the first visible light image, the non-coincidence region of the first depth image and the non-coincidence region of the first visible light image according to the coincidence degree and a relative position between the visible light camera and the IR camera. ### Claim 12 (depends on 9) The computer device according to claim 9, further comprising a visible light camera and an IR camera, wherein a field of view of the visible light camera, a field of view of the IR camera and a preset distance between the visible light camera and the IR camera are in one-to-one correspondence with a preset coincidence degree, the coincidence degree is a ratio of a coincidence region between a depth image and a visible light image to the visible light image, and feature matching boundaries of the first depth image and the first visible light image are determined according to the coincidence degree and a relative position between the IR camera and the visible light camera. ### Claim 13 A non-volatile computer-readable storage medium, comprising computer-executable instructions that, when executed by one or more processors, cause the one or more processors to perform operations for image processing comprising: acquiring a first depth image and a first visible light image of a present scene; acquiring a coincidence region between the first depth image and the first visible light image, a non-coincidence region of the first depth image and a non-coincidence region of the first visible light image; removing the non-coincidence region of the first depth image from the first depth image to obtain a second depth image corresponding to the coincidence region; removing the non-coincidence region of the first visible light image from the first visible light image to obtain a second visible light image corresponding to the coincidence region; and generating a three-dimensional image according to the second depth image and the second visible light image. ### Claim 14 (depends on 13) The non-volatile computer-readable storage medium according to claim 13, wherein the non-volatile computer-readable storage medium is applied to a computer device, the computer device comprises a visible light camera and an Infrared Radiation (IR) camera, the coincidence region between the first depth image and the first visible light image, the non-coincidence region of the first depth image and the non-coincidence region of the first visible light image are acquired according to a field of view of the visible light camera, a field of view of the IR camera and a preset distance between the visible light camera and the IR camera. ### Claim 15 (depends on 13) The non-volatile computer-readable storage medium according to claim 13, wherein the computer-executable instructions, when executed by the one or more processors, cause the one or more processors to perform the following operations: extracting boundary feature points and full image feature points of the first depth image; extracting boundary feature points and full image feature points of the first visible light image; and matching the boundary feature points of the first depth image with the full image feature points of the first visible light image and matching the boundary feature points of the first visible light image with the full image feature points of the first depth image, to acquire the coincidence region between the first depth image and the first visible light image, the non-coincidence region of the first depth image and the non-coincidence region of the first visible light image. ### Claim 16 (depends on 13) The non-volatile computer-readable storage medium according to claim 13, wherein the non-volatile computer-readable storage medium is applied to a computer device, the computer device further comprises a visible light camera and an IR camera, a field of view of the visible light camera, a field of view of the IR camera and a preset distance between the visible light camera and the IR camera are in one-to-one correspondence with a preset coincidence degree, the coincidence degree being a ratio of a coincidence region between a depth image and a visible light image to the visible light image. ### Claim 17 (depends on 16) The non-volatile computer-readable storage medium according to claim 16, wherein the computer-executable instructions, when executed by the one or more processors, cause the one or more processors to perform the following operations: acquiring a coincidence degree between the first depth image and the first visible light image according to the field of view of the visible light camera, the field of view of the IR camera and the preset distance; and determining the coincidence region between the first depth image and the first visible light image, the non-coincidence region of the first depth image and the non-coincidence region of the first visible light image according to the coincidence degree and a relative position between the visible light camera and the IR camera. ### Claim 18 (depends on 15) The non-volatile computer-readable storage medium according to claim 15, wherein the non-volatile computer-readable storage medium is applied to a computer device, the computer device further comprises a visible light camera and an IR camera, a field of view of the visible light camera, a field of view of the IR camera and a preset distance between the visible light camera and the IR camera are in one-to-one correspondence with a preset coincidence degree, the coincidence degree is a ratio of a coincidence region between a depth image and a visible light image to the visible light image, and feature matching boundaries of the first depth image and the first visible light image are determined according to the coincidence degree and a relative position between the IR camera and the visible light camera.