# US 10,121,253 B2 · Method and apparatus for modeling target object to represent smooth silhouette > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,121,253 B2 - Document ID: US10121253B2 - Status: Granted - Kind: B2 - Application number: 14/879,273 - Filed: 2015-10-09 - Published: 2016-04-14 - Granted: 2018-11-06 - Earliest claimed: 2014-10-13 - Assignees: Samsung Electronics Co., Ltd. - Applicants: Samsung Electronics Co., Ltd. - Inventors: Hwiryong Jung; Nahyup Kang; Jiyeon Kim; Hyong Euk Lee - Web page: https://patentgrep.com/patent/US10121253B2 ## CPC - G06T 5/70: Denoising; Smoothing - G06T 7/12: Edge-based segmentation - G06T 7/529: from texture - G06T 2207/20028: Bilateral filtering - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract Provided is a method of modeling a target object, that may obtain depth information from an image in which the target object is represented in a form of particles, obtain distance information between adjacent particles in the image, and detect a silhouette of the target object based on the depth information and the distance information between the adjacent particles in the image. ## Claims ### Claim 1 A method of modeling a target object from an image captured by an image sensor, the method comprising: obtaining, by a processor, depth information from the image in which the target object is represented in a form of particles; obtaining, by the processor, distance information indicating a distance between adjacent particles in the image; detecting, by a processor, a silhouette of the target object based on the depth information without using the distance information, in response to a determination that the distance information is less than a threshold; detecting, by the processor, the silhouette of the target object based on the depth information and the distance information, in response to a determination that the distance information is greater than or equal to the threshold; and performing, by the processor, smoothing on an adjacent area comprising the silhouette of the target object in the image, in response to the determination that the distance information is greater than or equal to the threshold. ### Claim 2 (depends on 1) The method of claim 1, wherein the detecting of the silhouette comprises: correcting the detected silhouette based on the distance information. ### Claim 3 (depends on 1) The method of claim 1, wherein the obtaining of the distance information comprises: defining a target area used to obtain the distance information based on the depth information, wherein the adjacent particles are included in the target area. ### Claim 4 (depends on 3) The method of claim 3, wherein the defining of the target area comprises defining the target area based on a difference in the depth information between the adjacent particles in the image. ### Claim 5 (depends on 4) The method of claim 4, wherein the difference in the depth information between the adjacent particles in the image comprises a difference in brightness between particles. ### Claim 6 (depends on 3) The method of claim 3, wherein the target area is defined based on a brightness difference between the adjacent particles in the image. ### Claim 7 (depends on 3) The method of claim 3, wherein a difference in depth information between sets of adjacent particles in the target area is greater than or equal to 0.5. ### Claim 8 (depends on 1) The method of claim 1, wherein the obtaining of the depth information comprises: visualizing the particles in a form of a circle or an oval using sprite (scheme); and computing the depth information based on the visualized particles. ### Claim 9 (depends on 8) The method of claim 8, wherein the visualizing of the particles comprises visualizing the particles by computing a movement of the target object. ### Claim 10 (depends on 1) The method of claim 1, wherein the performing of the smoothing on the adjacent area comprises performing smoothing on the adjacent area using a bilateral filter. ### Claim 11 (depends on 1) The method of claim 1, wherein the target object comprises either one of a fluid and a deformable body. ### Claim 12 (depends on 1) A non-transitory computer-readable storage medium storing instructions that are processor executable to implement the method of claim 1. ### Claim 13 (depends on 1) The method of claim 1, wherein the depth information comprises a position of the image sensor and an observance direction of the image sensor. ### Claim 14 (depends on 1) The method of claim 1, wherein the obtaining of the depth information comprises computing normal information using a normal map to represent shadowing with a texture. ### Claim 15 (depends on 1) The method of claim 1, further comprising displaying a graphic comprising a rendering of the silhouette. ### Claim 16 A method of modeling a target object from an image captured by an image sensor, the method comprising: obtaining, by a processor, depth information from the image in which the target object is represented in a form of particles; obtaining, by the processor, distance information indicating a distance between adjacent particles in the image; detecting, by the processor, a silhouette of the target object based on the depth information without using the distance information, in response to a determination that the distance information is less than a threshold; detecting, by the processor, the silhouette of the target object based on the depth information and the distance information, in response to a determination that the distance information is greater than or equal to the threshold; and performing, by the processor, smoothing on an adjacent area comprising the silhouette of the target object in the image, in response to the determination that the distance information is greater than or equal to the threshold, wherein the threshold is two times greater than a radius of a particle among the particles. ### Claim 17 An apparatus to model a target object from an image, the apparatus comprising: a processor configured to execute instructions stored in a memory to obtain depth information from the image in which the target object is represented in a form of particles, obtain distance information indicating a distance between adjacent particles in the image, detect a silhouette of the target object based on the depth information without using the distance information, in response to a determination that the distance information is less than a threshold, detect the silhouette of the target object based on the depth information and the distance information, in response to a determination that the distance information is greater than or equal to the threshold, and perform smoothing on an adjacent area comprising the silhouette of the target object in the image, in response to the determination that the distance information is greater than or equal to the threshold. ### Claim 18 (depends on 17) The apparatus of claim 17, wherein the processor is further configured to correct the detected silhouette based on the distance information. ### Claim 19 (depends on 17) The apparatus of claim 17, wherein the threshold is two times greater than a radius of a particle among the particles. ### Claim 20 (depends on 17) The apparatus of claim 17, wherein the processor is further configured to define a target area used to obtain the distance information from the image, based on the depth information, wherein the adjacent particles are included in the target area. ### Claim 21 (depends on 20) The apparatus of claim 20, wherein the processor is further configured to define the target area based on a difference in the depth information between the adjacent particles in the image. ### Claim 22 (depends on 17) The apparatus of claim 17, wherein the apparatus further comprises the memory, and the memory is a non-transitory computer-readable storage medium. ### Claim 23 (depends on 17) The apparatus of claim 17, further comprising a display configured to display a graphic comprising a rendering of the silhouette. ### Claim 24 (depends on 17) The apparatus of claim 17, further comprising a communicator configured to receive a position of a camera which photographs the target object, a direction of the camera, and a field of view of a scene captured by the camera which is used to obtain the depth information.