CN107734254A - A kind of unmanned plane is selected a good opportunity photographic method automatically - Google Patents

A kind of unmanned plane is selected a good opportunity photographic method automatically Download PDF

Info

Publication number
CN107734254A
CN107734254A CN201710955887.3A CN201710955887A CN107734254A CN 107734254 A CN107734254 A CN 107734254A CN 201710955887 A CN201710955887 A CN 201710955887A CN 107734254 A CN107734254 A CN 107734254A
Authority
CN
China
Prior art keywords
face
unmanned plane
frame
threshold value
photographic method
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201710955887.3A
Other languages
Chinese (zh)
Inventor
陶颋
陶磊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Instant Technology Co Ltd Hefei Branch
Original Assignee
Shanghai Instant Technology Co Ltd Hefei Branch
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Instant Technology Co Ltd Hefei Branch filed Critical Shanghai Instant Technology Co Ltd Hefei Branch
Priority to CN201710955887.3A priority Critical patent/CN107734254A/en
Publication of CN107734254A publication Critical patent/CN107734254A/en
Pending legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/61—Control of cameras or camera modules based on recognised objects
    • H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)

Abstract

Selected a good opportunity automatically photographic method the invention discloses a kind of unmanned plane, the face in picture is detected in real time by Face datection unit, obtain face rectangle frame, the absolute offset values of face rectangle frame central point relative target face frame central point to detecting in real time carry out threshold calculations, and threshold calculations are carried out to the relative displacement of face rectangle frame center point coordinate, after continuous k frames picture meets above-mentioned condition simultaneously, system presses shutter automatically, completes action of taking pictures.This method not only ensures to be located at predetermined picture-taking position in moment face of taking pictures, while prevents from occurring during photographing outdoors that wind-force is larger, causes occur situation about shaking in unmanned plane shooting process so that effect of taking pictures is more preferable.

Description

A kind of unmanned plane is selected a good opportunity photographic method automatically
Technical field
The present invention relates to unmanned air vehicle technique field, more particularly to a kind of unmanned plane is selected a good opportunity photographic method automatically.
Background technology
UAV abbreviation unmanned plane, currently with the maturation of correlation technique, the application of unmanned plane is also progressively Expand, it is main include taking photo by plane, agricultural, the field such as express delivery.During being taken pictures using unmanned plane, due to such environmental effects, In the case of wind-force is larger, unmanned plane can produce certain shake in itself, have impact on the shooting effect of photo.Stabilization technology is certain Degree solves this problem, but the unmanned plane performance of different manufacturers varies, and stabilization effect is also preferable not to the utmost.
The content of the invention
In order to solve problem of the prior art, selected a good opportunity automatically photographic method the invention provides a kind of unmanned plane, technical side Case is as follows：
1) target face frame center point coordinate (x is set0,y0)；
2) by Face datection unit, the face in picture is detected in real time, obtains face rectangle frame；
3) the i-th frame face rectangle frame center point coordinate (x is recordedi,yi), and to its relative target face frame central point (x0, y0) absolute offset values TiCalculated, if absolute offset values TiNot less than predetermined threshold value t, then step 4) is performed, is otherwise performed Step 2)；
4) the i-th frame is detected to the face rectangle frame central point (x obtainedi,yi) with former frame detection obtain face rectangle frame Central point (xi-1,yi-1) compare, calculate interframe face rectangle frame central point offset DiIf interframe offset DiNot less than pre- If threshold value d, then step 5) is performed, otherwise perform step 2)；
5) continuously detection k frame pictures meet above-mentioned condition, and system presses shutter automatically, completes action of taking pictures, otherwise performs Step 2).
Further, a kind of select a good opportunity automatically target face frame described in photographic method of unmanned plane meets aesthetics for systemic presupposition The human face target position of style.
Further, to face rectangle frame center point coordinate (x in step 3)i,yi) relative target face frame central point (x0, y0) absolute offset values TiCalculated, mainly calculate Face datection unit and detect human face region relative target face area in real time The displacement of domain coordinate position, represent that current face region is located at target face if displacement is no more than predetermined threshold value In regional extent, represent that current face region is in non-targeted human face region if displacement exceedes predetermined threshold value.
Further, step 4) calculates Face datection unit and detects the human face region of acquisition in real time in the i-th frame data and the (i-1) the relative movement distance D of the coordinate position in frame datai, represent current if displacement is no more than predetermined threshold value Picture is in stable state, represents to be currently at unstable state if displacement exceedes predetermined threshold value.
Further, target face frame center point coordinate offset TiPredetermined threshold value t scopes 2-5 pixel coverage it Between.
Further, face frame center point coordinate offset DiPredetermined threshold value d scopes should be less than t values.
Further, k values typically should be greater than being equal to 3 in step 5).
Further, for Face datection unit after face is detected, system reconciles parameter of taking pictures automatically, completes focusing step Suddenly.
The beneficial effect that technical scheme provided in an embodiment of the present invention is brought is：Unmanned plane provided by the invention is selected a good opportunity automatically Photographic method this method not only ensures to be located at predetermined picture-taking position in moment face of taking pictures, while prevents wind occur during photographing outdoors Power is larger, causes occur situation about shaking in unmanned plane shooting process so that effect of taking pictures is more preferable.
Brief description of the drawings
Fig. 1 is that a kind of unmanned plane provided in an embodiment of the present invention is selected a good opportunity the flow chart of photographic method automatically；
Fig. 2 is that a kind of unmanned plane provided in an embodiment of the present invention is selected a good opportunity the schematic diagram of photographic method automatically.
Embodiment
It is now described with reference to the drawings the embodiment of the present invention.
The photographic method as shown in figure 1, a kind of unmanned plane is selected a good opportunity automatically, comprises the following steps：
1) target face frame center point coordinate (x is set0,y0)；
2) by Face datection unit, the face in picture is detected in real time, obtains face rectangle frame；
3) the i-th frame face rectangle frame center point coordinate (x is recordedi,yi), and to its relative target face frame central point (x0, y0) absolute offset values TiCalculated, if absolute offset values TiNot less than predetermined threshold value t, then step 4) is performed, is otherwise performed Step 2)；
4) the i-th frame is detected to the face rectangle frame central point (x obtainedi,yi) with former frame detection obtain face rectangle frame Central point (xi-1,yi-1) compare, calculate interframe face rectangle frame central point offset DiIf interframe offset DiNot less than pre- If threshold value d, then step 5) is performed, otherwise perform step 2)；
5) continuously detection k frame pictures meet above-mentioned condition, and system presses shutter automatically, completes action of taking pictures, otherwise performs Step 2).
Further, a kind of select a good opportunity automatically target face frame described in photographic method of unmanned plane meets aesthetics for systemic presupposition The human face target position of style.
Further, to face rectangle frame center point coordinate (x in step 3)i,yi) relative target face frame central point (x0, y0) absolute offset values TiCalculated, mainly calculate Face datection unit and detect human face region relative target face area in real time The displacement of domain coordinate position, represent that current face region is located at target face if displacement is no more than predetermined threshold value In regional extent, represent that current face region is in non-targeted human face region if displacement exceedes predetermined threshold value.
Further, step 4) calculates Face datection unit and detects the human face region of acquisition in real time in the i-th frame data and the (i-1) the relative movement distance D of the coordinate position in frame datai, represent current if displacement is no more than predetermined threshold value Picture is in stable state, represents to be currently at unstable state if displacement exceedes predetermined threshold value.
Further, target face frame center point coordinate offset TiPredetermined threshold value t scopes 2-5 pixel coverage it Between.
Further, face frame center point coordinate offset DiPredetermined threshold value d scopes should be less than t values.
Further, k values typically should be greater than being equal to 3 in step 5).
Further, for Face datection unit after face is detected, system reconciles parameter of taking pictures automatically, completes focusing step Suddenly.
As shown in Fig. 2 O points are target face frame center position, and when step 3) threshold value is t, the people of detection acquisition in real time Face rectangle frame central point should be as shown in Fig. 2 using O points as the center of circle, and t values is in the great circles of radius.
As shown in Fig. 2 A points are the face rectangle frame central point that (i-1) frame picture detects acquisition in real time, step 4) threshold value For d when, the face rectangle frame central point that the i-th frame picture detects acquisition in real time should be as shown in Fig. 2 using A points as the center of circle, d values be In the roundlet of radius
Meet above-mentioned two condition simultaneously, face rectangle frame central point B should be in the i-th frame picture that detection obtains in real time In circle O and circle A overlapping region, shadow region as shown in Figure 2.
The face rectangle frame central point that continuous k frames or more picture detects acquisition in real time is respectively positioned on shadow region as shown in Figure 2 In domain, system presses shutter automatically, completes to take pictures.
Above content is to combine specific preferred embodiment further description made for the present invention, it is impossible to is assert The specific implementation of the present invention is confined to these explanations.For those skilled in the art of the invention, this hair is not being departed from On the premise of bright design, simple change or optimization are made, should all be considered as protection scope of the present invention.

Claims (8)

  1. The photographic method 1. a kind of unmanned plane is selected a good opportunity automatically, it is characterised in that comprise the following steps：
    1) target face frame center point coordinate (x is set0,y0)；
    2) by Face datection unit, the face in picture is detected in real time, obtains face rectangle frame；
    3) the i-th frame face rectangle frame center point coordinate (x is recordedi,yi), and to its relative target face frame central point (x0,y0) Absolute offset values TiCalculated, if absolute offset values TiNot less than predetermined threshold value t, then step 4) is performed, otherwise performs step 2)；
    4) the i-th frame is detected to the face rectangle frame central point (x obtainedi,yi) with former frame detection obtain face rectangle frame center Point (xi-1,yi-1) compare, calculate interframe face rectangle frame central point offset DiIf interframe offset DiNot less than default threshold Value d, then step 5) is performed, otherwise perform step 2)；
    5) continuously detection k frame pictures meet above-mentioned condition, and system presses shutter automatically, completes action of taking pictures, otherwise performs step 2)。
  2. The photographic method 2. a kind of unmanned plane according to claim 1 is selected a good opportunity automatically, it is characterised in that the target face frame For the human face target position for meeting aesthetic style of systemic presupposition.
  3. The photographic method 3. a kind of unmanned plane according to claim 1 is selected a good opportunity automatically, it is characterised in that right in the step 3) Face rectangle frame center point coordinate (xi,yi) relative target face frame central point (x0,y0) absolute offset values TiCalculated, it is main If calculating the displacement that Face datection unit detects human face region relative target human face region coordinate position in real time, if moved Dynamic distance then represents that current face region is located in target face regional extent no more than predetermined threshold value, if displacement exceedes Predetermined threshold value then represents that current face region is in non-targeted human face region.
  4. The photographic method 4. a kind of unmanned plane according to claim 1 is selected a good opportunity automatically, it is characterised in that the step 4) calculates Face datection unit detects phase of the human face region in the i-th frame data and the coordinate position in (i-1) frame data of acquisition in real time To displacement Di, if displacement be no more than predetermined threshold value if represent that current picture be in stable state, if move away from From then representing to be currently at unstable state more than predetermined threshold value.
  5. The photographic method 5. a kind of unmanned plane according to claim 1 is selected a good opportunity automatically, it is characterised in that the target face frame Center point coordinate offset TiPredetermined threshold value t scopes are between 2-5 pixel coverage.
  6. The photographic method 6. a kind of unmanned plane according to claim 1 is selected a good opportunity automatically, it is characterised in that the face frame center Point coordinates offset DiPredetermined threshold value d scopes should be less than t values.
  7. The photographic method 7. a kind of unmanned plane according to claim 1 is selected a good opportunity automatically, it is characterised in that k in the step 5) Value typically should be greater than being equal to 3.
  8. The photographic method 8. a kind of unmanned plane according to claim 1 is selected a good opportunity automatically, it is characterised in that the Face datection list For member after face is detected, system reconciles parameter of taking pictures automatically, completes focusing step.
CN201710955887.3A 2017-10-14 2017-10-14 A kind of unmanned plane is selected a good opportunity photographic method automatically Pending CN107734254A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710955887.3A CN107734254A (en) 2017-10-14 2017-10-14 A kind of unmanned plane is selected a good opportunity photographic method automatically

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710955887.3A CN107734254A (en) 2017-10-14 2017-10-14 A kind of unmanned plane is selected a good opportunity photographic method automatically

Publications (1)

Publication Number Publication Date
CN107734254A true CN107734254A (en) 2018-02-23

Family

ID=61211410

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710955887.3A Pending CN107734254A (en) 2017-10-14 2017-10-14 A kind of unmanned plane is selected a good opportunity photographic method automatically

Country Status (1)

Country Link
CN (1) CN107734254A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108495031A (en) * 2018-03-22 2018-09-04 广东小天才科技有限公司 Photographing method based on wearable device and wearable device
CN109145751A (en) * 2018-07-23 2019-01-04 安徽淘云科技有限公司 Page turning detection method and device
CN110290307A (en) * 2018-03-19 2019-09-27 东斓视觉科技发展（北京）有限公司 Robot, camera system and its image pickup method
CN112581410A (en) * 2021-02-26 2021-03-30 智己汽车科技有限公司 Image processing method, image processing device, electronic equipment and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100002912A1 (en) * 2005-01-10 2010-01-07 Solinsky James C Facial feature evaluation based on eye location
CN102665032A (en) * 2012-04-17 2012-09-12 西北工业大学 Onboard video image stabilizing method
CN102929288A (en) * 2012-08-23 2013-02-13 山东电力集团公司电力科学研究院 Unmanned aerial vehicle inspection head control method based on visual servo
CN105430262A (en) * 2015-11-17 2016-03-23 小米科技有限责任公司 Photographing control method and photographing control device
CN105487555A (en) * 2016-01-14 2016-04-13 浙江大华技术股份有限公司 Hovering positioning method and hovering positioning device of unmanned aerial vehicle
CN106339006A (en) * 2016-09-09 2017-01-18 腾讯科技（深圳）有限公司 Object tracking method of aircraft and apparatus thereof

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100002912A1 (en) * 2005-01-10 2010-01-07 Solinsky James C Facial feature evaluation based on eye location
CN102665032A (en) * 2012-04-17 2012-09-12 西北工业大学 Onboard video image stabilizing method
CN102929288A (en) * 2012-08-23 2013-02-13 山东电力集团公司电力科学研究院 Unmanned aerial vehicle inspection head control method based on visual servo
CN105430262A (en) * 2015-11-17 2016-03-23 小米科技有限责任公司 Photographing control method and photographing control device
CN105487555A (en) * 2016-01-14 2016-04-13 浙江大华技术股份有限公司 Hovering positioning method and hovering positioning device of unmanned aerial vehicle
CN106339006A (en) * 2016-09-09 2017-01-18 腾讯科技（深圳）有限公司 Object tracking method of aircraft and apparatus thereof

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110290307A (en) * 2018-03-19 2019-09-27 东斓视觉科技发展（北京）有限公司 Robot, camera system and its image pickup method
CN108495031A (en) * 2018-03-22 2018-09-04 广东小天才科技有限公司 Photographing method based on wearable device and wearable device
CN109145751A (en) * 2018-07-23 2019-01-04 安徽淘云科技有限公司 Page turning detection method and device
CN112581410A (en) * 2021-02-26 2021-03-30 智己汽车科技有限公司 Image processing method, image processing device, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
CN107734254A (en) A kind of unmanned plane is selected a good opportunity photographic method automatically
CN105301876B (en) The projecting method and the robot using the method for a kind of intelligence projection robot
AU2011343674B2 (en) Zooming factor computation
CN103607554B (en) It is a kind of based on full-automatic face without the image synthesizing method being stitched into
JP5703448B2 (en) Image display device and image display method
CN106910206B (en) Target tracking method and device
US20140267427A1 (en) Projector, method of controlling projector, and program thereof
CN105120247B (en) A kind of white balance adjustment method and electronic equipment
CN103679166B (en) The method and system of fish eye lens center offset in a kind of quick obtaining equipment
WO2017045326A1 (en) Photographing processing method for unmanned aerial vehicle
US10353403B2 (en) Autonomous flying device, control method of autonomous flying device, and non-transitory recording medium
JP2013257686A5 (en)
CN109981972B (en) Target tracking method of robot, robot and storage medium
CN106973221B (en) Unmanned aerial vehicle camera shooting method and system based on aesthetic evaluation
CN106530239B (en) The mobile target low altitude tracking method of miniature self-service gyroplane based on the bionical flake of big visual field
CN102196240B (en) Pick-up device and method for dynamically sensing monitored object by utilizing same
CN104317385A (en) Gesture identification method and system
CN106875341B (en) Distorted image correction method and positioning method thereof
CN109510949B (en) Camera automatic exposure method based on effective brightness of image feature points
JP2011166305A (en) Image processing apparatus and imaging apparatus
CN104574443B (en) The cooperative tracking method of moving target between a kind of panoramic camera
WO2018014517A1 (en) Information processing method, device and storage medium
WO2022160748A1 (en) Video processing method and apparatus
CN106550227A (en) A kind of image saturation method of adjustment and device
Hulens et al. Autonomous flying cameraman with embedded person detection and tracking while applying cinematographic rules

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20180223