EP3180739A2 - Detection of action frames of a video stream - Google Patents
Detection of action frames of a video streamInfo
- Publication number
- EP3180739A2 EP3180739A2 EP15756717.3A EP15756717A EP3180739A2 EP 3180739 A2 EP3180739 A2 EP 3180739A2 EP 15756717 A EP15756717 A EP 15756717A EP 3180739 A2 EP3180739 A2 EP 3180739A2
- Authority
- EP
- European Patent Office
- Prior art keywords
- image frame
- frame
- motion
- image
- trigger
- 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.)
- Ceased
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/44—Event detection
Definitions
- FIG. 7 illustrates an example of FIG. 6 where subsets of regions are indicated as neighborhoods
- FIG. 20 is a diagram of a method of operation at an electronic device of one or more of the systems disclosed herein;
- the JPEG compression engine 125a when the JPEG compression engine 125a is to compress a frame of a video clip, the JPEG compression engine 125a may receive the data for the frame of the video clip directly from the video encoder 125b or the ISP 110, and direct the compressed output of the frame to the DDR memory 130 and further to the storage SD card 135.
- the ISP 110 may receive image frames 202 from the imaging system 105.
- the image frames 202 may correspond to a video stream.
- the ISP 110 may generate second image frames from the image frames 202.
- the second image frames may be a lower resolution copy of the image frames 202.
- the ISP 110 may provide the image frames 202 to the ZSL picture buffer 120a and may provide the second image frames to the video buffer 120b.
- the image frames 202 may include a first image frame 204.
- the second image frames may include a second image frame 206.
- the first image frame 204 may represent a first camera view that is substantially the same as a second camera view represented by the second image frame 206.
- the trigger detector 215 may detect a trigger (or designate the second image frame 206 as an action frame) by analyzing the second image frame 206 based on the ISP statistics received from the ISP 110, the video statistics (e.g., MB statistics) received from the video encoder 125b, audio data received from the audio signal processor 208, or a combination thereof, as described herein.
- the audio data may indicate a characteristic (e.g., the signal energy data) of the audio samples.
- the trigger detector 215 may update a trigger detection threshold based on the characteristic of the audio samples, as described with reference to FIG. 24.
- the trigger detector 215 may detect the trigger in response to determining that motion data associated with the second image frame 206 satisfies a threshold value (e.g., the trigger detection threshold), as described with reference to FIGS. 3-4, 13-14, 17, and 24.
- a threshold value e.g., the trigger detection threshold
- the processor 115 may designate the second image frame 206 as a non-key frame (e.g., not an action frame) or use another algorithm to analyze the second image frame 206. For example, the processor 115 may designate the second image frame 206 as a non-key frame in response to determining that, for each MB, either a size of a corresponding subset for the MB is less than or equal to half of the size of a kernel, or that a corresponding motion vector length for the MB is less than or equal to the threshold value.
- the method 1300 may be used to perform motion detection using a micro-kernel (e.g., a small neighborhood of macro-blocks). Using a micro-kernel may enable motion detection of small objects. The method 1300 may be used to identify an image frame corresponding to a dynamic event that includes motion associated with small objects.
- a micro-kernel e.g., a small neighborhood of macro-blocks.
- the method 1400 further includes, in response to determining that the connected component size satisfies the connected component threshold, at 1412, designating the frame as a key frame, at 1414.
- the processor 115 of FIG. 1 may designate the second image frame 206 as a key frame (e.g., an action frame) in response to determining that the connected component size satisfies the connected component threshold.
- the processor 115 may detect a trigger in the second image frame 206 in response to determining that the connected component size satisfies the connected component threshold.
- the processor 115 may refrain from detecting a trigger in the second image frame 206 in response to determining that the second image frame 206 is a non-key frame.
- the processor 115 may, in response to determining that the second image frame 206 is a non-key frame, generate a trigger notification indicating that the second image frame 206 is a non-key frame (e.g., not an action frame).
- the group score may be an average of the frame scores of the image frames.
- the group score may indicate a level of motion activity corresponding to the temporal group.
- a higher group score may indicate a higher level of motion activity.
- the temporal groups may be prioritized based on corresponding group scores. For example, a first temporal group having a first group score may have a higher priority than a second temporal group having a second group score that is lower than the first group score.
- Image frames may be deleted based on priority (e.g., group scores, frame scores, or both). For example, an image frame from the second temporal group may be deleted prior to deletion of an image frame from the first temporal group. As another example, a first image frame having a first frame score may be deleted prior to deletion of a second image frame having a second frame score that is higher than the first frame score.
- the comparator 1508 may adjust a signal energy threshold based on the noise estimate data. For example, the comparator 1508 may decrease the signal energy threshold in response to determining that the noise estimate data indicates a noise level that is greater than a threshold noise level.
- the comparator 1508 may generate an audio level trigger 1510 in response to determining that a signal energy indicated by the signal energy data satisfies the signal energy threshold.
- the audio level trigger 1510 may indicate whether the signal energy satisfies the signal energy threshold.
- the trigger detector 215 may determine whether a trigger is detected based on the audio level trigger 1510, as described with reference to FIG. 17.
- the tracker 2110 may provide the trigger notification to the trigger JPEG snapshot.
- the tracker 2110 may generate the trigger notification in response to detecting a sudden movement in a head/eye direction of the user.
- the trigger notification may include the first timestamps of the user images.
- the trigger JPEG snapshot 2116 may access the first image frame 204 in response to determining that a timestamp of the first image frame 204 is within a threshold duration of the first timestamps of the user images.
- the method 2200 also includes storing, at the device, the first image frame in a first memory after receiving the first image frame, at 2204.
- the ISP 110 may store the first image frame 204 in the ZSL picture buffer 120a, the DDR memory 121, or both, after receiving the first image frame 204.
- the method 2400 also includes receiving audio data at the device, at 2404.
- the trigger detector 215 of FIG. 2 may receive audio data, as described with reference to FIGS. 2 and 15-17.
- the audio data may correspond to the video stream.
- the audio data may correspond to the image frames 202, as described with reference to FIG. 2.
- an apparatus includes means for storing a plurality of image frames corresponding to a video stream.
- the means for storing may include the ZSL picture buffer 120a, the DDR memory 121, the video buffer 120b, the DDR memory 130, the SD card 135, the device 100 of FIG. 1, the device 200 of FIG. 2, the device 1500 of FIG. 15, the device 1600 of FIG. 16, the device 1700 of FIG. 17, the device 2100 of FIG. 21, the memory 2632, one or more other devices, circuits, modules, or instructions configured to store a plurality of image frames, or a combination thereof.
- a computer-readable medium may be tangible and non-transitory.
- computer-program product refers to a computing device or processor in combination with code or instructions (e.g., a "program”) that may be executed, processed or computed by the computing device or processor.
- code may refer to software, instructions, code or data that is/are executable by a computing device or processor.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Studio Devices (AREA)
- Image Analysis (AREA)
- Television Signal Processing For Recording (AREA)
- Compression Or Coding Systems Of Tv Signals (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP20189585.1A EP3855350A1 (en) | 2014-08-14 | 2015-08-11 | Detection of action frames of a video stream |
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
IN3985CH2014 | 2014-08-14 | ||
US14/728,047 US9715903B2 (en) | 2014-06-16 | 2015-06-02 | Detection of action frames of a video stream |
PCT/US2015/044660 WO2016025485A2 (en) | 2014-08-14 | 2015-08-11 | Detection of action frames of a video stream |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP20189585.1A Division EP3855350A1 (en) | 2014-08-14 | 2015-08-11 | Detection of action frames of a video stream |
Publications (1)
Publication Number | Publication Date |
---|---|
EP3180739A2 true EP3180739A2 (en) | 2017-06-21 |
Family
ID=55304752
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP15756717.3A Ceased EP3180739A2 (en) | 2014-08-14 | 2015-08-11 | Detection of action frames of a video stream |
EP20189585.1A Pending EP3855350A1 (en) | 2014-08-14 | 2015-08-11 | Detection of action frames of a video stream |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP20189585.1A Pending EP3855350A1 (en) | 2014-08-14 | 2015-08-11 | Detection of action frames of a video stream |
Country Status (3)
Country | Link |
---|---|
EP (2) | EP3180739A2 (zh) |
CN (2) | CN111540387B (zh) |
WO (1) | WO2016025485A2 (zh) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108289191B (zh) * | 2017-02-15 | 2020-01-10 | 腾讯科技(深圳)有限公司 | 图像识别方法及装置 |
GB2575852B (en) * | 2018-07-26 | 2021-06-09 | Advanced Risc Mach Ltd | Image processing |
Family Cites Families (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6813372B2 (en) * | 2001-03-30 | 2004-11-02 | Logitech, Inc. | Motion and audio detection based webcamming and bandwidth control |
US7027513B2 (en) * | 2003-01-15 | 2006-04-11 | Microsoft Corporation | Method and system for extracting key frames from video using a triangle model of motion based on perceived motion energy |
JP4053490B2 (ja) * | 2003-03-25 | 2008-02-27 | 株式会社東芝 | フレーム補間のための補間画像作成方法及びこれを用いた画像表示システム、補間画像作成装置 |
JP2006174415A (ja) * | 2004-11-19 | 2006-06-29 | Ntt Docomo Inc | 画像復号装置、画像復号プログラム、画像復号方法、画像符号化装置、画像符号化プログラム及び画像符号化方法 |
CA2674830A1 (en) * | 2007-01-05 | 2008-07-17 | Nestor, Inc. | Video speed detection system |
US7925112B2 (en) * | 2007-02-28 | 2011-04-12 | Honeywell International Inc. | Video data matching using clustering on covariance appearance |
US9584710B2 (en) * | 2008-02-28 | 2017-02-28 | Avigilon Analytics Corporation | Intelligent high resolution video system |
US9251423B2 (en) * | 2008-03-21 | 2016-02-02 | Intel Corporation | Estimating motion of an event captured using a digital video camera |
US8284249B2 (en) * | 2008-03-25 | 2012-10-09 | International Business Machines Corporation | Real time processing of video frames for triggering an alert |
US8121424B2 (en) * | 2008-09-26 | 2012-02-21 | Axis Ab | System, computer program product and associated methodology for video motion detection using spatio-temporal slice processing |
CN101924923B (zh) * | 2010-08-03 | 2013-01-09 | 杭州翰平电子技术有限公司 | 嵌入式智能自动变焦抓拍方法 |
WO2012027893A1 (en) * | 2010-09-02 | 2012-03-08 | Intersil Americas Inc. | Systems and methods for video content analysis |
CN101996410B (zh) * | 2010-12-07 | 2012-12-12 | 北京交通大学 | 动态背景下的运动目标检测方法及系统 |
US9311271B2 (en) * | 2010-12-15 | 2016-04-12 | Andrew William Wright | Method and system for logging vehicle behavior |
CN102685574A (zh) * | 2011-03-09 | 2012-09-19 | 须泽中 | 从数字电视节目中自动抽取图像的系统及其应用 |
EP2798519A4 (en) * | 2011-12-27 | 2015-10-21 | Eye Stalks Corp | METHOD AND APPARATUS FOR VISUAL FOLLOW-UP |
US9225904B2 (en) * | 2012-02-13 | 2015-12-29 | Htc Corporation | Image capture method and image capture system thereof |
US10713499B2 (en) * | 2012-04-23 | 2020-07-14 | Conduent Business Services, Llc | Real-time video triggering for traffic surveillance and photo enforcement applications using near infrared video acquisition |
EP2662827B1 (en) * | 2012-05-08 | 2016-01-13 | Axis AB | Video analysis |
CN103428483B (zh) * | 2012-05-16 | 2017-10-17 | 华为技术有限公司 | 一种媒体数据处理方法及设备 |
US9131143B2 (en) * | 2012-07-20 | 2015-09-08 | Blackberry Limited | Dynamic region of interest adaptation and image capture device providing same |
-
2015
- 2015-08-11 EP EP15756717.3A patent/EP3180739A2/en not_active Ceased
- 2015-08-11 WO PCT/US2015/044660 patent/WO2016025485A2/en active Application Filing
- 2015-08-11 CN CN202010396251.1A patent/CN111540387B/zh active Active
- 2015-08-11 CN CN201580042994.6A patent/CN106575359B/zh active Active
- 2015-08-11 EP EP20189585.1A patent/EP3855350A1/en active Pending
Non-Patent Citations (1)
Title |
---|
None * |
Also Published As
Publication number | Publication date |
---|---|
CN111540387B (zh) | 2022-03-22 |
WO2016025485A2 (en) | 2016-02-18 |
CN106575359B (zh) | 2020-05-19 |
CN111540387A (zh) | 2020-08-14 |
CN106575359A (zh) | 2017-04-19 |
EP3855350A1 (en) | 2021-07-28 |
WO2016025485A3 (en) | 2016-04-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9715903B2 (en) | Detection of action frames of a video stream | |
US10706892B2 (en) | Method and apparatus for finding and using video portions that are relevant to adjacent still images | |
JP2023526207A (ja) | フレーム中の標的物体を一定のサイズに維持すること | |
US9426409B2 (en) | Time-lapse video capture with optimal image stabilization | |
KR102090105B1 (ko) | 카메라를 구비하는 장치의 이미지 처리장치 및 방법 | |
JP5833137B2 (ja) | 失敗したフレームを削除するためのビデオ編集デバイス | |
US20100188511A1 (en) | Imaging apparatus, subject tracking method and storage medium | |
WO2012106314A2 (en) | Estimating subject motion between image frames | |
ITVI20120104A1 (it) | Metodo e apparato per generare in tempo reale uno storyboard visuale | |
JP2010258710A5 (zh) | ||
US20120019685A1 (en) | Image capturing device, image capturing method, program, and integrated circuit | |
JP6892524B2 (ja) | 対象追跡に基づくスローモーションビデオキャプチャ | |
JP2012239085A (ja) | 画像処理装置、画像処理方法 | |
US9799376B2 (en) | Method and device for video browsing based on keyframe | |
JP2018535572A (ja) | カメラプレビュー | |
KR20100138168A (ko) | 영상감시 시스템 및 그 시스템의 영상감시방법 | |
JP2013239796A (ja) | 画像処理装置 | |
EP3855350A1 (en) | Detection of action frames of a video stream | |
US20160295064A1 (en) | Photo cluster detection and compression | |
US10230955B2 (en) | Method and system to detect and utilize attributes of frames in video sequences | |
JP2007006385A (ja) | 撮像装置、画像記録装置、制御方法、およびプログラム | |
JP2016201617A (ja) | 動画像再生装置および方法 | |
JP2010074315A (ja) | 被写体追尾方法及び撮像装置 | |
US9282306B2 (en) | Imaging device, information processing device, and non-transitory computer readable medium storing program | |
KR20100118811A (ko) | 감시 카메라 시스템의 관리를 위한 장면 전환 검출 방법과 장면 전환 검출 신뢰도 산출 방법 및 소프트웨어 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
17P | Request for examination filed |
Effective date: 20170213 |
|
AK | Designated contracting states |
Kind code of ref document: A2 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
AX | Request for extension of the european patent |
Extension state: BA ME |
|
DAV | Request for validation of the european patent (deleted) | ||
DAX | Request for extension of the european patent (deleted) | ||
17Q | First examination report despatched |
Effective date: 20180626 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R003 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION HAS BEEN REFUSED |
|
18R | Application refused |
Effective date: 20200514 |