CN103716635A - Method and device for improving intelligent analysis performance - Google Patents
Method and device for improving intelligent analysis performance Download PDFInfo
- Publication number
- CN103716635A CN103716635A CN201310684226.3A CN201310684226A CN103716635A CN 103716635 A CN103716635 A CN 103716635A CN 201310684226 A CN201310684226 A CN 201310684226A CN 103716635 A CN103716635 A CN 103716635A
- Authority
- CN
- China
- Prior art keywords
- interest
- vedio data
- area
- internal memory
- data
- 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.)
- Granted
Links
Images
Abstract
The invention provides a method for improving the intelligent analysis performance. The method is characterized by comprising the following steps: A, a graphics processing unit (GPU) hard-decodes an input compression coding video code stream, and the hard-decoded video image data is stored in a video memory of the GPU; B, according to a preset region of interest, the video image data, corresponding to the region of interest, in the video memory is copied to an internal memory; and C, the video image data in the internal memory is intelligently analyzed. According to the technical scheme of the invention, the advantages of the decoding performance of the GPU is fully utilized, the region of interest is set so that each intelligent recognition algorithm is enabled to acquire original image data of interest, and as only data in the region of interest is copied from the video memory to the internal memory, the data volume is small, thus enhancing the overall intelligent analysis performance.
Description
Technical field
The present invention relates to technical field of video monitoring, relate in particular to a kind of method and apparatus that promotes intellectual analysis performance.
Background technology
Along with the extensive use of video monitoring service, the intellectual analysis of monitor video is more and more ripe, comprises that the virtual line of stumbling detects, amount of exercise detects, human face analysis, and packet loss detection (detects in a region, a kind of intellectual analysis that object suddenly disappears), intensive detection of personnel etc.But the complete intellectual analysis flow process in monitoring field has not only comprised intellectual analysis algorithm, it also comprises the decoding performance of video flowing simultaneously.Lifting along with current field of video monitoring video camera resolution, if 1080P resolution is 1920 * 1080, the about 700Mbps of its decoded 1080P yuv data, even i73770 processor also at full capacity parallel parsing 6 tunnel frame per second be 30 frames, resolution is the video code flow of the H264 of 1080P, very big to cpu performance consumption.
Summary of the invention
In view of this, the invention provides a kind of method and apparatus that promotes intellectual analysis performance.
Method of the present invention comprises the steps: that A, graphic process unit GPU carry out hard decoder to the compressed encoded video code stream of input, and the vedio data after hard decoder is stored in the video memory of described GPU;
B, according to default area-of-interest, vedio data corresponding to this area-of-interest in described video memory copied in internal memory; C, this vedio data in internal memory is carried out to intellectual analysis.
Preferably, before in vedio data corresponding to this area-of-interest in described video memory copied to internal memory, judge that whether the vedio data that this area-of-interest is corresponding needs to carry out transpose process, if so, copies the vedio data of transposition to internal memory; If not, copy this vedio data to internal memory.
Preferably, vedio data corresponding to this area-of-interest in described video memory copied in internal memory and specifically comprised: according to the classification of intellectual analysis, copy the Y component of the vedio data that this area-of-interest is corresponding, U component, V component or its are combined to internal memory.
Preferably, according to this vedio data in internal memory being carried out to the result of intellectual analysis, judge whether further from video memory, to copy the vedio data of another area-of-interest, if, from video memory, copy the vedio data of another area-of-interest, otherwise do not copy; Wherein another area-of-interest is that the positional information obtaining according to described intellectual analysis is determined.
Promote a device for intellectual analysis performance, this device comprises: hard decoder module, and for the compressed encoded video code stream of input is carried out to hard decoder, the vedio data after hard decoder is stored in the video memory of GPU; Data Replica module, for according to default area-of-interest, copies to vedio data corresponding to this area-of-interest in described video memory in internal memory; Intelligent analysis module, carries out intellectual analysis for this vedio data to internal memory.
Preferably, this device further comprises transposition judge module; Before in vedio data corresponding to this area-of-interest in described video memory copied to internal memory, transposition judge module judges whether the vedio data that this area-of-interest is corresponding needs to carry out transpose process, if so the vedio data that, data Replica module copies transposition is to internal memory; If not, data Replica module copies this vedio data to internal memory.
Preferably, data Replica module copies to concrete execution as follows in internal memory by vedio data corresponding to this area-of-interest in described video memory and operates: according to the classification of intellectual analysis, copy the Y component of the vedio data that this area-of-interest is corresponding, U component, V component or its are combined to internal memory.
Preferably, data Replica module is according to this vedio data in internal memory being carried out to the result of intellectual analysis, judge whether further from video memory, to copy the vedio data of another area-of-interest, if, from video memory, copy the vedio data of another area-of-interest, otherwise do not copy; Wherein another area-of-interest is that the positional information obtaining according to described intellectual analysis is determined.
Compared to prior art, technical solution of the present invention makes full use of the decoding performance advantage of GPU, by each Intelligent Recognition algorithm after area-of-interest being set, making decoding, can both obtain own interested original image data, and be only the data of area-of-interest due to what copy between video memory and internal memory, so data volume is smaller, thereby promoted on the whole the performance of intellectual analysis.
Accompanying drawing explanation
Fig. 1 is the flow chart of embodiment mono-.
Fig. 2 is the flow chart of embodiment bis-.
Fig. 3 is the flow chart of embodiment tri-.
Fig. 4 is area-of-interest exemplary plot.
Fig. 5 is the area-of-interest exemplary plot after transposition.
Fig. 6 is another area-of-interest exemplary plot.
Fig. 7 is apparatus of the present invention logic diagrams.
Embodiment
Technical solution of the present invention makes full use of the decoding performance advantage of GPU, by each Intelligent Recognition algorithm after area-of-interest being set, making decoding, can both obtain own interested original image data (without the loss of primary data information (pdi)), the direct data copy number of video memory and internal memory is little, thereby can significantly improve the performance of intellectual analysis; And a plurality of intelligent algorithms can common memory, makes the memory consumption of whole scheme also minimum; And owing to treating that the original video data information of intellectual analysis does not have to lose, so can adapt to various intellectual analysis.Below in conjunction with embodiment, describe technical solution of the present invention in detail.
Embodiment mono-
Please refer to the drawing 1, the method for the lifting intellectual analysis performance of the present embodiment, comprises the steps:
S11, graphic process unit GPU carry out hard decoder to the compressed encoded video code stream of input, and the vedio data after hard decoder is stored in the video memory of described GPU.
S12, according to default area-of-interest, vedio data corresponding to this area-of-interest in described video memory copied in internal memory.
S13, this vedio data in internal memory is carried out to intellectual analysis.
The video code flow Yi Zhengwei unit input intellectual analysis equipment of compressed encoding, the GPU of this intellectual analysis equipment decodes to each frame compressed encoded video view data of input, and the vedio data obtaining after decoding is stored in the video memory of this GPU.Decoded vedio data is all generally that the form of Y component with yuv space, U component, V component exists.Because this decode procedure belongs to hard decoder, so performance is very high.Above-mentioned intellectual analysis equipment can be an independent physical equipment, can be to be also present on other physical equipments as a logic entity.
After having decoded, the vedio data in video memory need to be copied in internal memory, CPU could carry out intellectual analysis to decoded vedio data like this.CPU, when carrying out intellectual analysis, may only need to be used local vedio data.Such as, when mixing line detection, only need to use and mix near some vedio datas of line; When carrying out the detection of people's face, may only need to use the vedio data that people's face is corresponding.So only the partial video view data in video memory need to be copied in internal memory from this point of view.In the time of specific implementation, user can pre-determine the area-of-interest of intellectual analysis, when then vedio data copies in carrying out video memory, only copies the vedio data of area-of-interest.The mode that user presets area-of-interest belongs to prior art, does not repeat them here; Corresponding vedio data in the area-of-interest how to confirm video memory that intellectual analysis equipment is set according to user also belongs to prior art, no longer further describes.
After the vedio data of area-of-interest is copied in internal memory, CPU carries out intellectual analysis to the vedio data in internal memory.
Although the vedio data data volume being kept at after decoding in video memory is larger, owing to copying to, in internal memory, be only the data that area-of-interest is corresponding, so data volume will can be very not large, to the performance of whole intellectual analysis, will be significantly improved; And the data of copy belong to the raw video image data without information dropout, and the result of intellectual analysis will be more accurate.
Embodiment bis-
On the basis at above-described embodiment one, further improve the performance of intellectual analysis, the embodiment of the present invention two has increased the whether processing of vedio data transposition.The flow process of please refer to the drawing 2:
S21, graphic process unit GPU carry out hard decoder to the compressed encoded video code stream of input, and the vedio data after hard decoder is stored in the video memory of described GPU.
S22, according to default area-of-interest, judge whether the vedio data that in video memory, this area-of-interest is corresponding needs to carry out transpose process, if so, execution step S23, otherwise, execution step S24.
S23, copy transposition the vedio data of area-of-interest to internal memory.
S24, copy this this area-of-interest vedio data to internal memory.
S25, this vedio data in internal memory is carried out to intellectual analysis.
Judge whether above-mentioned vedio data needs the principle of carrying out transpose process to be: if the data volume after transposition is less than the data volume before transposition, carry out transposition, otherwise do not carry out transposition.
Take and mix line and detect this intellectual analysis as example.Please refer to the drawing 4, user paints one and is equivalent to determine area-of-interest after mixing line in monitoring image, because the coordinate information that intellectual analysis equipment can be mixed line according to this is determined the scope of area-of-interest.Such as the solid-line rectangle frame in Fig. 4 is equivalent to the definite area-of-interest of user.When execution copies to internal memory by the vedio data in this area-of-interest, what in fact copy is the vedio data in dotted rectangle.If but the vedio data in solid-line rectangle frame were carried out to transposition, the video image after please refer to the drawing 5 transposition, could obviously find out that data volume is less than the vedio data before transposition.So need to copy in this case, the vedio data of the area-of-interest of transposition, to internal memory, for CPU, carry out the intellectual analysis that the line of stumbling detects.
In the situation that needs are carried out transpose process, the vedio data that copies the area-of-interest of transposition has further reduced the data volume of copy to internal memory, also can reduce the operand of follow-up Intelligent Recognition algorithm, so this has further played to performance the effect promoting simultaneously.
For embodiment mono-and two, can also further according to the classification of intellectual analysis, copy Y component, the U component of area-of-interest vedio data, V component or its are combined to internal memory.Such as, for mixing line, detect, due to its monochrome information that needs to pay close attention to the line periphery of stumbling, do not need to pay close attention to chromatic component, so when carrying out data Replica, only need to copy the Y component (brightness data) of area-of-interest vedio data; Such as for the detection of color, can only copy U component and V component.That is to say, for further reducing the amount of copying of data, can, according to actual Intelligent Recognition algorithm needs, carry out copying of corresponding vector.So just there are six kinds of situations: copy Y component, or U component, or V component, or YU component, or YV component, or UV component, or YUV component.
Embodiment tri-
Embodiment tri-relates generally to the problem of further returning to the vedio data that copies another area-of-interest according to the analysis result of area-of-interest vedio data.Please refer to the drawing 3, the handling process of this embodiment is as follows:
S31, graphic process unit GPU carry out hard decoder to the compressed encoded video code stream of input, and the vedio data after hard decoder is stored in the video memory of described GPU.
S32, according to default area-of-interest, vedio data corresponding to this area-of-interest in described video memory copied in internal memory.
S33, this area-of-interest vedio data in internal memory is carried out to intellectual analysis.
S34, according to intellectual analysis result, judge whether further from video memory, to copy the vedio data of another area-of-interest, if so, carry out S35, otherwise carry out S36.
S35, from video memory, copy the vedio data of another area-of-interest, wherein this another area-of-interest is to determine according to the positional information that in step S33, intellectual analysis obtains, and turns S37.
S36, no longer from video memory, copy the vedio data of another area-of-interest.
S37, the vedio data of this another area-of-interest in internal memory is carried out to intellectual analysis.
An example application of this embodiment is: for car plate identification, first carry out and mix line detection, if testing result is for there being vehicle to cross the line of stumbling, further carry out the car plate identification to this vehicle.For this application, just can consider to use the method for embodiment tri-.
In step S34, the result of this intellectual analysis, such as have vehicle to cross the line of stumbling, need further to carry out car plate identification; Now need further according to the result of intellectual analysis, be whether to exist in the current internal memory of vedio data of needed another area-of-interest of car plate identification, if existed, without further copy the vedio data of another area-of-interest from video memory; If there is no, need further from video memory, to copy the vedio data of another area-of-interest.For determining of another area-of-interest position, can rely on the positional information that in step S33, intellectual analysis obtains determines.Please refer to the drawing 6, in the example of Fig. 6, mix line detection and the positional information (as A point in figure) that vehicle triggers the line of stumbling detected, now can determine according to this positional information the coordinate information in the region (as dotted rectangle in Fig. 6) of carrying out car plate identification, the i.e. coordinate information of another area-of-interest.Because car plate identification needs the data that resolution is higher conventionally, so directly copy the decoded original video data (with respect to further carrying out the data that compressed encoding obtains small in resolution after decoding) of area-of-interest, will contribute to carry out this car plate identification; And if the vedio data of needed another area-of-interest of car plate identification exists in current internal memory, before and after twice intellectual analysis vedio data in can common memory, the memory consumption of whole like this scheme is by smaller.
The vedio data of the area-of-interest copying in the vedio data of another area-of-interest copying from video memory in step S35 in the present embodiment and step S32 is with respect to same frame video image data, and what only copy is the data of diverse location in these frame data.
It should be noted that, in embodiment tri-, also can increase transpose process whether judgement and copy Y component, U component according to Intelligent Recognition classification, V component or its are combined to the processing of internal memory.
Design based on same, the present invention also provides a kind of device that promotes intellectual analysis performance.Please refer to the drawing 7, this device comprises: hard decoder module, data Replica module, transposition judge module and intelligent analysis module.
This hard decoder module, carries out hard decoder for GPU to the compressed encoded video code stream of input, and the vedio data after hard decoder is stored in the video memory of GPU; Data Replica module, for according to default area-of-interest, copies to vedio data corresponding to this area-of-interest in described video memory in internal memory, for CPU, this vedio data is carried out to intellectual analysis; Intelligent analysis module, carries out intellectual analysis for this vedio data to internal memory.
Before in vedio data corresponding to this area-of-interest in described video memory copied to internal memory, transposition judge module judges whether the vedio data that this area-of-interest is corresponding needs to carry out transpose process, if so, the vedio data of data Replica module reproducing unit to internal memory; If not, data Replica module directly copies this vedio data to internal memory.
The vedio data that copies transposition can further promote the performance of intellectual analysis to internal memory, plays the effect of further optimization.
Data Replica module copies to concrete execution as follows in internal memory by vedio data corresponding to this area-of-interest in described video memory and operates: according to the classification of intellectual analysis, copy the Y component of the vedio data that this area-of-interest is corresponding, U component, V component or its are combined to internal memory.
Data Replica module is according to this vedio data in internal memory being carried out to the result of intellectual analysis, judge whether further from video memory, to copy the vedio data of another area-of-interest, if, from video memory, copy the vedio data of another area-of-interest, otherwise do not copy; Wherein another area-of-interest is that the positional information obtaining according to described intellectual analysis is determined.
The foregoing is only preferred embodiment of the present invention, in order to limit the present invention, within the spirit and principles in the present invention not all, any modification of making, be equal to replacement, improvement etc., within all should being included in the scope of protection of the invention.
Claims (8)
1. a method that promotes intellectual analysis performance, is characterized in that, the method comprises the steps:
A, graphic process unit GPU carry out hard decoder to the compressed encoded video code stream of input, and the vedio data after hard decoder is stored in the video memory of described GPU;
B, according to default area-of-interest, vedio data corresponding to this area-of-interest in described video memory copied in internal memory;
C, this vedio data in internal memory is carried out to intellectual analysis.
2. the method for claim 1, it is characterized in that, before in vedio data corresponding to this area-of-interest in described video memory copied to internal memory, judge whether the vedio data that this area-of-interest is corresponding needs to carry out transpose process, if so the vedio data that, copies transposition is to internal memory; If not, copy this vedio data to internal memory.
3. method as claimed in claim 1 or 2, it is characterized in that, vedio data corresponding to this area-of-interest in described video memory copied in internal memory and specifically comprised: according to the classification of intellectual analysis, copy the Y component of the vedio data that this area-of-interest is corresponding, U component, V component or its are combined to internal memory.
4. the method for claim 1, it is characterized in that, according to this vedio data in internal memory being carried out to the result of intellectual analysis, judge whether further from video memory, to copy the vedio data of another area-of-interest, if, from video memory, copy the vedio data of another area-of-interest, otherwise do not copy; Wherein another area-of-interest is that the positional information obtaining according to described intellectual analysis is determined.
5. a device that promotes intellectual analysis performance, is characterized in that, this device comprises:
Hard decoder module, carries out hard decoder for GPU to the compressed encoded video code stream of input, and the vedio data after hard decoder is stored in the video memory of this GPU;
Data Replica module, for according to default area-of-interest, copies to vedio data corresponding to this area-of-interest in described video memory in internal memory, for CPU, this vedio data is carried out to intellectual analysis;
Intelligent analysis module, carries out intellectual analysis for this vedio data to internal memory.
6. device as claimed in claim 5, is characterized in that, this device further comprises transposition judge module;
Before in vedio data corresponding to this area-of-interest in described video memory copied to internal memory, transposition judge module judges whether the vedio data that this area-of-interest is corresponding needs to carry out transpose process, if so the vedio data that, data Replica module copies transposition is to internal memory; If not, data Replica module copies this vedio data to internal memory.
7. the device as described in claim 5 or 6, it is characterized in that, data Replica module copies to concrete execution as follows in internal memory by vedio data corresponding to this area-of-interest in described video memory and operates: according to the classification of intellectual analysis, copy the Y component of the vedio data that this area-of-interest is corresponding, U component, V component or its are combined to internal memory.
8. device as claimed in claim 5, it is characterized in that, data Replica module is according to this vedio data in internal memory being carried out to the result of intellectual analysis, judge whether further from video memory, to copy the vedio data of another area-of-interest, if, from video memory, copy the vedio data of another area-of-interest, otherwise do not copy; Wherein another area-of-interest is that the positional information obtaining according to described intellectual analysis is determined.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310684226.3A CN103716635B (en) | 2013-12-12 | 2013-12-12 | Method and device for improving intelligent analysis performance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310684226.3A CN103716635B (en) | 2013-12-12 | 2013-12-12 | Method and device for improving intelligent analysis performance |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103716635A true CN103716635A (en) | 2014-04-09 |
| CN103716635B CN103716635B (en) | 2017-04-19 |
Family
ID=50409140
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310684226.3A Active CN103716635B (en) | 2013-12-12 | 2013-12-12 | Method and device for improving intelligent analysis performance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103716635B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104063313A (en) * | 2014-04-15 | 2014-09-24 | 深圳英飞拓科技股份有限公司 | Intelligent analytical algorithm test system and method |
| CN108206937A (en) * | 2016-12-20 | 2018-06-26 | 浙江宇视科技有限公司 | A kind of method and apparatus for promoting intellectual analysis performance |
| CN110691224A (en) * | 2019-10-31 | 2020-01-14 | 上海电力大学 | Transformer substation perimeter video intelligent detection system |
| CN112040148A (en) * | 2020-09-02 | 2020-12-04 | 北京锐马视讯科技有限公司 | Video value-added service method, device and storage medium |
| CN114143595A (en) * | 2021-12-08 | 2022-03-04 | 珠海豹趣科技有限公司 | Video wallpaper playing method and device, electronic equipment and readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101261683A (en) * | 2008-03-26 | 2008-09-10 | 北京航空航天大学 | A vehicle detection method based on color video |
| CN101908035A (en) * | 2010-07-30 | 2010-12-08 | 北京华傲精创科技开发有限公司 | Video coding and decoding method, GPU (Graphics Processing Unit) as well as interacting method and system of same and CPU (Central Processing Unit) |
| CN102034265A (en) * | 2010-11-24 | 2011-04-27 | 清华大学 | Three-dimensional view acquisition method |
| CN102143386A (en) * | 2010-01-28 | 2011-08-03 | 复旦大学 | Streaming media server acceleration method based on graphics processing unit |
| CN102695040A (en) * | 2012-05-03 | 2012-09-26 | 中兴智能交通（无锡）有限公司 | Parallel high definition video vehicle detection method based on GPU |
| WO2013097098A1 (en) * | 2011-12-27 | 2013-07-04 | 华为技术有限公司 | Data processing method, graphics processing unit (gpu) and first node device |
-
2013
- 2013-12-12 CN CN201310684226.3A patent/CN103716635B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101261683A (en) * | 2008-03-26 | 2008-09-10 | 北京航空航天大学 | A vehicle detection method based on color video |
| CN102143386A (en) * | 2010-01-28 | 2011-08-03 | 复旦大学 | Streaming media server acceleration method based on graphics processing unit |
| CN101908035A (en) * | 2010-07-30 | 2010-12-08 | 北京华傲精创科技开发有限公司 | Video coding and decoding method, GPU (Graphics Processing Unit) as well as interacting method and system of same and CPU (Central Processing Unit) |
| CN102034265A (en) * | 2010-11-24 | 2011-04-27 | 清华大学 | Three-dimensional view acquisition method |
| WO2013097098A1 (en) * | 2011-12-27 | 2013-07-04 | 华为技术有限公司 | Data processing method, graphics processing unit (gpu) and first node device |
| CN102695040A (en) * | 2012-05-03 | 2012-09-26 | 中兴智能交通（无锡）有限公司 | Parallel high definition video vehicle detection method based on GPU |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104063313A (en) * | 2014-04-15 | 2014-09-24 | 深圳英飞拓科技股份有限公司 | Intelligent analytical algorithm test system and method |
| CN108206937A (en) * | 2016-12-20 | 2018-06-26 | 浙江宇视科技有限公司 | A kind of method and apparatus for promoting intellectual analysis performance |
| CN108206937B (en) * | 2016-12-20 | 2020-05-19 | 浙江宇视科技有限公司 | Method and device for improving intelligent analysis performance |
| CN110691224A (en) * | 2019-10-31 | 2020-01-14 | 上海电力大学 | Transformer substation perimeter video intelligent detection system |
| CN112040148A (en) * | 2020-09-02 | 2020-12-04 | 北京锐马视讯科技有限公司 | Video value-added service method, device and storage medium |
| CN114143595A (en) * | 2021-12-08 | 2022-03-04 | 珠海豹趣科技有限公司 | Video wallpaper playing method and device, electronic equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103716635B (en) | 2017-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10477249B2 (en) | Video processing for masking coding artifacts using dynamic noise maps | |
| AU2020207857B2 (en) | Image encoding method and apparatus, and image decoding method and apparatus | |
| US8804827B2 (en) | Encoding or decoding method and apparatus | |
| CN103716635A (en) | Method and device for improving intelligent analysis performance | |
| CN103702124B (en) | A kind of transcoding accelerated method and transcoder | |
| US10397574B2 (en) | Video coding quantization parameter determination suitable for video conferencing | |
| US20100128798A1 (en) | Video processor using optimized macroblock sorting for slicemap representations | |
| US10051271B2 (en) | Coding structure | |
| US9609338B2 (en) | Layered video encoding and decoding | |
| TW201448571A (en) | Adaptive filtering mechanism to remove encoding artifacts in video data | |
| US10148935B2 (en) | Depth picture inter encoding and decoding method, encoder and decoder | |
| WO2016065872A1 (en) | Image prediction method and relevant device | |
| US20190313111A1 (en) | Adaptive thresholding for computer vision on low bitrate compressed video streams | |
| US20220116627A1 (en) | Method and apparatus in video coding for machines | |
| US20130235931A1 (en) | Masking video artifacts with comfort noise | |
| CN114339238A (en) | Video coding method, video decoding method and device thereof | |
| JP2009522650A (en) | Hardware motion compensation in video recording | |
| EP3207705B1 (en) | Method for color mapping a video signal based on color mapping data and method of encoding a video signal and color mapping data and corresponding devices and storage media having a signal encoded thereupon | |
| US20150264345A1 (en) | Method for Coding Videos and Pictures Using Independent Uniform Prediction Mode | |
| CN103929640A (en) | Techniques For Managing Video Streaming | |
| WO2018038316A1 (en) | Method and device for transmitting block division information in image codec for security camera | |
| US20100158105A1 (en) | Post-processing encoding system and method | |
| CN103051891A (en) | Method and device for determining a saliency value of a block of a video frame block-wise predictive encoded in a data stream | |
| CN110740316A (en) | Data coding method and device | |
| US11164328B2 (en) | Object region detection method, object region detection apparatus, and non-transitory computer-readable medium thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |