CN105072324A - Falling detection law enforcement recorder and falling detection method - Google Patents
Falling detection law enforcement recorder and falling detection method Download PDFInfo
- Publication number
- CN105072324A CN105072324A CN201510501918.9A CN201510501918A CN105072324A CN 105072324 A CN105072324 A CN 105072324A CN 201510501918 A CN201510501918 A CN 201510501918A CN 105072324 A CN105072324 A CN 105072324A
- Authority
- CN
- China
- Prior art keywords
- image
- law
- moment
- enforcing recorder
- current time
- 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
Abstract
The invention discloses a falling detection law enforcement recorder and a falling detection method. The law enforcement recorder comprises an imaging module, an acquisition module, a storage module and a detection module, wherein the imaging module is used for acquiring a video signal around the law enforcement recorder; the acquisition module is used for acquiring a first image at a first moment and a second image at a second moment from the video signal; the storage module is used for storing the first image and the second image; and the detection module is used for judging whether or not the law enforcement recorder is in a falling state, and judging that the law enforcement recorder is in a falling state if the vertical similarity between the first image and the second image is smaller than a similarity threshold and the time difference between the first moment and the second moment is smaller than a time threshold. The images are used for identifying whether or not the law enforcement recorder is in the falling state, so that the aim of rapidly saving law enforcement evidence is fulfilled.
Description
Technical field
The present invention relates to one fall detection law-enforcing recorder and fall detection method.
Background technology
Whether traditional product is all carry out testing product by gravity sensing device to there occurs and fall, but for itself not having the product of gravity sensing device, such as existing law-enforcing recorder, additionally to the trouble that its increase electronic device can bring product weight increase, volume increase etc. unnecessary undoubtedly, thus cause the inconvenience in use to user.
Summary of the invention
The object of the invention is that proposing one falls detection law-enforcing recorder and fall detection method, to solve technical problem product being fallen to condition adjudgement inconvenience that above-mentioned prior art exists.
For this reason, the present invention proposes one and falls detection law-enforcing recorder, comprises image-forming module, acquisition module, memory module and detection module; Wherein,
Described image-forming module is for obtaining the vision signal around law-enforcing recorder;
Described acquisition module is used for from described vision signal, gather first image in the first moment and second image in the second moment;
Described memory module is for storing described first image and described second image;
Described detection module falls state for judging whether described law-enforcing recorder is in, if described first image and described second image vertical direction similarity are less than similarity threshold, and the time difference between described first moment and described second moment is less than time threshold, then judges that law-enforcing recorder is in and fall state.
Preferably, described similarity threshold is not less than 40%, and described time threshold is not more than 0.05s.
Preferably, described acquisition module is used for from described vision signal, gathering image every the specific sampling interval;
Described memory module for the image in K-1 moment continuously before storing current time and current time, K be not less than 2 positive integer;
Described detection module is for judging in the image in continuous K-1 moment before current time, the image vertical direction similarity of whether depositing a certain image at a time and current time is less than described similarity threshold, and the time difference of described a certain moment and current time is less than described time threshold, if so, then judge that detection law-enforcing recorder is in and fall state.
Preferably, the image in K-1 moment continuous before the image of current time and current time, according to the order from the close-by examples to those far off of the time difference with current time, compares by described detection module successively.
Preferably, K be not more than described time threshold round downwards divided by described sampling interval income value after positive integer.
Preferably, described law-enforcing recorder also comprises and empties module, described in empty module for emptying all images preserved in described memory module when law-enforcing recorder is started shooting at every turn.
What the present invention also proposed a kind of law-enforcing recorder falls detection method, comprises the steps:
Vision signal around S1, acquisition law-enforcing recorder;
S2, from described vision signal, gather first image in the first moment and second image in the second moment;
If described first image of S3 and described second image vertical direction similarity are less than similarity threshold, and the time difference between described first moment and described second moment is less than time threshold, then judge that law-enforcing recorder is in and fall state.
Preferably, described similarity threshold is not less than 40%, and described time threshold is not more than 0.05s.
Preferably, comprise the steps:
Vision signal around S1, acquisition law-enforcing recorder;
S2, from described vision signal, gather image every the specific sampling interval;
S3, store current time and current time before the image in K-1 moment continuously, K be not less than 2 positive integer;
S4, judge in the image in continuous K-1 moment before current time, the image vertical direction similarity of whether depositing a certain image at a time and current time is less than described similarity threshold, and the time difference of described a certain moment and current time is less than described time threshold, if so, then judge that detection law-enforcing recorder is in and fall state.
The image that the law-enforcing recorder that the present invention proposes utilizes imageing sensor to collect carrys out the scene change of recognition image vertical direction; thus judge whether law-enforcing recorder is in and acutely shake or fall state; and make corresponding conservation treatment, for the reliable progress of law-enforcing work provides a favorable security.
Accompanying drawing explanation
Fig. 1 is the law-enforcing recorder system block diagram of the specific embodiment of the invention one;
Fig. 2 is the law-enforcing recorder system block diagram of the specific embodiment of the invention two;
Fig. 3 is the detection module workflow diagram of the specific embodiment of the invention two;
Fig. 4 is the detection module workflow diagram of the specific embodiment of the invention three.
Embodiment
Contrast accompanying drawing below in conjunction with embodiment the present invention is described in further detail.It is emphasized that following explanation is only exemplary, instead of in order to limit the scope of the invention and apply.
With reference to the following drawings, will describe the embodiment of non-limiting and nonexcludability, wherein identical Reference numeral represents identical parts, unless stated otherwise.
Embodiment one:
The present invention proposes one and falls detection law-enforcing recorder, is the law-enforcing recorder system block diagram of the specific embodiment of the invention one see Fig. 1.This law-enforcing recorder comprises image-forming module, acquisition module, memory module and detection module; Wherein, image-forming module is for obtaining the vision signal around law-enforcing recorder; Acquisition module is used for from vision signal, gather first image in the first moment and second image in the second moment; Memory module is for storing the first image and the second image; Detection module falls state for judging whether law-enforcing recorder is in, if the first image and the second image vertical direction similarity are less than similarity threshold, and the time difference between the first moment and the second moment is less than time threshold, then judges that law-enforcing recorder is in and fall state.
The law-enforcing recorder that the present invention proposes does not need by extra electronic devices and components the judgement falling state, but the image sensing device utilizing it to carry can complete, and is conducive to saving product weight and power consumption.Under normal circumstances, image frame is the acute variation that vertical direction can not occur at short notice, thus, if in specific time threshold, front and back two changes of width image in vertical colour gamut exceed specific similarity threshold, and it is very large that law-enforcing recorder is in the probability falling state.Show through many experiments, get be not less than 40% when similarity threshold, when time threshold is got and is not more than 0.05s, law-enforcing recorder is the most effective to the judgement falling state.
Further, this law-enforcing recorder also comprises processing module, when detection module judge law-enforcing recorder be in fall state time, processing module is for performing corresponding operation.Such as, processing module sends instruction control law-enforcing recorder and stops shooting immediately and stored in the nonvolatile memory by current audio-video document, as in the TF card of law-enforcing recorder, to avoid law-enforcing recorder because falling impaired and causing the loss of important evidence file.
Embodiment two:
The present embodiment proposes one and falls detection law-enforcing recorder, is the law-enforcing recorder system block diagram of the specific embodiment of the invention two see Fig. 2.This law-enforcing recorder comprises image-forming module, acquisition module, memory module, detection module and processing module.Wherein, image-forming module is for obtaining the vision signal around law-enforcing recorder; Acquisition module is used for from vision signal, gathering image every the specific sampling interval, and the sampling interval is not more than default time threshold; Memory module for the image in K-1 moment continuously before storing current time and current time, wherein, K be not less than 2 positive integer; Detection module is for judging in the image in continuous K-1 moment before current time, the image vertical direction similarity of whether depositing a certain image at a time and current time is less than similarity threshold, and the time difference of a certain moment and current time is less than time threshold, if, then judge that detection law-enforcing recorder is in and fall state, processing module performs corresponding operation, if not, then judge that detection law-enforcing recorder is not in and fall state, turn the image being gathered subsequent time by acquisition module when the next sampling interval arrives.In the present embodiment, time threshold is not more than 0.05s, and similarity threshold is not less than 40%.
In one embodiment, see the detection module workflow diagram that Fig. 3 is the specific embodiment of the invention two, whether detection module is in law-enforcing recorder the detection falling state comprises: according to the order from the close-by examples to those far off of the time difference with current time, the image in K-1 moment continuous before the image of current time and current time is compared successively, i-th when taking turns, i is the positive integer being not more than K-1, before comparing current time and current time, whether the image vertical direction similarity in i-th moment is less than similarity threshold, if image vertical direction similarity is not less than similarity threshold, then detection module proceeds i-th+1 and takes turns and compare, namely before comparing current time and current time, whether the image vertical direction similarity in the i-th+1 moment is less than similarity threshold, if detection module completes K-1, wheel compares, still the image being less than similarity threshold with the similarity of current time image is not found, then judge that law-enforcing recorder is not in and fall state, if image vertical direction similarity is less than similarity threshold, before comparing current time and current time, whether the time difference in i-th moment is less than time threshold, if the time difference is not less than time threshold, then judges that law-enforcing recorder is not in and falls state, if the time difference is less than time threshold, then judges that law-enforcing recorder is in and fall state.
Alternatively, before current time and current time, the image vertical direction similarity in i-th moment is judged by the color histogram of two width images.For convenience of describing, the image claiming current time is the first image, and before current time, the image in i-th moment is the second image, comprises the following steps:
S1, obtain the color histogram of the first image and the color histogram of the second image, in an embodiment, color histogram comprises 0 ~ 255 totally 256 rank brightness values;
S2, obtain the first image and the second image vertical direction similarity
wherein,
Δ
1[p] is the absolute value of R, G, B color component difference in the first image p rank brightness value, is expressed as: Δ
1[p]=| R
1[p]-B
1[p] |+| R
1[p]-G
1[p] |+| B
1[p]-G
1[p] |, R1 [p], G1 [p], B1 [p] represent the numerical value of R, G, B in the first image p rank brightness value respectively;
Δ
2[p] is the absolute value of R, G, B color component difference in the second image p rank brightness value, is expressed as: Δ
2[p]=| R
2[p]-B
2[p] |+| R
2[p]-G
2[p] |+| B
2[p]-G
2[p] |, R2 [p], G2 [p], B2 [p] represent the numerical value of R, G, B in the second image p rank brightness value respectively.
More preferably, this law-enforcing recorder also comprises and empties module, for emptying all images preserved in memory module when law-enforcing recorder is started shooting at every turn.When law-enforcing recorder is just started shooting, detection module does not utilize the piece image of collection to fall state to judge whether law-enforcing recorder is in, because now also do not have effective contrast images.Memory module is by the image in K moment before the image of current time covering current time when preserving image, namely always the image of up-to-date storage is covered the image of oldest stored.In addition, in embodiments of the present invention, the sampling interval arranges less, whether is in the condition adjudgement falling at a high speed state sensitiveer to law-enforcing recorder, thus when law-enforcing recorder be in fall state time, it performs corresponding operating and also gets over fast and reliable.
Embodiment three:
The present embodiment proposes one and falls detection law-enforcing recorder, comprises image-forming module, acquisition module, memory module, detection module.Wherein, image-forming module is for obtaining the vision signal around law-enforcing recorder, acquisition module is used for from vision signal, extracting image every the specific sampling interval, and the sampling interval is not more than default time threshold, memory module for the image in K-1 moment continuously before storing current time and current time, wherein, K be not more than time threshold round downwards divided by sampling interval income value after positive integer, detection module is used for according to the order from the close-by examples to those far off of the time difference with current time, the image in K-1 moment continuous before the image of current time and current time is compared successively, i-th when taking turns, i is the positive integer being not more than K-1, before comparing current time and current time, whether the image vertical direction similarity in i-th moment is less than similarity threshold, if image vertical direction similarity is not less than similarity threshold, then detection module proceeds i-th+1 and takes turns and compare, namely before comparing current time and current time, whether the image vertical direction similarity in the i-th+1 moment is less than similarity threshold, if detection module completes K-1, wheel compares, still the image being less than similarity threshold with the similarity of current time image is not found, then judge that law-enforcing recorder is not in and fall state, turn the image being gathered subsequent time by acquisition module when the next sampling interval arrives, if image vertical direction similarity is less than similarity threshold, then judges that law-enforcing recorder is in and fall state, processing module performs corresponding operation, is the detection module workflow diagram of the specific embodiment of the invention three see Fig. 4.In the present embodiment, the time threshold preset is not more than 0.05s, and default similarity threshold is not less than 40%.
In the present embodiment, K is the positive integer after time threshold rounds downwards divided by sampling interval income value, like this, before current time and current time, the time difference in i-th moment is all less than default time threshold, therefore, detection module does not need whether be less than time threshold to the time difference of two width images again and judges, saves computer processing time, realizes detecting more fast, more efficiently.
The course of work of above-mentioned law-enforcing recorder is as follows:
Vision signal around S1, acquisition law-enforcing recorder;
S2, from vision signal, extract image every the specific sampling interval, the sampling interval is not more than time threshold;
The image in continuous K-1 moment before S3, storage current time N and current time N, namely include before current time N and current time N moment N-1 ..., moment N-K+1 image, wherein, K is the positive integer after time threshold rounds downwards divided by sampling interval income value;
S4, according to the order from the close-by examples to those far off of the time difference with current time N, the image in K-1 moment continuous before the image of current time N and current time N is compared successively, i-th when taking turns (i is the positive integer being not more than K-1), relatively before current time N and current time N, whether the image vertical direction similarity of i-th moment (i.e. moment N-i) is less than default similarity threshold, if image vertical direction similarity is not less than similarity threshold, then proceed i-th+1 to take turns and compare, if complete K-1 wheel to compare, still the image being less than similarity threshold with the similarity of current time image is not found, then judge that law-enforcing recorder is not in and fall state, return the image that step S2 gathers subsequent time N+1, if image vertical direction similarity is less than similarity threshold, then judges that law-enforcing recorder is in and fall state, law-enforcing recorder performs corresponding operating, in the present embodiment, the time threshold preset is 0.05s, and default similarity threshold is 40%.
Those skilled in the art will recognize that, it is possible for making numerous accommodation to above description, so embodiment is only used to describe one or more particular implementation.
Although described and described and be counted as example embodiment of the present invention, it will be apparent to those skilled in the art that and can make various change and replacement to it, and spirit of the present invention can not have been departed from.In addition, many amendments can be made so that particular case is fitted to religious doctrine of the present invention, and central concept of the present invention described here can not be departed from.So the present invention is not limited to specific embodiment disclosed here, but the present invention also may comprise all embodiments and equivalent thereof that belong to the scope of the invention.
Claims (9)
1. fall a detection law-enforcing recorder, it is characterized in that, comprise image-forming module, acquisition module, memory module and detection module; Wherein,
Described image-forming module is for obtaining the vision signal around law-enforcing recorder;
Described acquisition module is used for from described vision signal, gather first image in the first moment and second image in the second moment;
Described memory module is for storing described first image and described second image;
Described detection module falls state for judging whether described law-enforcing recorder is in, if described first image and described second image vertical direction similarity are less than similarity threshold, and the time difference between described first moment and described second moment is less than time threshold, then judges that law-enforcing recorder is in and fall state.
2. fall detection law-enforcing recorder as claimed in claim 1, it is characterized in that, described similarity threshold is not less than 40%, and described time threshold is not more than 0.05s.
3. fall detection law-enforcing recorder as claimed in claim 1 or 2, it is characterized in that, described acquisition module is used for from described vision signal, gathering image every the specific sampling interval;
Described memory module for the image in K-1 moment continuously before storing current time and current time, K be not less than 2 positive integer;
Described detection module is for judging in the image in continuous K-1 moment before current time, the image vertical direction similarity of whether depositing a certain image at a time and current time is less than described similarity threshold, and the time difference of described a certain moment and current time is less than described time threshold, if so, then judge that detection law-enforcing recorder is in and fall state.
4. fall detection law-enforcing recorder as claimed in claim 3, it is characterized in that, the image in K-1 moment continuous before the image of current time and current time, according to the order from the close-by examples to those far off of the time difference with current time, compares by described detection module successively.
5. fall detection law-enforcing recorder as claimed in claim 3, it is characterized in that, K be not more than described time threshold round downwards divided by described sampling interval income value after positive integer.
6. fall detection law-enforcing recorder as claimed in claim 3, it is characterized in that, described law-enforcing recorder also comprises and empties module, described in empty module for emptying all images preserved in described memory module when law-enforcing recorder is started shooting at every turn.
7. law-enforcing recorder fall a detection method, it is characterized in that, comprise the steps:
Vision signal around S1, acquisition law-enforcing recorder;
S2, from described vision signal, gather first image in the first moment and second image in the second moment;
If described first image of S3 and described second image vertical direction similarity are less than similarity threshold, and the time difference between described first moment and described second moment is less than time threshold, then judge that law-enforcing recorder is in and fall state.
8. fall detection method as claimed in claim 7, it is characterized in that, described similarity threshold is not less than 40%, and described time threshold is not more than 0.05s.
9. fall detection method as claimed in claim 7 or 8, it is characterized in that, comprise the steps:
Vision signal around S1, acquisition law-enforcing recorder;
S2, from described vision signal, gather image every the specific sampling interval;
S3, store current time and current time before the image in K-1 moment continuously, K be not less than 2 positive integer;
S4, judge in the image in continuous K-1 moment before current time, the image vertical direction similarity of whether depositing a certain image at a time and current time is less than described similarity threshold, and the time difference of described a certain moment and current time is less than described time threshold, if so, then judge that detection law-enforcing recorder is in and fall state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510501918.9A CN105072324B (en) | 2015-08-14 | 2015-08-14 | One is fallen detection law-enforcing recorder and falls detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510501918.9A CN105072324B (en) | 2015-08-14 | 2015-08-14 | One is fallen detection law-enforcing recorder and falls detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105072324A true CN105072324A (en) | 2015-11-18 |
| CN105072324B CN105072324B (en) | 2016-07-06 |
Family
ID=54501593
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510501918.9A Active CN105072324B (en) | 2015-08-14 | 2015-08-14 | One is fallen detection law-enforcing recorder and falls detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105072324B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108012119A (en) * | 2017-12-13 | 2018-05-08 | 苏州华兴源创电子科技有限公司 | A kind of transmission method of real-time video, Transmission system and a kind of readable storage medium storing program for executing |
| CN108668005A (en) * | 2018-03-14 | 2018-10-16 | 维沃移动通信有限公司 | A kind of endpoint detection methods and terminal |
| CN111464854A (en) * | 2020-04-16 | 2020-07-28 | 深圳市华德安科技有限公司 | Fall data processing method, device and equipment and readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101996327A (en) * | 2010-09-02 | 2011-03-30 | 西安电子科技大学 | Video anomaly detection method based on weighted tensor subspace background modeling |
| US20120063641A1 (en) * | 2009-04-01 | 2012-03-15 | Curtin University Of Technology | Systems and methods for detecting anomalies from data |
| CN103561243A (en) * | 2013-11-13 | 2014-02-05 | 太仓太乙信息工程有限公司 | Camera condition monitoring system and method |
| CN104539899A (en) * | 2014-12-25 | 2015-04-22 | 合肥寰景信息技术有限公司 | Method for distinguishing monitoring camera abnormal situation through video signal |
-
2015
- 2015-08-14 CN CN201510501918.9A patent/CN105072324B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120063641A1 (en) * | 2009-04-01 | 2012-03-15 | Curtin University Of Technology | Systems and methods for detecting anomalies from data |
| CN101996327A (en) * | 2010-09-02 | 2011-03-30 | 西安电子科技大学 | Video anomaly detection method based on weighted tensor subspace background modeling |
| CN103561243A (en) * | 2013-11-13 | 2014-02-05 | 太仓太乙信息工程有限公司 | Camera condition monitoring system and method |
| CN104539899A (en) * | 2014-12-25 | 2015-04-22 | 合肥寰景信息技术有限公司 | Method for distinguishing monitoring camera abnormal situation through video signal |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108012119A (en) * | 2017-12-13 | 2018-05-08 | 苏州华兴源创电子科技有限公司 | A kind of transmission method of real-time video, Transmission system and a kind of readable storage medium storing program for executing |
| CN108668005A (en) * | 2018-03-14 | 2018-10-16 | 维沃移动通信有限公司 | A kind of endpoint detection methods and terminal |
| CN108668005B (en) * | 2018-03-14 | 2020-09-15 | 维沃移动通信有限公司 | Terminal detection method and terminal |
| CN111464854A (en) * | 2020-04-16 | 2020-07-28 | 深圳市华德安科技有限公司 | Fall data processing method, device and equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105072324B (en) | 2016-07-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108228696B (en) | Face image retrieval method and system, shooting device and computer storage medium | |
| US20120092495A1 (en) | Object detection apparatus, object detection method, monitoring camera system and storage medium | |
| CN108875619B (en) | Video processing method and device, electronic equipment and computer readable storage medium | |
| CN103714327B (en) | Method and system for correcting image direction | |
| EP2709062B1 (en) | Image processing device, image processing method, and computer readable medium | |
| WO2021011287A1 (en) | Techniques for identifying skin color in images having uncontrolled lighting conditions | |
| CN106682620A (en) | Human face image acquisition method and device | |
| CN103324904A (en) | Face recognition system and method thereof | |
| US9953240B2 (en) | Image processing system, image processing method, and recording medium for detecting a static object | |
| CN101271519A (en) | A method and apparatus for detecting faces | |
| CN111901604A (en) | Video compression method, video reconstruction method, corresponding devices, camera and video processing equipment | |
| CN102915372A (en) | Image retrieval method, device and system | |
| CN105072324B (en) | One is fallen detection law-enforcing recorder and falls detection method | |
| CN109327626B (en) | Image acquisition method and device, electronic equipment and computer readable storage medium | |
| CN105590479A (en) | Parking space monitoring method and device | |
| CN103118220A (en) | Keyframe pick-up algorithm based on multi-dimensional feature vectors | |
| CN103426183A (en) | Method and device for tracking motion objects | |
| US11200681B2 (en) | Motion detection method and motion detection system with low computational complexity and high detection accuracy | |
| Hung et al. | A fast algorithm of temporal median filter for background subtraction. | |
| CN108230412A (en) | A kind of IR image compression method and device | |
| CN105046719A (en) | Method and system for video monitoring | |
| CN112232140A (en) | Crowd counting method and device, electronic equipment and computer storage medium | |
| CN113093556A (en) | Clothing collection reminding method, clothes hanger, system and storage medium | |
| CN111444758A (en) | Pedestrian re-identification method and device based on spatio-temporal information | |
| CN110769262B (en) | Video image compression method, system, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C56 | Change in the name or address of the patentee | ||
| CP03 | Change of name, title or address |
Address after: Binhai Road Nanshan District Guangdong street of Shenzhen city in Guangdong province 518000 software industry base in Shenzhen, 5 E block 1102 Patentee after: Shenzhen police wing smart Polytron Technologies Inc Address before: 518000 Shenzhen Institute of technology, Nanshan District science and Technology Park, Guangdong,, B401, Tsinghua University Patentee before: Shenzhen Jingyi Digital Technology Co., Ltd. |