CN111444752B - Shadow target data orientation analysis device and method - Google Patents
Shadow target data orientation analysis device and method Download PDFInfo
- Publication number
- CN111444752B CN111444752B CN201911005402.XA CN201911005402A CN111444752B CN 111444752 B CN111444752 B CN 111444752B CN 201911005402 A CN201911005402 A CN 201911005402A CN 111444752 B CN111444752 B CN 111444752B
- Authority
- CN
- China
- Prior art keywords
- image
- shadow
- equipment
- signal
- noise ratio
- 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.)
- Expired - Fee Related
Links
Images
Classifications
-
- 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
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
- G06V10/955—Hardware or software architectures specially adapted for image or video understanding using specific electronic processors
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
- H04N5/265—Mixing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/76—Television signal recording
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
Abstract
本发明涉及一种阴影目标数据定向分析装置及方法，所述装置包括：阴影采集设备，用于将当前组合图像中灰度值落在预设阴影灰度分布范围内的像素点作为阴影像素点，并基于所述当前组合图像中各个阴影像素点的分布位置去除所述当前组合图像中的孤立的阴影像素点以获得多个剩余的阴影像素点；信号辨识设备，用于在所述多个剩余的阴影像素点的数量大于等于预设数量阈值时，发出存在阴影信号。本发明的阴影目标数据定向分析装置及方法逻辑清楚，操作简便。由于对无影灯下方场景是否存在阴影进行定向识别，并在存在阴影时及时进行提醒，以进行后续的无影灯故障清理，从而避免出现严重的手术事故。
The invention relates to an apparatus and method for directional analysis of shadow target data. The apparatus includes: a shadow collection device, which is used for taking the pixels whose gray values fall within a preset shadow gray distribution range in a current combined image as shadow pixels. , and remove the isolated shadow pixels in the current combined image based on the distribution position of each shadow pixel in the current combined image to obtain a plurality of remaining shadow pixels; When the number of remaining shadow pixels is greater than or equal to a preset number threshold, a shadow presence signal is sent. The shadow target data orientation analysis device and method of the present invention have clear logic and simple operation. Because of the directional identification of whether there is a shadow in the scene under the shadowless lamp, and timely reminder when there is a shadow, so as to clean up the fault of the shadowless lamp in the follow-up, so as to avoid serious surgical accidents.
Description
Technical Field
The invention relates to the field of medical equipment, in particular to a shadow target data orientation analysis device and method.
Background
Medical instruments refer to instruments, devices, appliances, in-vitro diagnostic reagents and calibrators, materials and other similar or related items used directly or indirectly on the human body, including the required computer software.
The utility of medical devices is primarily achieved by physical, etc., means other than pharmacological, immunological, or metabolic means, or may be assisted by such means.
The purpose of medical devices is the diagnosis, prevention, monitoring, treatment, or amelioration of disease; diagnosis, monitoring, treatment, mitigation, or functional compensation of injury; examination, replacement, regulation or support of a physiological structure or physiological process; support or maintenance of life; controlling pregnancy; by examining a sample from a human body, information is provided for medical or diagnostic purposes.
Disclosure of Invention
The invention has at least the following two key points:
(1) the method comprises the steps of directionally identifying whether a shadow exists in a scene below the shadowless lamp, and timely reminding when the shadow exists so as to perform subsequent fault cleaning of the shadowless lamp, thereby avoiding serious operation accidents;
(2) and taking the definition corresponding to the central sequence number in the definition sequence as a referential balance value, and adopting the referential definition to carry out definition improvement processing on the sub-image with the object in the image instead of carrying out definition improvement processing on the sub-image without the object in the image, thereby reducing the data volume of image processing.
According to an aspect of the present invention, there is provided a shadow target data orientation analysis apparatus, the apparatus comprising:
the shadow collecting device is connected with the data combining device and used for receiving the current combined image, taking pixel points of which the gray values are within a preset shadow gray distribution range in the current combined image as shadow pixel points, and removing isolated shadow pixel points in the current combined image based on the distribution positions of the shadow pixel points in the current combined image to obtain a plurality of residual shadow pixel points;
the signal identification equipment is connected with the shadow acquisition equipment and is used for sending a shadow existence signal when the number of the plurality of residual shadow pixel points is greater than or equal to a preset number threshold;
the signal identification equipment is further used for not sending out a shadow existence signal when the number of the plurality of the remaining shadow pixel points is smaller than the preset number threshold;
the monitoring video equipment is arranged on the side surface of the shadowless lamp of the operating table and used for executing video recording action on a scene below the shadowless lamp so as to obtain and output a current video frame;
the quantity identification equipment is connected with the monitoring video recording equipment and is used for receiving the current video recording frame and obtaining the quantity of pixel points of each line of the current video recording frame to be output as the image length;
the instant segmentation equipment is connected with the quantity identification equipment and used for determining the size of a fragment area for image segmentation which is in direct proportion to the image length and segmenting the current video frame based on the determined fragment to obtain a plurality of sub-images;
the GPU chip is connected with the instant segmentation equipment and used for receiving each subimage of the current video frame, sequencing the definitions of each subimage from small to large to obtain a definition sequence, taking the definition corresponding to a central sequence number in the definition sequence as a reference balance value, and performing definition improving processing on the subimage of an object in the current video frame by using the reference definition, wherein the higher the reference definition is, the fewer the times of the definition improving processing are performed;
and the data combination equipment is connected with the GPU chip and is used for carrying out image combination on the sub-image without the object in the current video frame and the processed blocks obtained after the definition improvement processing is carried out on the sub-image with the object in the current video frame so as to obtain a current combined image corresponding to the current video frame, wherein one or more sub-images with the object in the current video frame are obtained, and one or more sub-images without the object in the current video frame are obtained.
According to another aspect of the invention, a shadow target data orientation analysis method is also provided, and the method comprises the steps of using the shadow target data orientation analysis device to perform orientation recognition on whether a shadow exists in a scene below a shadowless lamp, and reminding timely when the shadow exists.
The shadow target data orientation analysis device and the shadow target data orientation analysis method have clear logic and simple and convenient operation. Because the shadow is directionally identified in the scene below the shadowless lamp and the scene below the shadowless lamp is timely reminded when the shadow exists, the subsequent fault cleaning of the shadowless lamp is carried out, and the serious operation accident is avoided.
Drawings
Embodiments of the invention will now be described with reference to the accompanying drawings, in which:
fig. 1 is a view showing an outline configuration of a shadowless lamp to which a shadow target data orientation analysis apparatus is applied according to an embodiment of the present invention.
Detailed Description
Embodiments of the shadow target data orientation analyzing apparatus and method of the present invention will be described in detail below with reference to the accompanying drawings.
Surgical shadowless lamps are used to illuminate the surgical site for optimal viewing of small, low contrast objects at various depths in the incision and body cavity. Because the head, hands and instruments of the operator can cause interference shadows to the surgical site, the surgical shadowless lamp should be designed to eliminate the shadows as much as possible and minimize color distortion.
In addition, the shadowless lamp must be able to continue to operate for a long period of time without emitting excessive heat, since overheating can cause discomfort to the operator and can also dry the tissue in the surgical field.
In the prior art, the fault cleaning of the operating shadowless lamp is very important, for example, in the process of performing an operation, if a shadow exists in the lighting effect of a projected light beam due to the fault of the shadowless lamp, the sight of a primary doctor can be seriously interfered, even misjudgment or misoperation can be generated, and a bad interference effect is exerted on the success or failure of the operation.
In order to overcome the defects, the invention builds a shadow target data orientation analysis device and method, and can effectively solve the corresponding technical problem.
The shadow target data orientation analysis device shown according to the embodiment of the invention comprises:
the shadow collecting device is connected with the data combining device and used for receiving the current combined image, taking pixel points of which the gray values are within a preset shadow gray distribution range in the current combined image as shadow pixel points, and removing isolated shadow pixel points in the current combined image based on the distribution positions of the shadow pixel points in the current combined image to obtain a plurality of residual shadow pixel points;
the signal identification equipment is connected with the shadow acquisition equipment and is used for sending a shadow existence signal when the number of the plurality of residual shadow pixel points is greater than or equal to a preset number threshold;
the signal identification equipment is further used for not sending out a shadow existence signal when the number of the plurality of the remaining shadow pixel points is smaller than the preset number threshold;
the monitoring video equipment is arranged on the side surface of the shadowless lamp of the operating table and used for executing video recording action on a scene below the shadowless lamp so as to obtain and output a current video frame;
the outline structure of the shadowless lamp of the operating table is shown in figure 1;
the quantity identification equipment is connected with the monitoring video recording equipment and is used for receiving the current video recording frame and obtaining the quantity of pixel points of each line of the current video recording frame to be output as the image length;
the instant segmentation equipment is connected with the quantity identification equipment and used for determining the size of a fragment area for image segmentation which is in direct proportion to the image length and segmenting the current video frame based on the determined fragment to obtain a plurality of sub-images;
the GPU chip is connected with the instant segmentation equipment and used for receiving each subimage of the current video frame, sequencing the definitions of each subimage from small to large to obtain a definition sequence, taking the definition corresponding to a central sequence number in the definition sequence as a reference balance value, and performing definition improving processing on the subimage of an object in the current video frame by using the reference definition, wherein the higher the reference definition is, the fewer the times of the definition improving processing are performed;
and the data combination equipment is connected with the GPU chip and is used for carrying out image combination on the sub-image without the object in the current video frame and the processed blocks obtained after the definition improvement processing is carried out on the sub-image with the object in the current video frame so as to obtain a current combined image corresponding to the current video frame, wherein one or more sub-images with the object in the current video frame are obtained, and one or more sub-images without the object in the current video frame are obtained.
Next, a detailed configuration of the shadow target data orientation analyzing device of the present invention will be further described.
In the shadow target data orientation analysis device:
the GPU chip and the data combination device are arranged on the same printed circuit board;
wherein the quantity identification device and the instant slicing device use the same quartz oscillation device to obtain clock signals with different frequencies.
The shadow target data orientation analysis device may further include:
and the restoration processing equipment is connected with the monitoring video recording equipment and is used for receiving the current video recording frame and executing image restoration processing on the current video recording frame so as to obtain and output a corresponding instant restoration image.
The shadow target data orientation analysis device may further include:
and the multiple regression interpolation equipment is connected with the restoration processing equipment and is used for receiving the instant restoration image and executing multiple regression interpolation processing on the instant restoration image to obtain a corresponding multiple regression interpolation image.
The shadow target data orientation analysis device may further include:
the signal-to-noise ratio analysis device is connected with the multiple regression interpolation device and used for receiving the multiple regression interpolation image and the instant restoration image, acquiring the signal-to-noise ratio of the multiple regression interpolation image and the signal-to-noise ratio of the instant restoration image, dividing the signal-to-noise ratio of the multiple regression interpolation image by the signal-to-noise ratio of the instant restoration image to obtain a signal-to-noise ratio multiple, and sending a first control command when the signal-to-noise ratio multiple exceeds a preset multiple threshold value
The signal-to-noise ratio analysis equipment is further used for sending a second control command when the signal-to-noise ratio multiple does not exceed the preset multiple threshold.
The shadow target data orientation analysis device may further include:
the embedded processing chip is respectively connected with the multiple regression interpolation equipment and the signal-to-noise ratio analysis equipment and is used for controlling the multiple regression interpolation equipment to execute one or more times of multiple regression interpolation processing on the multiple regression interpolation image when receiving the second control command until a multiple obtained by dividing the signal-to-noise ratio of the processed image by the signal-to-noise ratio of the instant recovery image exceeds a preset multiple threshold value, and outputting the processed image as a reference image;
and the embedded processing chip is also used for outputting the multiple regression interpolation image as a reference image when receiving the first control command.
The shadow target data orientation analysis device may further include:
and the signal enhancement equipment is respectively connected with the quantity identification equipment, the embedded processing chip and the signal-to-noise ratio analysis equipment and is used for receiving the reference image, executing image enhancement processing on the reference image to obtain a corresponding enhanced processing image, and replacing the current video frame with the enhanced processing image and sending the enhanced processing image to the quantity identification equipment.
In the shadow target data orientation analysis device:
and the signal enhancement equipment, the embedded processing chip and the signal-to-noise ratio analysis equipment perform data interaction through a 32-bit parallel data bus.
Meanwhile, in order to overcome the defects, the invention also provides a shadow target data orientation analysis method, which comprises the steps of using the shadow target data orientation analysis device to carry out orientation identification on whether the shadow exists in the scene below the shadowless lamp, and reminding in time when the shadow exists.
In addition, the GPU is different from a DSP (Digital Signal Processing) architecture in several main aspects. All its calculations use floating point arithmetic and there is no bit or integer arithmetic instruction at this time. Furthermore, since the GPU is designed specifically for image processing, the storage system is actually a two-dimensional, segmented storage space, including a segment number (from which the image is read) and a two-dimensional address (X, Y coordinates in the image). Furthermore, there is no indirect write instruction. The output write address is determined by the raster processor and cannot be changed by the program. This is a significant challenge for algorithms that are naturally distributed among the memories. Finally, no communication is allowed between the processes of different shards. In effect, the fragment processor is a SIMD data parallel execution unit, executing code independently in all fragments.
Despite the above constraints, the GPU can still efficiently perform a variety of operations, from linear algebraic sum signal processing to numerical simulation. While the concept is simple, new users are still confused when using GPU computations because the GPU requires proprietary graphics knowledge. In this case, some software tools may provide assistance. The two high-level shading languages CG and HLSL enable users to write C-like code and then compile it into a shard program assembly language. Brook is a high-level language designed specifically for GPU computing and does not require graphical knowledge. Therefore, it can be a good starting point for the worker who first uses the GPU for development. Brook is an extension of the C language, integrating a simple data-parallel programming construct that can be mapped directly to a GPU. Data stored and manipulated by the GPU is visually analogized to "streams" (streams), similar to the arrays in standard C. The Kernel is a function that operates on the stream. Calling a core function on a series of input streams means that an implicit loop is implemented on the stream elements, i.e. a core body is called for each stream element. Brook also provides reduction mechanisms, such as performing sum, maximum, or product calculations on all elements in a stream. Brook also completely hides all the details of the graphics API and virtualizes many user-unfamiliar parts of the GPU, like the two-dimensional memory system. Applications written in Brook include linear algebra subroutines, fast fourier transforms, ray tracing, and image processing. With the X800XT for ATI and the GeForce 6800Ultra type GPU for Nvidia, the speed of many such applications increased by as much as 7 times under the same cache, SSE assembly optimized Pentium 4 execution conditions.
Those of ordinary skill in the art will understand that: all or part of the steps for implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer readable storage medium, and when executed, the program performs the steps including the method embodiments; and the aforementioned storage medium includes: Read-Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disk, and other various media capable of storing program codes.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (2)
1. An apparatus for directional analysis of shadow target data, the apparatus comprising:
the shadow collecting device is connected with the data combining device and used for receiving the current combined image, taking pixel points of which the gray values are within a preset shadow gray distribution range in the current combined image as shadow pixel points, and removing isolated shadow pixel points in the current combined image based on the distribution positions of the shadow pixel points in the current combined image to obtain a plurality of residual shadow pixel points;
the signal identification equipment is connected with the shadow acquisition equipment and is used for sending a shadow existence signal when the number of the plurality of residual shadow pixel points is greater than or equal to a preset number threshold;
the signal identification equipment is further used for not sending out a shadow existence signal when the number of the plurality of the remaining shadow pixel points is smaller than the preset number threshold;
the monitoring video equipment is arranged on the side surface of the shadowless lamp of the operating table and used for executing video recording action on a scene below the shadowless lamp so as to obtain and output a current video frame;
the quantity identification equipment is connected with the monitoring video recording equipment and is used for receiving the current video recording frame and obtaining the quantity of pixel points of each line of the current video recording frame to be output as the image length;
the instant segmentation equipment is connected with the quantity identification equipment and used for determining the size of a fragment area for image segmentation which is in direct proportion to the image length and segmenting the current video frame based on the determined fragment to obtain a plurality of sub-images;
the GPU chip is connected with the instant segmentation equipment and used for receiving each subimage of the current video frame, sequencing the definitions of each subimage from small to large to obtain a definition sequence, taking the definition corresponding to a central sequence number in the definition sequence as a reference balance value, and performing definition improving processing on the subimage of an object in the current video frame by adopting reference definition, wherein the higher the reference definition is, the fewer the times of the definition improving processing are performed;
the data combination equipment is connected with the GPU chip and is used for carrying out image combination on the sub-image without the object in the current video frame and the processed blocks obtained after the definition improvement processing is carried out on the sub-image with the object in the current video frame so as to obtain a current combined image corresponding to the current video frame, wherein one or more sub-images with the object in the current video frame are obtained, and one or more sub-images without the object in the current video frame are obtained;
the GPU chip and the data combination device are arranged on the same printed circuit board;
the quantity identification device and the instant segmentation device use the same quartz oscillation device to obtain clock signals with different frequencies;
the restoration processing equipment is connected with the monitoring video recording equipment and is used for receiving the current video recording frame and executing image restoration processing on the current video recording frame so as to obtain and output a corresponding instant restoration image;
the multivariate regression interpolation equipment is connected with the restoration processing equipment and used for receiving the instant restoration image and executing multivariate regression interpolation processing on the instant restoration image to obtain a corresponding multivariate regression interpolation image;
the signal-to-noise ratio analysis device is connected with the multiple regression interpolation device and used for receiving the multiple regression interpolation image and the instant restoration image, acquiring the signal-to-noise ratio of the multiple regression interpolation image and the signal-to-noise ratio of the instant restoration image, dividing the signal-to-noise ratio of the multiple regression interpolation image by the signal-to-noise ratio of the instant restoration image to obtain a signal-to-noise ratio multiple, and sending a first control command when the signal-to-noise ratio multiple exceeds a preset multiple threshold value
The signal-to-noise ratio analysis equipment is further used for sending a second control command when the signal-to-noise ratio multiple does not exceed the preset multiple threshold;
the embedded processing chip is respectively connected with the multiple regression interpolation equipment and the signal-to-noise ratio analysis equipment and is used for controlling the multiple regression interpolation equipment to execute one or more times of multiple regression interpolation processing on the multiple regression interpolation image when receiving the second control command until a multiple obtained by dividing the signal-to-noise ratio of the processed image by the signal-to-noise ratio of the instant recovery image exceeds a preset multiple threshold value, and outputting the processed image as a reference image;
the embedded processing chip is further used for outputting the multiple regression interpolation image as a reference image when receiving the first control command;
the signal enhancement equipment is respectively connected with the quantity identification equipment, the embedded processing chip and the signal-to-noise ratio analysis equipment and is used for receiving the reference image, executing image enhancement processing on the reference image to obtain a corresponding enhanced processing image, and replacing the current video frame with the enhanced processing image and sending the enhanced processing image to the quantity identification equipment;
in the GPU chip, all computations of the GPU use floating point arithmetic, and no bit or integer operation instruction exists, and the GPU is specially designed for image processing, so that the storage system is actually a two-dimensional segmented storage space which comprises a segment number and a two-dimensional address, namely X, Y coordinates in the image, the GPU does not have any indirect writing instruction, the output writing address is determined by a raster processor and cannot be changed by a program;
and the signal enhancement equipment, the embedded processing chip and the signal-to-noise ratio analysis equipment perform data interaction through a 32-bit parallel data bus.
2. A shadow target data orientation analysis method, the method comprising using the shadow target data orientation analysis device of claim 1 to identify the orientation of a shadow in a scene under a shadowless lamp and to prompt when the shadow is present.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911005402.XA CN111444752B (en) | 2019-10-22 | 2019-10-22 | Shadow target data orientation analysis device and method |
| GBGB2012209.9A GB202012209D0 (en) | 2019-10-22 | 2020-08-06 | Shadow target data orientation analysis device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911005402.XA CN111444752B (en) | 2019-10-22 | 2019-10-22 | Shadow target data orientation analysis device and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111444752A CN111444752A (en) | 2020-07-24 |
| CN111444752B true CN111444752B (en) | 2021-08-31 |
Family
ID=71653942
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911005402.XA Expired - Fee Related CN111444752B (en) | 2019-10-22 | 2019-10-22 | Shadow target data orientation analysis device and method |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111444752B (en) |
| GB (1) | GB202012209D0 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115493128A (en) * | 2022-09-26 | 2022-12-20 | 东莞市步步高教育软件有限公司 | A lamp adjustment method, device, computer readable storage medium and lamp |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8744123B2 (en) * | 2011-08-29 | 2014-06-03 | International Business Machines Corporation | Modeling of temporarily static objects in surveillance video data |
| US9025867B2 (en) * | 2012-05-31 | 2015-05-05 | Apple Inc. | Systems and methods for YCC image processing |
| CN106896622B (en) * | 2015-12-21 | 2019-08-30 | 宁波舜宇光电信息有限公司 | Bearing calibration based on multiple spurs from auto-focusing |
| CN107392946B (en) * | 2017-07-18 | 2020-06-16 | 宁波永新光学股份有限公司 | Microscopic multi-focus image sequence processing method for three-dimensional shape reconstruction |
| CN109712078A (en) * | 2018-07-23 | 2019-05-03 | 永康市巴九灵科技有限公司 | Cabinet security protection control platform |
| CN109711238B (en) * | 2018-07-24 | 2020-11-20 | 台州市怡开包装有限公司 | Rat-proof intelligent cabinet |
| CN108777765B (en) * | 2018-08-07 | 2021-04-30 | 成都西纬科技有限公司 | Method and device for acquiring full-definition image and electronic equipment |
| CN109686434B (en) * | 2018-12-29 | 2020-03-31 | 青岛大学附属医院 | Auxiliary institutions for clinical treatment |
| CN109884959A (en) * | 2019-04-01 | 2019-06-14 | 赵晓甦 | Medical data management system |
-
2019
- 2019-10-22 CN CN201911005402.XA patent/CN111444752B/en not_active Expired - Fee Related
-
2020
- 2020-08-06 GB GBGB2012209.9A patent/GB202012209D0/en not_active Ceased
Also Published As
| Publication number | Publication date |
|---|---|
| GB202012209D0 (en) | 2020-09-16 |
| CN111444752A (en) | 2020-07-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Montaha et al. | A shallow deep learning approach to classify skin cancer using down-scaling method to minimize time and space complexity | |
| CN112164026A (en) | Endoscope polyp real-time detection method, system and terminal | |
| JP2012143340A (en) | Image processing device, image processing method, and image processing program | |
| CN111444752B (en) | Shadow target data orientation analysis device and method | |
| CN110648318A (en) | Auxiliary analysis method and device for skin diseases, electronic equipment and storage medium | |
| Khan et al. | LMBF-Net: a lightweight multipath bidirectional focal attention network for multifeatures segmentation | |
| CN116664513A (en) | Intracranial aneurysm detection method, device and equipment based on nuclear magnetic resonance image | |
| JP7603344B2 (en) | Method for generating images of tissue specimens and computing system for performing the same - Patents.com | |
| WO2021035119A1 (en) | Systems and methods for processing electronic medical images to determine enhanced electronic medical images | |
| JP2024509105A (en) | A method for learning an artificial neural network for detecting prostate cancer from TURP pathological images, and a computing system that performs the same | |
| JP6923129B2 (en) | Information processing equipment, programs, methods and systems | |
| Liu et al. | DCA-Net: Dual-branch contextual-aware network for auxiliary localization and segmentation of parathyroid glands | |
| Patra et al. | Enhancing Diagnostic Precision for Early Detection of Gastric Polyps with U-Net3+ Segmentation | |
| JP7092888B2 (en) | Medical image processing system and learning method | |
| Ramacher et al. | A 53-GOPS programmable vision processor for processing, coding-decoding and synthesizing of images | |
| Mukku et al. | CMT-CNN: colposcopic multimodal temporal hybrid deep learning model to detect cervical intraepithelial neoplasia | |
| CN104715463A (en) | Optimizing method for performing ultrasonic image smooth treating program based on DSP (Digital Signal Processor) | |
| Guanche-Hernández et al. | MPSoC FPGA Implementation of Algorithms of Machine Learning for Clinical Applications Using High-Level Design Methodology | |
| CN117542083B (en) | Bone image recognition method and system based on ultrasonic waves | |
| CN109740612B (en) | Trigger mechanism of instrument switch | |
| CN119850632B (en) | Image focus recognition system for assisting digestive physician in sampling and checking | |
| Long et al. | MAUNet: Polyp segmentation network based on multiscale feature fusion of attention U‐shaped network structure | |
| Odagawa et al. | A hardware implementation of colorectal tumor classification for endoscopic video on customizable DSP toward real-time computer-aided diagnosis system | |
| WO2023281294A1 (en) | Method and system for processing medical image | |
| Varadhaganapathy et al. | Gastrointestinal Ulcer Detection Using Deep Learning |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Shen Zenggui Inventor after: Zhu Peiling Inventor after: Cai Yutai Inventor after: Miao Qiuping Inventor before: Miao Qiuping |
|
| CB03 | Change of inventor or designer information | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210813 Address after: 511400 Nanfang Hospital of Southern Medical University, 1838 North Guangzhou Avenue, Guangzhou, Guangdong Applicant after: NANFANG HOSPITAL, SOUTHERN MEDICAL University Address before: 225300 room 614, 98 Ying Chun East Road, hailing Industrial Park, Taizhou, Jiangsu Applicant before: Taizhou City hailing a business information Consulting Co. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210831 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |