CN116912880A - Bird recognition quality assessment method and system based on bird key point detection - Google Patents
Bird recognition quality assessment method and system based on bird key point detection Download PDFInfo
- Publication number
- CN116912880A CN116912880A CN202310856044.3A CN202310856044A CN116912880A CN 116912880 A CN116912880 A CN 116912880A CN 202310856044 A CN202310856044 A CN 202310856044A CN 116912880 A CN116912880 A CN 116912880A
- Authority
- CN
- China
- Prior art keywords
- bird
- frame
- key point
- image
- detection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 54
- 238000001303 quality assessment method Methods 0.000 title claims description 12
- 238000013441 quality evaluation Methods 0.000 claims abstract description 43
- 238000000034 method Methods 0.000 claims abstract description 26
- 238000013145 classification model Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 210000001015 abdomen Anatomy 0.000 claims description 3
- 210000003323 beak Anatomy 0.000 claims description 3
- 210000001061 forehead Anatomy 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000009471 action Effects 0.000 abstract description 3
- 238000013135 deep learning Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 241000894007 species Species 0.000 description 5
- 230000006978 adaptation Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 235000019504 cigarettes Nutrition 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000875 corresponding effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000036544 posture Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video 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
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computational Linguistics (AREA)
- Human Computer Interaction (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The application is suitable for the technical field of image recognition, and provides a bird recognition quality evaluation method and a bird recognition quality evaluation system based on bird key point detection, wherein the method comprises the following steps: acquiring video data; performing bird frame detection and bird key point detection on each frame in the video data, outputting a bird detection frame and key point positions, wherein each key point corresponds to a visibility label; performing quality evaluation on each frame of image in the video data according to the size of the detected picture, the definition of the picture and the visibility of the key points; and identifying the types of birds in the image with qualified quality evaluation to obtain an identification result. According to the bird identification method, the quality of the identification image is evaluated before bird model identification, so that the identification model can be identified based on some key distinguishing features of birds, some images with missing key parts caused by the orientation or the action of the birds can be filtered out, the identification error rate is reduced, and therefore better quality image frames are selected to improve the identification accuracy.
Description
Technical Field
The application relates to the technical field of image recognition, in particular to a bird recognition quality evaluation method and system based on bird key point detection.
Background
Image recognition, which is a technique for processing, analyzing and understanding images by a computer to recognize targets and objects in various modes, is a practical application for applying a deep learning algorithm. The image recognition technology at the present stage is applied to various industries, such as face recognition commonly used in security inspection, identity verification and mobile payment; plant identification, animal identification, household article identification, etc. are common at search software portals.
In the process of identifying bird images, the collected images are affected by realistic factors such as environment, illumination, species distribution and the like, the collected images are poor in definition, key bird parts are shielded, and therefore the identification result is unstable.
In order to stabilize the image quality, many studies have been made on the quality evaluation of face images at present, and the quality evaluation can be mainly classified into deep learning-based and non-deep learning-based according to technological development, wherein the FQA algorithm based on deep learning starts to appear mainly after 2015 and is dominant recently. The traditional non-deep learning method is mainly used for quality assessment through multi-factor fusion and global learning. For example, quality scoring is carried out according to the gesture, the brightness and the resolution ratio respectively, and finally, the overall quality score is obtained by weighting and fusion. Quality labels are predicted by training a Support Vector Machine (SVM) using the magnitude of the Gabor filter as a feature value.
The above studies have resulted in progressive reduction of errors in the assessment of the quality of facial images, and these methods have focused on correlating the quality assessment effect with human visual assessment. Although the current recognition model quality assessment method is relatively mature in face recognition, no quality assessment method for bird recognition exists.
Therefore, there is a need to provide a bird recognition quality assessment method and system based on bird key point detection, which aims to solve the above problems.
Disclosure of Invention
Aiming at the defects of the prior art, the application aims to provide a bird recognition quality evaluation method and a bird recognition quality evaluation system based on bird key point detection so as to solve the problems in the background art.
The application is realized in such a way that a bird recognition quality evaluation method based on bird key point detection comprises the following steps:
acquiring video data;
performing bird frame detection and bird key point detection on each frame in the video data, outputting a bird detection frame and key point positions, wherein each key point corresponds to a visibility label;
performing quality evaluation on each frame of image in the video data according to the size of the detected picture, the definition of the picture and the visibility of the key points;
and identifying the types of birds in the image with qualified quality evaluation to obtain an identification result.
As a further scheme of the application: when the key point detection of the birds is carried out, a yolov8 key point detection model is used, the marked bird frame and key point data set are used for training, and after the yolov8 key point detection model is trained, the key points of the bird frame and the birds can be detected simultaneously.
As a further scheme of the application: the key points of the bird include back, beak, abdomen, crown, chest, forehead, left eye, left leg, left wing, neck, right eye, right leg, right wing, tail and throat.
As a further scheme of the application: when the quality evaluation is carried out on the picture size detected by the bird frame, screening the images by the width and the height of the bird frame, and judging the picture definition and the visibility of key points of the images larger than the set width and the set height; otherwise, the image is discarded.
As a further scheme of the application: when the quality evaluation is carried out on the definition of the picture detected by the bird frame, after the Fourier transformation is carried out on the image, determining that the edge belongs to a high-frequency component or a low-frequency component, and when the edge belongs to the high-frequency component, judging that the picture detected by the bird frame is clear; when the bird frame belongs to the low-frequency component, the picture detected by the bird frame is judged to be fuzzy, the clear image is subjected to the judgment of the visibility of the key points, and the fuzzy image is discarded.
As a further scheme of the application: when the quality evaluation is carried out according to the visibility of the key points, the visible key points are determined, whether the visible key points meet the basic key point requirements is judged, and when the basic key point requirements are met, the image quality evaluation is qualified; otherwise, the image quality is evaluated as unacceptable.
As a further scheme of the application: the basic key point requirements are as follows: left or right eye, left or right wing, neck, back and tail.
As a further scheme of the application: when the bird species are identified, a resnet50 classification model is adopted, a bird classification data set is constructed through wetland scenes and network data, and the resnet50 classification model is trained.
It is another object of the present application to provide a bird recognition quality assessment system based on bird keypoint detection, the system comprising:
the image acquisition module is used for acquiring video data;
the bird detection module is used for detecting bird frames and key points of birds for each frame in the video data, outputting bird detection frames and key point positions, and each key point is correspondingly provided with a visibility tag;
the quality evaluation module is used for evaluating the quality of each frame of image in the video data according to the size of the picture, the definition of the picture and the visibility of the key points detected by the bird frame;
and the bird recognition module is used for recognizing the types of birds in the image with qualified quality evaluation to obtain a recognition result.
Compared with the prior art, the application has the beneficial effects that:
the application evaluates the quality of the identification image before bird model identification, selects the image with high quality for identification, and discards the images with low quality. Specifically, quality evaluation is performed on each frame of image in the video data according to the size, the definition and the visibility of key points of the detected bird frame; and further, the recognition model can be ensured to recognize based on some key distinguishing features of birds, some images with missing key parts caused by the orientation or the action of the birds can be filtered out, the recognition error rate is reduced, and therefore better image frames are selected to improve the recognition accuracy.
Drawings
FIG. 1 is a flow chart of a bird recognition quality assessment method based on bird keypoint detection.
Fig. 2 is a schematic structural diagram of a bird recognition quality evaluation system based on bird key point detection.
Description of the embodiments
In order to make the objects, technical solutions and advantages of the present application more clear, the present application will be described in further detail with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
Specific implementations of the application are described in detail below in connection with specific embodiments.
As shown in fig. 1, an embodiment of the present application provides a bird recognition quality evaluation method based on bird key point detection, the method comprising the steps of:
s100, acquiring video data;
s200, detecting bird frames and key points of birds in each frame of video data, outputting bird detection frames and key point positions, wherein each key point corresponds to a visibility label;
s300, evaluating the quality of each frame of image in the video data according to the size, the definition and the visibility of key points of the detected bird frame;
s400, identifying the types of birds in the image with qualified quality evaluation, and obtaining an identification result.
In the aspect of wetland protection, birds in nature are monitored and recorded for a long time, and the types of the birds are identified, so that the survival and migration conditions of species are conveniently researched, and corresponding measures are taken to protect endangered species. Currently, in most bird monitoring schemes of intelligent wetlands, the main scheme is: a large number of cameras are arranged in the protection area to collect bird image data in the protection area, the collected data are manually marked and then used as training samples, so that an AI model learns important characteristics of birds including but not limited to information such as outlines, postures and key part characteristics through existing data, and the image characteristics are analyzed through a classifier to determine specific types of birds. In the above process, only enough pictures (training samples) are provided for the AI model, so that a better recognition effect can be obtained. In an actual application scene, the acquired picture is poor in definition and key parts of birds are shielded under the influence of realistic factors such as environment, illumination, species distribution and the like, so that the identification result is unstable. Therefore, in bird video recognition, if an accurate high-quality bird image can be selected, the recognition accuracy can be improved, and the required recognition operation resources can be reduced.
In the embodiment of the application, video data is obtained through a video acquisition terminal, and in bird recognition application, the video acquisition terminal is often deployed in a protection area with rare human cigarettes and is used for capturing video of a camera coverage area so as to observe the number, the type, the habit and the like of birds, and meanwhile, the video data is used for inputting an algorithm, and the offline video data is data acquired and stored by the video acquisition terminal.
In the embodiment of the application, when the key point of the bird is detected, the yolov8 key point detection model is used, the marked bird frame and the key point data set are used for training, and after the yolov8 key point detection model is trained, the key points of the bird frame and the bird can be detected simultaneously. The yolov8 detection model can also be replaced by commonly used models of CPM, deeperCut, CMU OpenPose, alphaPose and the like, and the model is retrained by using marked bird frames and key point data sets.
In the embodiment of the application, the key points of the bird include back, beak, abdomen, crown, chest, forehead, left eye, left leg, left wing, neck, right eye, right leg, right wing, tail and throat. The embodiment of the application can output the bird detection frame and the positions of the key points, and each key point is correspondingly provided with a visibility label which indicates whether the key point is shielded or not.
In the embodiment of the application, because the definition of the birds is an important factor affecting the recognition result, the picture size and the picture definition of the bird frame detection are required to be evaluated, when the quality evaluation is carried out on the picture size of the bird frame detection, the images are screened through the width and the height of the bird detection frame, and the images which are larger than the set width and the set height are subjected to the judgment on the picture definition and the visibility of key points; otherwise, the image is discarded. The detail of the waiting bird and the size of the image are positively correlated in most of the bird monitoring environment, so the method is simple and effective.
In the embodiment of the application, the unclear acquired image is mainly caused by motion blur caused by unfocused or too fast bird motion in the shooting process, and the unclear image edge is not obvious. When the quality evaluation is carried out on the definition of the picture detected by the bird frame, after the Fourier transformation is carried out on the image, determining that the edge belongs to a high-frequency component or a low-frequency component, and when the edge belongs to the high-frequency component, judging that the picture detected by the bird frame is clear; when the bird frame belongs to the low-frequency component, the picture detected by the bird frame is judged to be fuzzy, the clear image is subjected to the judgment of the visibility of the key points, and the fuzzy image is discarded.
In the embodiment of the application, because the identification of the birds is mainly carried out by judging the types of important characteristics of the birds, particularly when the same genus carries out type classification, the characteristics of a key part are key for distinguishing the types of the birds, so that the visibility of key points in the image is required to be evaluated. When the quality evaluation is carried out according to the visibility of the key points, the visible key points are determined, whether the visible key points meet the basic key point requirements is judged, and when the basic key point requirements are met, the image quality evaluation is qualified; otherwise, the image quality is evaluated as unacceptable. The basic key point requirements are as follows: left or right eye, left or right wing, neck, back and tail. In addition, the basic key point requirements can be adjusted according to the type of the actual identified bird. According to the embodiment of the application, based on the visibility of the key parts of the birds as a standard, the recognition model can be ensured to recognize based on some key distinguishing characteristics of the birds, some images with missing key parts caused by the orientation or the action of the birds can be filtered out, the recognition error rate is reduced, and therefore, better image frames are selected to improve the recognition accuracy.
In the embodiment of the application, when the types of birds are identified, a resnet50 classification model is adopted, a bird classification data set is constructed through wetland scenes and network data, and the resnet50 classification model is trained.
As shown in fig. 2, the embodiment of the application further provides a bird recognition quality evaluation system based on bird key point detection, which comprises:
the image acquisition module 100 is used for acquiring video data;
the bird detection module 200 is configured to perform bird frame detection and bird key point detection on each frame in the video data, output a bird detection frame and a key point position, and each key point corresponds to a visibility tag;
the quality evaluation module 300 is configured to perform quality evaluation on each frame of image in the video data according to the size of the frame, the definition of the frame, and the visibility of the key points detected by the bird frame;
the bird recognition module 400 is used for recognizing the types of birds in the image with qualified quality evaluation to obtain a recognition result.
The foregoing description of the preferred embodiments of the present application should not be taken as limiting the application, but rather should be understood to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the application.
It should be understood that, although the steps in the flowcharts of the embodiments of the present application are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in various embodiments may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or other steps.
Those skilled in the art will appreciate that all or part of the processes in the methods of the above embodiments may be implemented by a computer program for instructing relevant hardware, where the program may be stored in a non-volatile computer readable storage medium, and where the program, when executed, may include processes in the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
Other embodiments of the present disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
Claims (9)
1. A bird recognition quality assessment method based on bird key point detection, characterized in that the method comprises the following steps:
acquiring video data;
performing bird frame detection and bird key point detection on each frame in the video data, outputting a bird detection frame and key point positions, wherein each key point corresponds to a visibility label;
performing quality evaluation on each frame of image in the video data according to the size of the detected picture, the definition of the picture and the visibility of the key points;
and identifying the types of birds in the image with qualified quality evaluation to obtain an identification result.
2. The bird recognition quality evaluation method based on bird keypoint detection according to claim 1, wherein when performing the bird keypoint detection, a yolov8 keypoint detection model is used, training is performed using the marked bird frame and keypoint data set, and after the yolov8 keypoint detection model is trained, the bird frame and the bird keypoints can be detected simultaneously.
3. The method for assessing the quality of bird identification based on the detection of key points of birds according to claim 1, wherein the key points of birds comprise back, beak, abdomen, crown, chest, forehead, left eye, left leg, left wing, neck, right eye, right leg, right wing, tail and throat.
4. The bird recognition quality evaluation method based on bird key point detection according to claim 1, wherein when the quality evaluation is performed on the picture size of the bird frame detection, images are screened by the width and the height of the bird detection frame, and the pictures larger than the set width and the set height are subjected to the judgment of the picture definition and the visibility of the key point; otherwise, the image is discarded.
5. The bird recognition quality evaluation method based on bird key point detection according to claim 1, wherein when the quality evaluation is performed on the sharpness of the picture detected by the bird frame, after fourier transformation is performed on the image, it is determined that the edge belongs to a high frequency component or a low frequency component, and when the edge belongs to the high frequency component, it is determined that the picture detected by the bird frame is sharp; when the bird frame belongs to the low-frequency component, the picture detected by the bird frame is judged to be fuzzy, the clear image is subjected to the judgment of the visibility of the key points, and the fuzzy image is discarded.
6. The bird recognition quality evaluation method based on bird key point detection according to claim 1, wherein when the quality evaluation is performed according to the visibility of the key points, the visible key points are determined, whether the visible key points meet the basic key point requirement is judged, and when the basic key point requirements are met, the image quality evaluation is qualified; otherwise, the image quality is evaluated as unacceptable.
7. The bird recognition quality assessment method based on bird keypoint detection of claim 6, wherein the basic keypoint requirements are: left or right eye, left or right wing, neck, back and tail.
8. The bird recognition quality evaluation method based on bird key point detection according to claim 1, wherein when the types of birds are recognized, a resnet50 classification model is adopted, a bird classification data set is constructed through wetland scenes and network data, and the resnet50 classification model is trained.
9. A bird recognition quality assessment system based on bird keypoint detection, the system comprising:
the image acquisition module is used for acquiring video data;
the bird detection module is used for detecting bird frames and key points of birds for each frame in the video data, outputting bird detection frames and key point positions, and each key point is correspondingly provided with a visibility tag;
the quality evaluation module is used for evaluating the quality of each frame of image in the video data according to the size of the picture, the definition of the picture and the visibility of the key points detected by the bird frame;
and the bird recognition module is used for recognizing the types of birds in the image with qualified quality evaluation to obtain a recognition result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310856044.3A CN116912880A (en) | 2023-07-13 | 2023-07-13 | Bird recognition quality assessment method and system based on bird key point detection |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310856044.3A CN116912880A (en) | 2023-07-13 | 2023-07-13 | Bird recognition quality assessment method and system based on bird key point detection |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116912880A true CN116912880A (en) | 2023-10-20 |
Family
ID=88355804
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310856044.3A Pending CN116912880A (en) | 2023-07-13 | 2023-07-13 | Bird recognition quality assessment method and system based on bird key point detection |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116912880A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117809099A (en) * | 2023-12-29 | 2024-04-02 | 百鸟数据科技(北京)有限责任公司 | Method and system for predicting bird category by means of key part prediction network |
CN117975344A (en) * | 2024-04-02 | 2024-05-03 | 吉林省中农阳光数据有限公司 | Method and device for identifying uniqueness of cow face |
-
2023
- 2023-07-13 CN CN202310856044.3A patent/CN116912880A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117809099A (en) * | 2023-12-29 | 2024-04-02 | 百鸟数据科技(北京)有限责任公司 | Method and system for predicting bird category by means of key part prediction network |
CN117975344A (en) * | 2024-04-02 | 2024-05-03 | 吉林省中农阳光数据有限公司 | Method and device for identifying uniqueness of cow face |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zhang et al. | Animal detection from highly cluttered natural scenes using spatiotemporal object region proposals and patch verification | |
CN112528960B (en) | Smoking behavior detection method based on human body posture estimation and image classification | |
CN116912880A (en) | Bird recognition quality assessment method and system based on bird key point detection | |
CN110008909B (en) | Real-name system business real-time auditing system based on AI | |
CN111368758B (en) | Face ambiguity detection method, face ambiguity detection device, computer equipment and storage medium | |
CN111626123A (en) | Video data processing method and device, computer equipment and storage medium | |
CN105512683A (en) | Target positioning method and device based on convolution neural network | |
CN111160275B (en) | Pedestrian re-recognition model training method, device, computer equipment and storage medium | |
WO2022213540A1 (en) | Object detecting, attribute identifying and tracking method and system | |
CN114049499A (en) | Target object detection method, apparatus and storage medium for continuous contour | |
CN112528823A (en) | Striped shark movement behavior analysis method and system based on key frame detection and semantic component segmentation | |
CN110618129A (en) | Automatic power grid wire clamp detection and defect identification method and device | |
CN113076860B (en) | Bird detection system under field scene | |
CN117475353A (en) | Video-based abnormal smoke identification method and system | |
CN115797970B (en) | Dense pedestrian target detection method and system based on YOLOv5 model | |
CN106650824B (en) | Moving object classification method based on support vector machines | |
CN116994049A (en) | Full-automatic flat knitting machine and method thereof | |
CN117152625A (en) | Remote sensing small target identification method, system, equipment and medium based on CoordConv and Yolov5 | |
CN107403192B (en) | Multi-classifier-based rapid target detection method and system | |
CN111402185A (en) | Image detection method and device | |
CN111935480B (en) | Detection method for image acquisition device and related device | |
CN114724091A (en) | Method and device for identifying foreign matters on transmission line wire | |
CN114663803A (en) | Logistics center hanging clothing classification method and device based on video streaming | |
CN111191575B (en) | Naked flame detection method and system based on flame jumping modeling | |
CN112907206A (en) | Service auditing method, device and equipment based on video object identification |
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 |