CN114494965A - Method and system for detecting wandering pets based on vision - Google Patents

Method and system for detecting wandering pets based on vision Download PDF

Info

Publication number
CN114494965A
CN114494965A CN202210089984.XA CN202210089984A CN114494965A CN 114494965 A CN114494965 A CN 114494965A CN 202210089984 A CN202210089984 A CN 202210089984A CN 114494965 A CN114494965 A CN 114494965A
Authority
CN
China
Prior art keywords
pet
wandering
target
image
detected
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
Application number
CN202210089984.XA
Other languages
Chinese (zh)
Inventor
李山路
朱光强
王和平
欧阳一村
陈芳明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Maxvision Technology Corp
Original Assignee
Maxvision Technology Corp
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Maxvision Technology Corp filed Critical Maxvision Technology Corp
Priority to CN202210089984.XA priority Critical patent/CN114494965A/en
Publication of CN114494965A publication Critical patent/CN114494965A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/253—Fusion techniques of extracted features
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/047—Probabilistic or stochastic networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2200/00—Indexing scheme for image data processing or generation, in general
    • G06T2200/32—Indexing scheme for image data processing or generation, in general involving image mosaicing
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20021—Dividing image into blocks, subimages or windows
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20112—Image segmentation details
    • G06T2207/20132—Image cropping

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Probability & Statistics with Applications (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Quality & Reliability (AREA)
  • Image Analysis (AREA)

Abstract

The invention relates to the technical field of city management, in particular to a method and a system for detecting a wandering pet based on vision, which comprises the following steps: an image acquisition step: collecting and transmitting video data to a first target detector; and a target detection step: performing frame-separated detection on the video data by a target detector to obtain a corresponding target picture; obtaining an image block: performing target cutting on the detected pet picture to obtain an image block; and (3) target secondary detection: inputting the image block into a second target detector to detect whether the pet has wearing characteristics; confirming the wandering pets: and confirming the pet without the detected wearing characteristics as the wandering pet. According to the invention, by detecting the pet, whether the collar, the rope and the clothes exist on the pet body is further detected, and whether the pet is a wandering pet is further judged, so that the detection efficiency of the wandering pet is improved.

Description

Method and system for detecting wandering pets based on vision
Technical Field
The invention relates to the technical field of city management, in particular to a method and a system for detecting a wandering pet based on vision.
Background
Along with the acceleration of the urbanization process, more and more people are kept in cities, and the phenomena of urban wandering cats and wandering dogs are frequent due to other reasons such as poor caretaking and the like. Hundreds of thousands or even millions of wandering pets exist in the whole country every year, and the wandering pets are distributed in cities where people live, so that the wandering pets have great influence on the living environment, health and safety and public order of people. The biggest problem that the wandering pets confuse people is that the wandering pets are healthy and safe to the public, unknown viruses may be carried by the wandering pets, the unattended wandering pets maliciously hurt people, and bacterial breeding caused by the excrement of the wandering pets also greatly affects people living nearby. Therefore, the method is an important subject to identify and position the wandering pet as soon as possible and facilitate the subsequent treatment of the problem of arranging the wandering pet.
Chinese patent No. 202011553697.7 provides a neural network-based animal identification method, system, device and storage medium, the method comprising: carrying out animal classification on the image through a trained animal classification network to obtain animal information of the image, including picture preprocessing; constructing a deep convolutional neural network, wherein the deep convolutional neural network comprises a feature extraction network and a training network, and the feature extraction network comprises a target detection part for extracting features and an image classification part for classifying and learning global information and features; performing model training, initializing a feature extraction network by using the trained weights, extracting features of all pictures, dividing the extracted features into a training set and a verification set, and performing training at a network layer; and classifying the pictures, and outputting a classification result to obtain a classification label with the maximum probability.
The unrestrained pet of prior art mode discernment mainly relies on the manpower to solve, has the owner to follow through looking over the pet and follows, perhaps the state of pet, for example: the conditions that the pet body is very dirty and the like are judged, the mode of artificially identifying the wandering pet is obviously not efficient enough, and the pet body cannot be deployed in each area in large batch due to the labor cost. Therefore, it is desirable to design a method and a system for detecting a wandering pet based on vision to solve the above problems.
Disclosure of Invention
The invention aims to provide a method and a system for detecting a wandering pet based on vision, which aim to solve the problem of low detection efficiency in the background technology.
The technical scheme of the invention is as follows: a detection method of a wandering pet based on vision comprises the following steps:
an image acquisition step: collecting and transmitting video data to a first target detector;
and a target detection step: performing frame-separated detection on the video data by a target detector to obtain a corresponding target picture;
obtaining an image block: performing target cutting on the detected pet picture to obtain an image block;
and (3) target secondary detection: inputting the image block into a second target detector to detect whether the pet has wearing characteristics;
confirming the wandering pets: and confirming the pet without the detected wearing characteristics as the wandering pet.
Further, in the step of confirming the wandering pet, whether people exist in the image blocks without wearing the characteristic pet is detected, and if no people are detected, the wandering pet is directly judged.
Further, in the step of confirming the wandering pet, if a person is detected, the centers of the pet and the person coordinate frames are obtained and judged, and when the center position of the pet coordinate frame appears in the upper half part of the person coordinate frame, the pet is in a state that the person holds the pet, and the pet is judged to be a non-wandering pet.
Further, in the step of obtaining the image blocks, the image blocks are cut by expanding outwards by one time according to the width and the height of the pet target.
Further, in the target detection step, when no pet is detected, the image acquisition step is returned to continue to acquire the image.
Further, in the target detection step, the frame detection range is 15-120 frames, in the target secondary detection step, the wearing characteristics of the pet include any one of a pet collar, a pet rope and pet clothes, when the pet collar, the pet rope or the pet clothes is detected to be in the image block, the pet is judged to be a non-wandering pet, and the image collection step is returned to continue to collect the image.
Further, in the object detection step, the coordinate frame information, the confidence information of the object and the class probability are provided through the first object detector.
A detection system for wandering pets based on vision comprises
An image acquisition module: collecting and transmitting video data to a first target detector;
a target detection module: performing frame-separated detection on the video data through a target detector to obtain a corresponding target picture;
an image block obtaining module: performing target cutting on the detected pet picture to obtain an image block;
a target secondary detection module: inputting the image block into a second target detector to detect whether the pet has wearing characteristics or not;
the wandering pet confirmation module: and confirming the pet without the detected wearing characteristics as the wandering pet.
Further, in the wandering pet confirmation module, whether people exist in the image blocks without wearing the characteristic pet is detected, and if no people are detected, the wandering pet is directly judged.
Further, in the wandering pet confirmation module, if a person is detected, the centers of the pet and the person coordinate frames are obtained and judged, and when the center position of the pet coordinate frame appears in the upper half part of the person coordinate frame, the pet and the person coordinate frame belong to the situation that the person holds the pet, and the pet is judged to be a non-wandering pet.
Further, in the image block obtaining module, the image blocks are cut by expanding outwards by one time according to the width and the height of the pet target.
Further, in the target detection module, when no pet is detected, the target detection module returns to the image acquisition module to continue to acquire the image.
Further, in the target detection step, the frame detection range is 15-120 frames, in the target secondary detection module, the pet wearing feature includes any one of a pet collar, a pet leash and a pet clothes, and when the pet collar, the pet leash and the pet clothes are detected to exist in the image block, the image block is judged to be a non-wandering pet, and the image block returns to the image acquisition module to continue to acquire the image.
Further, in the object detection module, the coordinate frame information, the confidence information of the object and the class probability are provided through the first object detector.
The invention provides a method and a system for detecting a wandering pet based on vision through improvement, compared with the prior art, the method and the system have the following improvement and advantages:
(1) according to the invention, by detecting the pet, whether the collar, the rope and the clothes exist on the pet body is further detected, and whether the pet is a wandering pet is further judged, so that the detection efficiency of the wandering pet is improved.
(2) In order to prevent false alarm caused by missed detection, the invention judges whether the pet without the collar embraces the pet by combining the positions of the coordinate centers of the person and the pet, thereby analyzing the pet target more accurately.
Drawings
The invention is further explained below with reference to the figures and examples:
FIG. 1 is a flow chart of an embodiment of the present invention;
FIG. 2 is a flow chart of the detection of a first target detector according to an embodiment of the present invention;
fig. 3 is a detection flow chart of the second target detector according to the embodiment of the present invention.
Detailed Description
The present invention will be described in detail with reference to fig. 1 to 3, and the technical solutions in the embodiments of the present invention will be clearly and completely described, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
The detection method of the wandering pet based on the vision, disclosed by the embodiment of the invention, as shown in figures 1-3, comprises the following steps: the method comprises the following steps:
an image acquisition step: collecting and transmitting video data to a first target detector;
and a target detection step: the method comprises the following steps of performing frame-separated detection on pets and people through a pair of video data of a target detector, and obtaining corresponding target pictures, wherein the pets are pets such as cats, dogs and the like, and the processing of a pair of images by the target detector comprises the following steps:
data enhancer step: randomly scaling, cutting and splicing the image blocks in a Mosaic data enhancement mode;
an image feature extraction sub-step; slicing the image block through a Focus structure, obtaining image characteristics through convolution kernel convolution, then mapping the image characteristics into 2 parts through a CSP structure, and merging the parts in a cross-stage and a cross-level manner, so that the repeated calculation amount of gradient information is reduced, and the accuracy is ensured;
an image characteristic processing substep: processing image characteristics through a network structure of the FPN and the PAN, and fusing information of the pictures by using a structure of the CSP 2;
obtaining an image block: performing target cutting on the detected pet picture to obtain an image block;
and (3) target secondary detection: inputting the image block into a second target detector to detect whether the pet has wearing characteristics, wherein the second target detector has the same principle as the first target detector;
confirming the wandering pets: and confirming the pet without the detected wearing characteristics as the wandering pet.
Further, in the step of confirming the wandering pet, whether people exist in the image blocks without wearing the characteristic pet is detected, and if no people are detected, the wandering pet is directly judged.
Further, in the step of confirming the wandering pet, if a person is detected, the centers of the pet and the person coordinate frames are obtained and judged, and when the center position of the pet coordinate frame appears in the upper half part of the person coordinate frame, the pet is in a state that the person holds the pet, and the pet is judged to be a non-wandering pet.
Furthermore, in the step of obtaining the image block, the image block is cut by expanding one time according to the width and the height of the pet target, so that more information about a pet collar, a pet rope, a pet wearing clothes and a person can be presented in the image block, the information reflected by the image block is more comprehensive, the false alarm is prevented, and the accuracy of identifying the wandering pet is improved.
Further, in the target detection step, when no pet is detected, the image acquisition step is returned to continue to acquire the image.
Further, in the target detection step, the frame detection range is 15-120 frames, in the target secondary detection step, the wearing characteristics of the pet include any one of a pet collar, a pet rope and pet clothes, when the pet collar, the pet rope or the pet clothes is detected to exist in the image block, the pet is judged to be a non-wandering pet, and the image collection step is returned to continue to collect the image.
Further, in the object detection step, the coordinate frame information, the confidence information of the object and the class probability are provided through the first object detector.
A detection system for wandering pets based on vision comprises
An image acquisition module: collecting and transmitting video data to a first target detector;
a target detection module: the method comprises the following steps of performing frame-separated detection on pet and people through a pair of video data of an object detector, and obtaining a corresponding object picture, wherein the processing of a pair of images of the object detector comprises the following modules:
a data enhancer module: randomly scaling, cutting and splicing the image blocks in a Mosaic data enhancement mode;
an image feature extraction submodule; slicing the image block through a Focus structure, obtaining image characteristics through convolution kernel convolution, then mapping the image characteristics into 2 parts through a CSP structure, and merging the parts in a cross-stage and a cross-level manner, so that the repeated calculation amount of gradient information is reduced, and the accuracy is ensured;
an image characteristic processing submodule: processing image characteristics through a network structure of the FPN and the PAN, and fusing information of the pictures by using a structure of the CSP 2;
an image block obtaining module: performing target cutting on the detected pet picture to obtain an image block;
a target secondary detection module: inputting the image block into a second target detector to detect whether the pet has wearing characteristics;
the wandering pet confirmation module: and confirming the pet without the detected wearing characteristics as the wandering pet.
Further, in the wandering pet confirmation module, whether people exist in the image blocks without wearing the characteristic pets is detected, and if no people are detected, the wandering pet is directly judged.
Further, in the wandering pet confirmation module, if a person is detected, the centers of the pet and the person coordinate frames are obtained and judged, and when the center position of the pet coordinate frame appears in the upper half part of the person coordinate frame, the pet and the person coordinate frame belong to the situation that the person holds the pet, and the pet is judged to be a non-wandering pet.
Furthermore, in the image block obtaining module, the image blocks are cut by expanding one time according to the width and the height of the pet target, so that more information about a pet collar, a pet rope, a pet wearing clothes and a person can be presented in the image blocks, the information reflected by the image blocks is more comprehensive, the false alarm is prevented, and the accuracy of identifying the wandering pet is improved.
Further, in the target detection module, when no pet is detected, the target detection module returns to the image acquisition module to continue to acquire the image.
Further, in the target detection step, the frame detection range is 15-120 frames, in the target secondary detection module, the pet wearing feature includes any one of a pet collar, a pet leash and a pet clothes, and when the pet collar, the pet leash and the pet clothes are detected to exist in the image block, the image block is judged to be a non-wandering pet, and the image block returns to the image acquisition module to continue to acquire the image.
Further, in the object detection module, the coordinate frame information, the confidence information of the object and the class probability are provided through the first object detector.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (14)

1. A detection method of a wandering pet based on vision is characterized by comprising the following steps:
an image acquisition step: collecting and transmitting video data to a first target detector;
and a target detection step: performing frame-separated detection on the video data through a target detector to obtain a corresponding target picture;
obtaining an image block: performing target cutting on the detected pet picture to obtain an image block;
and (3) target secondary detection: inputting the image block into a second target detector to detect whether the pet has wearing characteristics;
confirming the wandering pets: and confirming the pet without the detected wearing characteristics as the wandering pet.
2. The vision-based detection method for the wandering pet of claim 1, wherein in the wandering pet confirmation step, whether a person exists is detected in the image block without the wearing feature pet, and if the person is not detected, the pet is directly determined as the wandering pet.
3. The method for detecting a wandering pet based on vision of claim 2, wherein in the step of confirming the wandering pet, if a person is detected, the centers of the pet and the person are obtained and judged, and when the center position of the pet coordinate frame appears in the upper half part of the person coordinate frame, the pet is in a situation that the person holds the pet, and the pet is judged to be a non-wandering pet.
4. The vision-based detection method for wandering pets according to claim 1, wherein in the step of obtaining image patches, the image patches are cut by expanding outwards by one time according to the width and height of the pet target.
5. The vision-based detection method for wandering pets according to claim 1, wherein in the target detection step, when no pet is detected, the image acquisition step is returned to continue to acquire the image.
6. The method for detecting a wandering pet based on vision as claimed in claim 1, wherein in the target detection step, the detection range of every frame is 15-120 frames, in the target secondary detection step, the wearing feature of the pet comprises any one of a pet collar, a pet rope and a pet clothes, and when the pet collar, the pet rope or the pet clothes is detected in the image block, the pet collar, the pet rope or the pet clothes is judged to be a non-wandering pet, and the image acquisition step is returned to continue to acquire the image.
7. The vision-based detection method of a wandering pet of claim 1, wherein in the object detection step, the coordinate frame information, the confidence level information of the object, and the category probability are provided by a first object detector.
8. A detection system for wandering pets based on vision is characterized by comprising
An image acquisition module: collecting and transmitting video data to a first target detector;
a target detection module: performing frame-separated detection on the video data by a target detector to obtain a corresponding target picture;
an image block obtaining module: performing target cutting on the detected pet picture to obtain an image block;
a target secondary detection module: inputting the image block into a second target detector to detect whether the pet has wearing characteristics;
the wandering pet confirmation module: and confirming the pet without the detected wearing characteristics as the wandering pet.
9. The vision-based detection system for the wandering pet of claim 8, wherein in the wandering pet confirmation module, the image blocks of the pet without wearing the characteristics are detected to determine whether a person exists, and if no person is detected, the pet is directly determined as the wandering pet.
10. The vision-based detection system for the wandering pet of claim 9, wherein in the wandering pet confirmation module, if a person is detected, the centers of the pet and the person are obtained and judged, and when the center position of the pet coordinate frame appears in the upper half of the person coordinate frame, the pet is in a situation that the person holds the pet, and the pet is judged to be a non-wandering pet.
11. The vision-based detection system for wandering pet of claim 8, wherein in the image patch obtaining module, the image patches are cut by expanding outwards by one time according to the width and height of the pet target.
12. The vision-based detection system for wandering pet of claim 8, wherein in the object detection module, the detection module returns to the image capture module to continue capturing images when no pet is detected.
13. The vision-based detection system for the wandering pet of claim 8, wherein in the target detection step, the detection range of every other frame is 15-120 frames, in the target secondary detection module, the pet wearing feature comprises any one of a pet collar, a pet rope and pet clothes, and when the pet collar, the pet rope or the pet clothes is detected in the image block, the image is determined to be a non-wandering pet, and the image acquisition module is returned to continue to acquire the image.
14. The vision-based wandering pet detection system of claim 8, wherein the providing of the coordinate frame information, the confidence information of the object, and the class probability is performed by an object detector one in the object detection module.
CN202210089984.XA 2022-01-25 2022-01-25 Method and system for detecting wandering pets based on vision Pending CN114494965A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210089984.XA CN114494965A (en) 2022-01-25 2022-01-25 Method and system for detecting wandering pets based on vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210089984.XA CN114494965A (en) 2022-01-25 2022-01-25 Method and system for detecting wandering pets based on vision

Publications (1)

Publication Number Publication Date
CN114494965A true CN114494965A (en) 2022-05-13

Family

ID=81475271

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210089984.XA Pending CN114494965A (en) 2022-01-25 2022-01-25 Method and system for detecting wandering pets based on vision

Country Status (1)

Country Link
CN (1) CN114494965A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115063751A (en) * 2022-07-27 2022-09-16 深圳市海清视讯科技有限公司 Pet leash detection method, equipment and storage medium
CN116385965A (en) * 2023-03-17 2023-07-04 深圳市明源云科技有限公司 Method, apparatus and computer readable storage medium for identifying a wandering animal

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115063751A (en) * 2022-07-27 2022-09-16 深圳市海清视讯科技有限公司 Pet leash detection method, equipment and storage medium
CN116385965A (en) * 2023-03-17 2023-07-04 深圳市明源云科技有限公司 Method, apparatus and computer readable storage medium for identifying a wandering animal

Similar Documents

Publication Publication Date Title
CN104303193B (en) Target classification based on cluster
TWI416068B (en) Object tracking method and apparatus for a non-overlapping-sensor network
CN114494965A (en) Method and system for detecting wandering pets based on vision
CN108319926A (en) A kind of the safety cap wearing detecting system and detection method of building-site
Schmid et al. The LOKI underwater imaging system and an automatic identification model for the detection of zooplankton taxa in the Arctic Ocean
CN109800802A (en) Visual sensor and object detecting method and device applied to visual sensor
CN111210399B (en) Imaging quality evaluation method, device and equipment
CN110532899B (en) Sow antenatal behavior classification method and system based on thermal imaging
CN111310596A (en) Animal diseased state monitoring system and method
CN113269091A (en) Personnel trajectory analysis method, equipment and medium for intelligent park
CN111161265A (en) Animal counting and image processing method and device
CN113076818A (en) Pet excrement identification method and device and computer readable storage medium
US11935378B2 (en) Intrusion detection methods and devices
CN106650623A (en) Face detection-based method for verifying personnel and identity document for exit and entry
KR102584357B1 (en) Apparatus for identifying a livestock using a pattern, and system for classifying livestock behavior pattern based on images using the apparatus and method thereof
CN110852236A (en) Target event determination method and device, storage medium and electronic device
CA3230401A1 (en) Systems and methods for the automated monitoring of animal physiological conditions and for the prediction of animal phenotypes and health outcomes
CN111797831A (en) BIM and artificial intelligence based parallel abnormality detection method for poultry feeding
CN111753610A (en) Weather identification method and device
KR102527058B1 (en) Apparatus for detecting mounting behavior of cattle
CN116546287A (en) Multi-linkage wild animal online monitoring method and system
CN113837138B (en) Dressing monitoring method, dressing monitoring system, dressing monitoring medium and electronic terminal
JP6893812B2 (en) Object detector
CN113068657B (en) Intelligent efficient pig raising method and system
WO2021022427A1 (en) Community stray-animal monitoring system and monitoring method

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