CN113378648A - Artificial intelligence port and wharf monitoring method - Google Patents
Artificial intelligence port and wharf monitoring method Download PDFInfo
- Publication number
- CN113378648A CN113378648A CN202110543771.5A CN202110543771A CN113378648A CN 113378648 A CN113378648 A CN 113378648A CN 202110543771 A CN202110543771 A CN 202110543771A CN 113378648 A CN113378648 A CN 113378648A
- Authority
- CN
- China
- Prior art keywords
- dangerous
- image
- video
- dangerous behavior
- artificial intelligence
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 19
- 230000006399 behavior Effects 0.000 claims abstract description 72
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims description 8
- 238000012706 support-vector machine Methods 0.000 claims description 6
- 238000011410 subtraction method Methods 0.000 claims description 5
- 230000004927 fusion Effects 0.000 claims description 4
- 230000000877 morphologic effect Effects 0.000 claims description 4
- 238000005286 illumination Methods 0.000 abstract description 7
- 230000009471 action Effects 0.000 description 6
- 238000001514 detection method Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000000391 smoking effect Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Images
Classifications
-
- 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
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Alarm Systems (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, in particular to a method for monitoring an artificial intelligence port and wharf; the wharf oil depot monitoring video is obtained through the high-definition camera, and is preprocessed, so that the influence of illumination and background is reduced; extracting a foreground target area in a preprocessed video, preprocessing the foreground target area to reduce interference and obtain a dangerous behavior image; then extracting dangerous features in the dangerous behavior image, so as to facilitate later-stage identification and classification; dangerous characteristic samples which are manufactured in advance are input into the classifier, then dangerous behaviors are identified and classified by inputting dangerous characteristics which are actually extracted into the classifier, a dangerous behavior conclusion is obtained, the conclusion is uploaded to a manager, the manager can conveniently and timely prevent the dangerous behaviors, safety is guaranteed, artificial intelligence is adopted for monitoring, identifying and reminding, and monitoring efficiency is improved.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an artificial intelligence port and wharf monitoring method.
Background
At present, port trade activity is more frequent, and obtains good development achievement, but wherein has certain potential safety hazard, especially in the aspect of port petrochemical industry pier, often can deposit or transport dangerous goods such as oil, easy burning, explosion, when actual storage jar oil charging, if do not make sufficient effectual monitoring work, for example banning fire control, will lead to wherein having the potential safety hazard, can't guarantee pier's safety really.
In the prior art, safety monitoring of a port petrochemical industry wharf oil depot is basically performed in a mode of patrolling and spot-checking by personnel on site or manually checking a monitoring video and the like, and monitoring time and space are very limited, so that efficiency is low.
Disclosure of Invention
The invention aims to provide an artificial intelligent port and wharf monitoring method, and aims to solve the technical problem that in the prior art, safety monitoring of a port petrochemical industry wharf oil depot is basically performed in the modes of patrolling and spot inspection by personnel on site, or manually checking a monitoring video, and the like, so that the monitoring time and space are very limited, and the efficiency is low.
In order to achieve the purpose, the artificial intelligence port and pier monitoring method adopted by the invention comprises the following steps:
acquiring a wharf oil depot monitoring video, and preprocessing the wharf oil depot monitoring video to obtain a preprocessed video;
extracting a foreground target area of the preprocessed video, and preprocessing the foreground target area to obtain a dangerous behavior image;
analyzing and extracting the dangerous behavior image to obtain dangerous characteristics;
and inputting the pre-obtained dangerous feature samples into a classifier, inputting the dangerous features into the classifier, completing the identification and classification of dangerous behaviors, and transmitting a dangerous behavior conclusion to a manager.
Processing the obtained wharf oil depot monitoring video, extracting a foreground target area, extracting a dangerous behavior image, and finally extracting dangerous features in the dangerous behavior image; dangerous characteristic samples are input into the classifier in advance, the actually extracted dangerous characteristics are input into the classifier to be classified and recognized, and finally, dangerous behavior recognition results are uploaded to managers, so that the managers can find dangerous behaviors conveniently, can take precautions in time, protect wharf safety and improve monitoring efficiency.
The method comprises the following steps of obtaining a wharf oil depot monitoring video, preprocessing the wharf oil depot monitoring video to obtain a preprocessed video, and further comprises the following steps:
and converting the image sequence of the wharf oil depot monitoring video into gray scale by adopting a YUV space color model to obtain the preprocessed video.
And the YUV space color model is utilized to convert the image sequence into gray scale, so that the influence of illumination and complex color background is reduced, and the detection accuracy is improved.
Extracting a foreground target area of the preprocessed video, preprocessing the foreground target area to obtain a dangerous behavior image, wherein the method further comprises the following steps:
and establishing a background model based on a ViBe algorithm, separating a foreground target area in the preprocessed video, and extracting a suspected dangerous behavior area by combining a background subtraction method to obtain an image of the suspected dangerous behavior area.
The ViBe algorithm and the background subtraction method are combined, so that the image sequence can be processed in real time, interference is reduced, and the detection efficiency is improved.
Extracting a foreground target area of the preprocessed video, preprocessing the foreground target area to obtain a dangerous behavior image, wherein the method further comprises the following steps:
and carrying out image denoising and morphological processing on the suspected dangerous behavior area image to obtain the dangerous behavior image.
The influence of environment and illumination is reduced, the binary image of the suspected dangerous behavior area is optimized, and a foundation is laid for subsequent feature extraction.
Analyzing and extracting the dangerous behavior image to obtain dangerous features, wherein the method further comprises the following steps:
and extracting the HOG characteristic and the LBP texture characteristic of the dangerous behavior image, and fusing the HOG characteristic and the LBP texture characteristic by using a serial fusion algorithm to obtain a dangerous characteristic.
And the features are classified and detected by using a serial fusion algorithm, so that dangerous features can be better identified in the follow-up process.
The method comprises the following steps of inputting a pre-acquired dangerous feature sample into a classifier, inputting the dangerous feature into the classifier, completing identification and classification of dangerous behaviors, and transmitting a dangerous behavior conclusion to a manager, wherein the method further comprises the following steps:
and selecting a support vector machine as a classifier for dangerous behavior recognition.
The support vector machine is suitable for small sample images, the memory occupation is small, and the operation classification speed is relatively high.
The invention relates to an artificial intelligent port and pier monitoring method, which comprises the steps of firstly, acquiring a pier oil depot monitoring video through a high-definition camera, preprocessing the pier oil depot monitoring video to reduce the influence of illumination and background, extracting a foreground target area in the preprocessed video, preprocessing the foreground target area to reduce interference to obtain a dangerous behavior image, then extracting dangerous characteristics in the dangerous behavior image to facilitate later-stage identification and classification, inputting a prefabricated dangerous characteristic sample into a classifier, inputting the actually extracted dangerous characteristics into the classifier to identify and classify dangerous behaviors to obtain a dangerous behavior conclusion, uploading the dangerous behavior conclusion to a manager to warn the manager, so that the manager can prevent dangerous behaviors in time and guarantee safety, and simultaneously monitoring, identifying and reminding through artificial intelligence, the monitoring efficiency is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a step diagram of the artificial intelligence port terminal monitoring method of the invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
In the description of the present invention, it is to be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on the orientations or positional relationships illustrated in the drawings, and are used merely for convenience in describing the present invention and for simplicity in description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed in a particular orientation, and be operated, and thus, are not to be construed as limiting the present invention. Further, in the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
Referring to fig. 1, the present invention provides an artificial intelligence port and pier monitoring method, which includes the following steps:
s101: the method comprises the steps of obtaining a wharf oil depot monitoring video, and preprocessing the wharf oil depot monitoring video to obtain a preprocessed video.
Specifically, at first, at a plurality of high definition digtal cameras of pier oil depot installation, acquire through high definition digtal camera pier oil depot surveillance video, and will pier oil depot surveillance video uploads to central processing unit, then, central processing unit adopts YUV space color model right pier oil depot surveillance video carries out the preliminary treatment, turns into the grey scale with the video image sequence to this reduces illumination and the influence of complicated colour background to the image, the discernment of the follow-up image of being convenient for, and then is favorable to improving the detection precision, in time judges out dangerous action, can in time make safeguard measure, improves monitoring efficiency.
S102: and extracting a foreground target area of the preprocessed video, and preprocessing the foreground target area to obtain a dangerous behavior image.
Specifically, firstly, a background model is established based on a ViBe algorithm, wherein the ViBe algorithm is a background modeling algorithm which can be applied to different videos and dynamic scenes, a random selection mechanism is adopted to establish the model, and an equal probability selection field is adopted to update the background, the main principle is that a sample set of pixel values of pixel points in the areas before and adjacent to the pixel point is arranged for the pixel point of a video image, then the similarity of the pixel value of the current pixel point and the background model, namely each point in the sample set, is calculated, whether the pixel point is a background point at the moment is judged by comparing whether the pixel point is in the similar range of the model, and a foreground target area in the preprocessed video is separated, wherein the foreground target area can be a dangerous behavior action image which endangers a storage oil tank, such as a smoking action image, an open fire action image and the like, then, combining with a background subtraction method to extract a suspected dangerous behavior area, wherein the background subtraction method is to utilize an established background model, then perform differential calculation on a current frame in a video and the background model to obtain an area of a foreground target, then compare the area with a set threshold value, judge the part exceeding the threshold value as the foreground target area, if the part not exceeding the threshold value is regarded as a background, and update a background picture in real time along with external change or the steering of a camera, further extract the foreground target area in real time to obtain an image of the suspected dangerous behavior area, and then perform image denoising and morphological processing on the image of the dangerous behavior area, wherein the image denoising adopts a median filtering principle, namely, an odd number of sliding windows combined by sampling points are used for sorting pixel values in the image, a central pixel value is replaced by the median value, and scattered noise points can be obviously reduced, and the fuzzy condition of the image is relieved, and the morphological processing operation can supplement the image so as to more accurately extract the dangerous behavior region and obtain the dangerous behavior image, so that the subsequent analysis and extraction are facilitated, the interference is reduced, and the detection effect is improved.
S103: and analyzing and extracting the dangerous behavior image to obtain dangerous characteristics.
Specifically, the dangerous behavior image is analyzed and extracted, HOG characteristics and LBP texture characteristics of the dangerous behavior image are extracted, wherein the HOG feature is a feature description operator for detecting the object in image processing and machine vision, the principle of the feature extraction is that the local information of the image can be effectively embodied by calculating the directional gradient histogram of the local area in the target image and counting the feature vectors, and has good performance in the aspects of illumination deformation prevention and translation deformation prevention, LBP texture characteristics are used as description operators for expressing textures, can meet the requirement of distribution rotation non-deformation in the dangerous behavior, and then the HOG characteristic and the LBP texture characteristic are fused through a serial fusion algorithm, and further, dangerous behavior characteristics can be well described, so that the dangerous characteristic description is better, sufficient and abundant, accurate basis is provided for further classification and identification, and sufficient preparation is made.
S104: and inputting the pre-obtained dangerous feature samples into a classifier, inputting the dangerous features into the classifier, completing the identification and classification of dangerous behaviors, and transmitting a dangerous behavior conclusion to a manager.
Specifically, firstly, a support vector machine is selected as a classifier for identifying dangerous behaviors, wherein the support vector machine is suitable for small sample images, the memory occupation is small, the operation classification speed is relatively high, then, videos of dangerous behaviors are recorded and processed, samples of dangerous behaviors and non-dangerous behaviors required in the dangerous behavior videos are intercepted, HOG characteristics and LBP texture characteristics of the samples are extracted and fused to generate a data set, then, the data set is guided into the support vector machine to generate the classifier, training of the classifier is carried out, when the classifier is used specifically, the dangerous characteristics generated in S103 are guided into the generated classifier, the classifier compares the dangerous characteristics with the dangerous characteristic samples to carry out identification and classification, finally, a conclusion of the dangerous behaviors is obtained, and the conclusion is edited into warning information, wherein, warning information can remind for pronunciation, text message, flashing light are reminded etc to convey to managers to this informs that managers appears dangerous action, makes managers can in time control dangerous action, avoids dangerous emergence, adopts artificial intelligence to assist the control, can in time discover harm, improves monitoring efficiency.
The artificial intelligent port and pier monitoring method of the invention comprises the steps of firstly, acquiring a pier oil depot monitoring video through a high-definition camera, preprocessing the pier oil depot monitoring video to reduce the influence of illumination and background, extracting a foreground target area in the preprocessed video, preprocessing the foreground target area to reduce interference to obtain a dangerous behavior image, extracting dangerous characteristics in the dangerous behavior image to facilitate later-stage identification and classification, inputting a prefabricated dangerous characteristic sample into a classifier, inputting the actually extracted dangerous characteristics into the classifier to identify and classify dangerous behaviors to obtain a dangerous behavior conclusion, uploading the dangerous behavior conclusion to a manager to warn the manager, so that the manager can prevent dangerous behaviors in time and ensure safety, and simultaneously monitoring, identifying and reminding by adopting artificial intelligence, the monitoring efficiency is improved.
While the invention has been described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (6)
1. An artificial intelligence port and wharf monitoring method is characterized by comprising the following steps:
acquiring a wharf oil depot monitoring video, and preprocessing the wharf oil depot monitoring video to obtain a preprocessed video;
extracting a foreground target area of the preprocessed video, and preprocessing the foreground target area to obtain a dangerous behavior image;
analyzing and extracting the dangerous behavior image to obtain dangerous characteristics;
and inputting the pre-obtained dangerous feature samples into a classifier, inputting the dangerous features into the classifier, completing the identification and classification of dangerous behaviors, and transmitting a dangerous behavior conclusion to a manager.
2. The artificial intelligence port terminal monitoring method of claim 1, wherein a terminal oil depot monitoring video is obtained and preprocessed to obtain a preprocessed video, the method further comprising:
and converting the image sequence of the wharf oil depot monitoring video into gray scale by adopting a YUV space color model to obtain the preprocessed video.
3. The artificial intelligence port and pier monitoring method of claim 2, wherein a foreground target area is extracted from the preprocessed video and preprocessed to obtain a dangerous behavior image, and the method further comprises:
and establishing a background model based on a ViBe algorithm, separating a foreground target area in the preprocessed video, and extracting a suspected dangerous behavior area by combining a background subtraction method to obtain an image of the suspected dangerous behavior area.
4. The artificial intelligence port and pier monitoring method of claim 3, wherein a foreground target area is extracted from the preprocessed video and preprocessed to obtain a dangerous behavior image, and the method further comprises:
and carrying out image denoising and morphological processing on the suspected dangerous behavior area image to obtain the dangerous behavior image.
5. The artificial intelligence port terminal monitoring method of claim 4, wherein the dangerous behavior image is analyzed and extracted to obtain dangerous characteristics, the method further comprising:
and extracting the HOG characteristic and the LBP texture characteristic of the dangerous behavior image, and fusing the HOG characteristic and the LBP texture characteristic by using a serial fusion algorithm to obtain a dangerous characteristic.
6. The artificial intelligence port terminal monitoring method of claim 1, wherein the dangerous feature samples obtained in advance are input into a classifier, and the dangerous features are input into the classifier, so as to complete the identification and classification of dangerous behaviors and transmit the dangerous behavior conclusion to a manager, and the method further comprises:
and selecting a support vector machine as a classifier for dangerous behavior recognition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110543771.5A CN113378648A (en) | 2021-05-19 | 2021-05-19 | Artificial intelligence port and wharf monitoring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110543771.5A CN113378648A (en) | 2021-05-19 | 2021-05-19 | Artificial intelligence port and wharf monitoring method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113378648A true CN113378648A (en) | 2021-09-10 |
Family
ID=77571320
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110543771.5A Pending CN113378648A (en) | 2021-05-19 | 2021-05-19 | Artificial intelligence port and wharf monitoring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113378648A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113807227A (en) * | 2021-09-11 | 2021-12-17 | 浙江浙能嘉华发电有限公司 | Safety monitoring method, device and equipment based on image recognition and storage medium |
| CN116681699A (en) * | 2023-07-31 | 2023-09-01 | 国网浙江省电力有限公司宁波供电公司 | Intelligent storage method and device for transformer substation oil samples |
| CN117474337A (en) * | 2023-11-08 | 2024-01-30 | 上海海勃物流软件有限公司 | Port hazard source detection method and system based on big data |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106096523A (en) * | 2016-06-02 | 2016-11-09 | 王玉德 | The detection of a kind of Moving Object in Video Sequences and Deviant Behavior parser |
| US20180268222A1 (en) * | 2017-03-17 | 2018-09-20 | Nec Laboratories America, Inc. | Action recognition system for action recognition in unlabeled videos with domain adversarial learning and knowledge distillation |
| CN108647582A (en) * | 2018-04-19 | 2018-10-12 | 河南科技学院 | Goal behavior identification and prediction technique under a kind of complex dynamic environment |
| CN109033954A (en) * | 2018-06-15 | 2018-12-18 | 西安科技大学 | A kind of aerial hand-written discrimination system and method based on machine vision |
| CN109472233A (en) * | 2018-11-01 | 2019-03-15 | 济南创视睿智能科技有限公司 | A kind of behaviortrace system |
| CN109935042A (en) * | 2019-03-07 | 2019-06-25 | 大连大学 | A kind of harbour dangerous material intelligent monitoring early warning system |
| CN111464779A (en) * | 2020-03-12 | 2020-07-28 | 天津港远航矿石码头有限公司 | Camera system for intelligent visual identification of open large scene |
-
2021
- 2021-05-19 CN CN202110543771.5A patent/CN113378648A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106096523A (en) * | 2016-06-02 | 2016-11-09 | 王玉德 | The detection of a kind of Moving Object in Video Sequences and Deviant Behavior parser |
| US20180268222A1 (en) * | 2017-03-17 | 2018-09-20 | Nec Laboratories America, Inc. | Action recognition system for action recognition in unlabeled videos with domain adversarial learning and knowledge distillation |
| CN108647582A (en) * | 2018-04-19 | 2018-10-12 | 河南科技学院 | Goal behavior identification and prediction technique under a kind of complex dynamic environment |
| CN109033954A (en) * | 2018-06-15 | 2018-12-18 | 西安科技大学 | A kind of aerial hand-written discrimination system and method based on machine vision |
| CN109472233A (en) * | 2018-11-01 | 2019-03-15 | 济南创视睿智能科技有限公司 | A kind of behaviortrace system |
| CN109935042A (en) * | 2019-03-07 | 2019-06-25 | 大连大学 | A kind of harbour dangerous material intelligent monitoring early warning system |
| CN111464779A (en) * | 2020-03-12 | 2020-07-28 | 天津港远航矿石码头有限公司 | Camera system for intelligent visual identification of open large scene |
Non-Patent Citations (2)
| Title |
|---|
| CHEN Z等: "Dangerous driving behavior detection using video-extracted vehicle trajectory histograms", 《JOURNAL OF INTELLIGENT TRANSPORTATION SYSTEMS》, vol. 21, no. 5, pages 409 - 421 * |
| 李淑娟: "船舶机舱危险行为智能视觉监控***", 《舰船科学技术》, no. 12, pages 181 - 183 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113807227A (en) * | 2021-09-11 | 2021-12-17 | 浙江浙能嘉华发电有限公司 | Safety monitoring method, device and equipment based on image recognition and storage medium |
| CN113807227B (en) * | 2021-09-11 | 2023-07-25 | 浙江浙能嘉华发电有限公司 | Safety monitoring method, device, equipment and storage medium based on image recognition |
| CN116681699A (en) * | 2023-07-31 | 2023-09-01 | 国网浙江省电力有限公司宁波供电公司 | Intelligent storage method and device for transformer substation oil samples |
| CN116681699B (en) * | 2023-07-31 | 2023-12-15 | 国网浙江省电力有限公司宁波供电公司 | Intelligent storage method and device for transformer substation oil samples |
| CN117474337A (en) * | 2023-11-08 | 2024-01-30 | 上海海勃物流软件有限公司 | Port hazard source detection method and system based on big data |
| CN117474337B (en) * | 2023-11-08 | 2024-06-18 | 上海海勃物流软件有限公司 | Port hazard source detection method and system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113378648A (en) | Artificial intelligence port and wharf monitoring method | |
| US10127448B2 (en) | Method and system for dismount detection in low-resolution UAV imagery | |
| US9911055B2 (en) | Method and system for detection and classification of license plates | |
| EP3899508A1 (en) | Automated inspection system and associated method for assessing the condition of shipping containers | |
| CN102982313B (en) | The method of Smoke Detection | |
| CN103839085B (en) | A kind of detection method of compartment exception crowd density | |
| CN113962274B (en) | Abnormity identification method and device, electronic equipment and storage medium | |
| CN110751079A (en) | Article detection method, apparatus, system and computer readable storage medium | |
| Ahmad et al. | Overhead view person detection using YOLO | |
| US11495022B2 (en) | Method for recognizing an object of a mobile unit | |
| CN112307840A (en) | Indicator light detection method, device, equipment and computer readable storage medium | |
| Indrabayu et al. | Blob modification in counting vehicles using gaussian mixture models under heavy traffic | |
| Hidayatullah et al. | Automatic sperms counting using adaptive local threshold and ellipse detection | |
| KR101690050B1 (en) | Intelligent video security system | |
| CN117809154A (en) | Neural network model training method, flaw detection method of product and related devices | |
| US20200394802A1 (en) | Real-time object detection method for multiple camera images using frame segmentation and intelligent detection pool | |
| CN112866654A (en) | Intelligent video monitoring system | |
| CN111402185B (en) | Image detection method and device | |
| CN115359306B (en) | Intelligent identification method and system for high-definition images of railway freight inspection | |
| Wang et al. | An efficient method of shadow elimination based on image region information in HSV color space | |
| Noor et al. | Automatic parking slot occupancy detection using Laplacian operator and morphological kernel dilation | |
| Kim et al. | Abnormal object detection using feedforward model and sequential filters | |
| Rao et al. | Convolutional Neural Network Model for Traffic Sign Recognition | |
| Valentin et al. | Weld classification using gray level co-occurrence matrix and local binary patterns | |
| CN115713758B (en) | Carriage identification method, system, device and storage medium |
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 |