CN113641852A - Unmanned aerial vehicle photoelectric video target retrieval method, electronic device and medium - Google Patents
Unmanned aerial vehicle photoelectric video target retrieval method, electronic device and medium Download PDFInfo
- Publication number
- CN113641852A CN113641852A CN202110800077.7A CN202110800077A CN113641852A CN 113641852 A CN113641852 A CN 113641852A CN 202110800077 A CN202110800077 A CN 202110800077A CN 113641852 A CN113641852 A CN 113641852A
- Authority
- CN
- China
- Prior art keywords
- target
- video
- unmanned aerial
- photoelectric
- aerial vehicle
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/71—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/75—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/787—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The application discloses a retrieval method, electronic equipment and medium for photoelectric video targets of unmanned aerial vehicles. The method can comprise the following steps: receiving photoelectric video data of the unmanned aerial vehicle and corresponding position data; classifying the targets through a target identification algorithm, and performing data structured storage according to the category and position data of the photoelectric video data; generating a regional density map of the specified target category; and selecting a target area in the area density map, and retrieving photoelectric video data of the target area. The invention provides a target area density map for searching personnel based on receiving photoelectric image data and target position data of the unmanned aerial vehicle, and carries out detailed time axis searching with target category information on a source video section, and finally successfully searches an interested target and obtains related space-time context information.
Description
Technical Field
The invention relates to the technical field of target retrieval, in particular to a method, electronic equipment and medium for retrieving an unmanned aerial vehicle photoelectric video target.
Background
In recent years, as the unmanned aerial vehicle system technology matures, unmanned aerial vehicles have been widely used. Airborne photoelectricity is the main means for unmanned aerial vehicle to detect the target, and the generated photoelectric video has the characteristics of complex dynamic background, large visual angle change, large content change, multiple target types and the like, and various use strategies and algorithms are generated for effectively utilizing the photoelectric video data generated by the airborne photoelectricity of the unmanned aerial vehicle.
The existing mainstream unmanned aerial vehicle video target retrieval method is mainly based on electronic equipment and media for target classification storage, and video target classification retrieval is carried out on labels obtained by a target classification algorithm.
Therefore, it is necessary to develop a method, an electronic device and a medium for retrieving an optoelectronic video object of an unmanned aerial vehicle.
The information disclosed in this background section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.
Disclosure of Invention
The invention provides a retrieval method, electronic equipment and a medium for an unmanned aerial vehicle photoelectric video target, which can provide a target area density map for a retrieval personnel based on receiving photoelectric image data and target position data of an unmanned aerial vehicle, perform detailed time axis search with target category information on a source video section, and finally successfully retrieve an interested target and acquire related space-time context information.
In a first aspect, an embodiment of the present disclosure provides a method for retrieving an optoelectronic video target of an unmanned aerial vehicle, including:
receiving photoelectric video data of the unmanned aerial vehicle and corresponding position data;
classifying the targets through a target identification algorithm, and performing data structured storage according to the category and the position data of the photoelectric video data;
generating a regional density map of the specified target category;
and selecting a target area in the area density map, and retrieving photoelectric video data of the target area.
Preferably, the method further comprises the following steps:
and the photoelectric video data of the target area is played in a time axis mode with a target class label.
Preferably, the method further comprises the following steps:
and selecting the time point of the target category on the time axis, and determining whether the target category is the required target category.
Preferably, the target recognition algorithm is a target recognition algorithm based on a priori sample deep learning.
Preferably, the optoelectronic video data is stored in an association structure according to the structural composition of video paragraph-video image frame number-object class-object position.
Preferably, the regional density map divides the density gradient by the number of objects in a region per square kilometer that comprise a specified class of objects.
Preferably, the corresponding video segments in the target area are screened into a video segment list through the position data.
As a specific implementation of the embodiments of the present disclosure,
in a second aspect, an embodiment of the present disclosure further provides an electronic device, including:
a memory storing executable instructions;
a processor executing the executable instructions in the memory to implement the steps of:
receiving photoelectric video data of the unmanned aerial vehicle and corresponding position data;
classifying the targets through a target identification algorithm, and performing data structured storage according to the category and the position data of the photoelectric video data;
generating a regional density map of the specified target category;
and selecting a target area in the area density map, and retrieving photoelectric video data of the target area.
Preferably, the method further comprises the following steps:
and the photoelectric video data of the target area is played in a time axis mode with a target class label.
Preferably, the method further comprises the following steps:
and selecting the time point of the target category on the time axis, and determining whether the target category is the required target category.
Preferably, the target recognition algorithm is a target recognition algorithm based on a priori sample deep learning.
Preferably, the optoelectronic video data is stored in an association structure according to the structural composition of video paragraph-video image frame number-object class-object position.
Preferably, the regional density map divides the density gradient by the number of objects in a region per square kilometer that comprise a specified class of objects.
Preferably, the corresponding video segments in the target area are screened into a video segment list through the position data.
In a third aspect, the disclosed embodiment also provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the retrieval method for the unmanned aerial vehicle photoelectric video target is implemented.
The method and apparatus of the present invention have other features and advantages which will be apparent from or are set forth in detail in the accompanying drawings and the following detailed description, which are incorporated herein, and which together serve to explain certain principles of the invention.
Drawings
The above and other objects, features and advantages of the present invention will become more apparent by describing in more detail exemplary embodiments thereof with reference to the attached drawings, in which like reference numerals generally represent like parts.
Fig. 1 shows a flow chart of the steps of a method for retrieving a photo-electric video target of a drone according to one embodiment of the invention.
FIG. 2 illustrates a schematic diagram of a target tag selection interface, according to one embodiment of the invention.
FIG. 3 shows a schematic diagram of a target area density setting interface according to one embodiment of the invention.
Fig. 4 shows a schematic diagram of a region-corresponding source video segment list according to an embodiment of the present invention.
FIG. 5 shows a schematic diagram of a timeline with target tags according to one embodiment of the present invention.
Detailed Description
Preferred embodiments of the present invention will be described in more detail below. While the following describes preferred embodiments of the present invention, it should be understood that the present invention may be embodied in various forms and should not be limited by the embodiments set forth herein.
The invention provides a method for searching a photoelectric video target of an unmanned aerial vehicle, which comprises the following steps:
receiving photoelectric video data of the unmanned aerial vehicle and corresponding position data;
classifying the targets through a target identification algorithm, and performing data structured storage according to the category and position data of the photoelectric video data;
generating a regional density map of the specified target category;
and selecting a target area in the area density map, and retrieving photoelectric video data of the target area.
In one example, further comprising:
and the photoelectric video data of the target area is played in a time axis mode with a target class label.
In one example, further comprising:
the time point when the desired object class exists is selected on the time axis, and whether the object class is the desired object class is determined.
In one example, the target recognition algorithm is a target recognition algorithm by a priori sample based deep learning.
In one example, the optoelectronic video data is stored in an associative structure according to the structural composition of video paragraph-video image frame number-object class-object position.
In one example, the regional density map divides the density gradient by the number of targets in the region per square kilometer that contain the specified target class.
In one example, the corresponding video segments in the target area are filtered into a video segment list by the location data.
Specifically, the invention provides a method for retrieving a photoelectric video target of an unmanned aerial vehicle, which comprises the following steps:
when receiving unmanned aerial vehicle data, receiving position data of a corresponding target in photoelectric video data and photoelectric video data of the unmanned aerial vehicle;
classifying the targets through a target identification algorithm, and storing the category and the position information of the same frame of target as a structured label of the target according to the category and the position data of the photoelectric video data, namely performing relevance structured storage on the photoelectric video data according to the structural composition of a video paragraph, a video image frame number, a target category and a target position, wherein the target identification algorithm is a target identification algorithm based on prior sample deep learning;
when a searcher searches, after determining the interested target category, the database automatically filters the target category label, and draws the associated target position information into a target area density map which is superposed in a digital map, wherein the density gradient is divided by the target number of the appointed target category contained in each square kilometer in the area;
searching personnel selects a target area in the area density map by observing the area density map, and searches photoelectric video data of the target area according to the matching of the selected target area and the information of the target position in the database; photoelectric video data of the target area is played in a time axis mode with a target category label; the time point when the desired object class exists is selected on the time axis, and whether the object class is the desired object class is determined.
The method comprises the steps that corresponding video sections in a target area are screened into a video section list through position data, the screened video sections are selected to be played, whether specific category targets contained in a time point exist or not is displayed through a playing time axis, the interested targets needed by a searching person can be accurately obtained through checking the same category targets on the time axis, and the interested targets exist in continuous video sections, so that motion related information of the interested targets is complete, the searching person can further process space-time context information of the interested targets according to task requirements, and more three-dimensional interested target information is obtained.
The present invention also provides an electronic device, comprising: a memory storing executable instructions; a processor executing executable instructions in the memory to implement the steps of:
receiving photoelectric video data of the unmanned aerial vehicle and corresponding position data;
classifying the targets through a target identification algorithm, and performing data structured storage according to the category and position data of the photoelectric video data;
generating a regional density map of the specified target category;
and selecting a target area in the area density map, and retrieving photoelectric video data of the target area.
In one example, further comprising:
and the photoelectric video data of the target area is played in a time axis mode with a target class label.
In one example, further comprising:
the time point when the desired object class exists is selected on the time axis, and whether the object class is the desired object class is determined.
In one example, the target recognition algorithm is a target recognition algorithm by a priori sample based deep learning.
In one example, the optoelectronic video data is stored in an associative structure according to the structural composition of video paragraph-video image frame number-object class-object position.
In one example, the regional density map divides the density gradient by the number of targets in the region per square kilometer that contain the specified target class.
In one example, the corresponding video segments in the target area are filtered into a video segment list by the location data.
The invention also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the searching method of the photoelectric video target of the unmanned aerial vehicle.
To facilitate understanding of the solution of the embodiments of the present invention and the effects thereof, three specific application examples are given below. It will be understood by those skilled in the art that this example is merely for the purpose of facilitating an understanding of the present invention and that any specific details thereof are not intended to limit the invention in any way.
Example 1
Fig. 1 shows a flow chart of the steps of a method for retrieving a photo-electric video target of a drone according to one embodiment of the invention.
As shown in fig. 1, the method for retrieving the photoelectric video target of the unmanned aerial vehicle comprises the following steps: step 101, receiving photoelectric video data of an unmanned aerial vehicle and corresponding position data; step 102, classifying the targets through a target identification algorithm, and performing data structured storage according to the category and position data of the photoelectric video data; step 103, generating a region density map of the specified target category; and 104, selecting a target area in the area density map, and searching photoelectric video data of the target area.
Firstly, receiving the photoelectric video data of the unmanned aerial vehicle and the position data of the corresponding target in the photoelectric video data simultaneously.
And for the photoelectric video image, selecting a target recognition algorithm of a deep learning neural network to perform target recognition on the received photoelectric video data, and classifying the targets on the basis of a machine learning result of a prior data set sample. Specifically, in the embodiment, a ShuffleNet neural network architecture is adopted for target identification and prior data set sample learning, so that the deep learning efficiency is improved; in the target learning stage, a priori data set sample with the network data set and the actual photoelectric data collection quantity of the unmanned aerial vehicle being 1:1 is adopted, the target category is set as the main target of four unmanned aerial vehicles, namely people, automobiles, buildings and armed vehicles, and the priori data set sample learning is carried out; when unmanned aerial vehicle target recognition is considered, the scale of a target in a video image is small, in order to improve the recognition rate of multi-scale small targets, a target recognition algorithm of a UNET structure is adopted for target recognition, if one or more of four types of targets including people, automobiles, buildings and armed vehicles exist in a current video image frame, relevance structural storage is carried out on videos and target accessory information thereof, the videos and the target accessory information are stored together with the current video image to form a database in the form of video paragraph-video image frame number-target type, and each video paragraph lasts for 10 minutes.
And for the position data of the corresponding target in the photoelectric video data, performing relevance structured storage on the video and the target position information thereof during receiving to obtain a database in the form of video paragraph-video image frame number-target category-target position.
And generating a region density map of the specific class of the target through the class and the position data of the target.
FIG. 2 illustrates a schematic diagram of a target tag selection interface, according to one embodiment of the invention.
FIG. 3 shows a schematic diagram of a target area density setting interface according to one embodiment of the invention.
On the basis of a structured database, a searcher selects a certain interested target from four targets of people, automobiles, buildings and armed vehicles, as shown in fig. 2, sets the number of density gradient lines and the corresponding target density (the number of targets per square kilometer) of each gradient line area in a density map setting tab, as shown in fig. 3, and finally generates a target area density map on a digital map.
And selecting the interested area in the area density map, and automatically screening the video paragraph corresponding to the interested area in the database.
Fig. 4 shows a schematic diagram of a region-corresponding source video segment list according to an embodiment of the present invention.
An interested target area is selected in the target area density map, as shown in fig. 4, in this embodiment, the target area is a rectangular frame, after the position and size of the rectangular frame are set by a searcher, a corresponding video paragraph list is refreshed in the area video source tab, the maximum value of the number of video paragraphs is set to be 15, and the video paragraphs which have the largest number of associated target positions and meet at least one corresponding target are selected by screening.
The video passage is played by means of a time axis with a target list label.
FIG. 5 shows a schematic diagram of a timeline with target tags according to one embodiment of the present invention.
The search person selects the video segment in the video source tab of the area for detailed examination, and after the video segment is opened, the existence condition of the object class of the current image frame is displayed on the time axis, as shown in fig. 5, the light gray part on the time axis represents the existence of the object of the class of 'people'.
A time point of a desired category object is selected on a time axis, and whether the object is a desired object is checked.
The searching personnel drag the time axis to search the interested target at different time points, and the interested areas are selected in the previous steps, so that the target areas in the video are basically the interested areas when the time axis is dragged, and the searching personnel can search the interested target more conveniently and pertinently. After the interested target is determined, the source video section where the interested target is located can provide continuous time-space context information, and extraction of environment information associated with the interested target or other associated target information is very convenient.
By applying the retrieval method of the photoelectric video target of the unmanned aerial vehicle, the retrieval time of a retrieval person on the interested target in the designated area is shortened by 3 to 4 times in the actual retrieval process, and the acquisition efficiency of the associated information of the interested target in the designated area is improved by more than 2 times.
Example 2
The present disclosure provides an electronic device including: a memory storing executable instructions; and the processor runs the executable instructions in the memory to realize the retrieval method of the photoelectric video target of the unmanned aerial vehicle.
An electronic device according to an embodiment of the present disclosure includes a memory and a processor.
The memory is to store non-transitory computer readable instructions. In particular, the memory may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, Random Access Memory (RAM), cache memory (cache), and/or the like. The non-volatile memory may include, for example, Read Only Memory (ROM), hard disk, flash memory, etc.
The processor may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device to perform desired functions. In one embodiment of the disclosure, the processor is configured to execute the computer readable instructions stored in the memory.
Those skilled in the art should understand that, in order to solve the technical problem of how to obtain a good user experience, the present embodiment may also include well-known structures such as a communication bus, an interface, and the like, and these well-known structures should also be included in the protection scope of the present disclosure.
For the detailed description of the present embodiment, reference may be made to the corresponding descriptions in the foregoing embodiments, which are not repeated herein.
Example 3
The embodiment of the disclosure provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program realizes the retrieval method of the unmanned aerial vehicle photoelectric video target.
A computer-readable storage medium according to an embodiment of the present disclosure has non-transitory computer-readable instructions stored thereon. The non-transitory computer readable instructions, when executed by a processor, perform all or a portion of the steps of the methods of the embodiments of the disclosure previously described.
The computer-readable storage media include, but are not limited to: optical storage media (e.g., CD-ROMs and DVDs), magneto-optical storage media (e.g., MOs), magnetic storage media (e.g., magnetic tapes or removable disks), media with built-in rewritable non-volatile memory (e.g., memory cards), and media with built-in ROMs (e.g., ROM cartridges).
It will be appreciated by persons skilled in the art that the above description of embodiments of the invention is intended only to illustrate the benefits of embodiments of the invention and is not intended to limit embodiments of the invention to any examples given.
Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments.
Claims (10)
1. The method for retrieving the photoelectric video target of the unmanned aerial vehicle is characterized by comprising the following steps:
receiving photoelectric video data of the unmanned aerial vehicle and corresponding position data;
classifying the targets through a target identification algorithm, and performing data structured storage according to the category and the position data of the photoelectric video data;
generating a regional density map of the specified target category;
and selecting a target area in the area density map, and retrieving photoelectric video data of the target area.
2. The method for retrieving the optoelectronic video target of the unmanned aerial vehicle as claimed in claim 1, further comprising:
and the photoelectric video data of the target area is played in a time axis mode with a target class label.
3. The unmanned aerial vehicle photoelectric video target retrieval method of claim 2, further comprising:
and selecting the time point of the target category on the time axis, and determining whether the target category is the required target category.
4. The unmanned aerial vehicle photoelectric video target retrieval method of claim 1, wherein the target recognition algorithm is a target recognition algorithm through a priori sample deep learning based.
5. The unmanned aerial vehicle photoelectric video target retrieval method of claim 1, wherein the photoelectric video data is stored in an association structure according to a structural composition of video paragraph-video image frame number-target class-target position.
6. The method of claim 1, wherein the area density map divides density gradients by the number of objects in an area per square kilometer that comprise a specified class of objects.
7. The method for retrieving the optoelectronic video target of the unmanned aerial vehicle as claimed in claim 1, wherein the corresponding video segment in the target area is screened into a video segment list through position data.
8. An electronic device, characterized in that the electronic device comprises:
a memory storing executable instructions;
a processor executing the executable instructions in the memory to implement the steps of:
receiving photoelectric video data of the unmanned aerial vehicle and corresponding position data;
classifying the targets through a target identification algorithm, and performing data structured storage according to the category and the position data of the photoelectric video data;
generating a regional density map of the specified target category;
and selecting a target area in the area density map, and retrieving photoelectric video data of the target area.
9. The electronic device of claim 8, further comprising:
the photoelectric video data of the target area is played in a time axis mode with a target category label;
and selecting the time point of the target category on the time axis, and determining whether the target category is the required target category.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program, which when executed by a processor implements the method for retrieving an optoelectronic video object of a drone according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110800077.7A CN113641852A (en) | 2021-07-13 | 2021-07-13 | Unmanned aerial vehicle photoelectric video target retrieval method, electronic device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110800077.7A CN113641852A (en) | 2021-07-13 | 2021-07-13 | Unmanned aerial vehicle photoelectric video target retrieval method, electronic device and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113641852A true CN113641852A (en) | 2021-11-12 |
Family
ID=78417346
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110800077.7A Pending CN113641852A (en) | 2021-07-13 | 2021-07-13 | Unmanned aerial vehicle photoelectric video target retrieval method, electronic device and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113641852A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106354816A (en) * | 2016-08-30 | 2017-01-25 | 东软集团股份有限公司 | Video image processing method and video image processing device |
| CN106910229A (en) * | 2015-12-23 | 2017-06-30 | 韩华泰科株式会社 | Image processing equipment and method |
| CN110390031A (en) * | 2019-06-28 | 2019-10-29 | 深圳市商汤科技有限公司 | Information processing method and device, vision facilities and storage medium |
| CN111581433A (en) * | 2020-05-18 | 2020-08-25 | Oppo广东移动通信有限公司 | Video processing method and device, electronic equipment and computer readable medium |
-
2021
- 2021-07-13 CN CN202110800077.7A patent/CN113641852A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106910229A (en) * | 2015-12-23 | 2017-06-30 | 韩华泰科株式会社 | Image processing equipment and method |
| CN106354816A (en) * | 2016-08-30 | 2017-01-25 | 东软集团股份有限公司 | Video image processing method and video image processing device |
| CN110390031A (en) * | 2019-06-28 | 2019-10-29 | 深圳市商汤科技有限公司 | Information processing method and device, vision facilities and storage medium |
| CN111581433A (en) * | 2020-05-18 | 2020-08-25 | Oppo广东移动通信有限公司 | Video processing method and device, electronic equipment and computer readable medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112016464B (en) | Method and device for detecting face shielding, electronic equipment and storage medium | |
| CN101689394B (en) | Method and system for video indexing and video synopsis | |
| CN105144239B (en) | Image processing apparatus, image processing method | |
| CN106446150B (en) | A kind of method and device of vehicle precise search | |
| CN110209866A (en) | A kind of image search method, device, equipment and computer readable storage medium | |
| US20140365506A1 (en) | Video searching | |
| CN107358596A (en) | A kind of car damage identification method based on image, device, electronic equipment and system | |
| CN102831239B (en) | A kind of method and system building image data base | |
| CN107808126A (en) | Vehicle retrieval method and device | |
| US11403766B2 (en) | Method and device for labeling point of interest | |
| US8254678B2 (en) | Image segmentation | |
| US11062455B2 (en) | Data filtering of image stacks and video streams | |
| CN111581423A (en) | Target retrieval method and device | |
| CN104615986A (en) | Method for utilizing multiple detectors to conduct pedestrian detection on video images of scene change | |
| Zhang et al. | A hybrid framework for single tree detection from airborne laser scanning data: A case study in temperate mature coniferous forests in Ontario, Canada | |
| US10275656B2 (en) | Large scale video search using queries that define relationships between objects | |
| CN110750311A (en) | Data classification method, device and equipment | |
| CN115100469A (en) | Target attribute identification method, training method and device based on segmentation algorithm | |
| Delleji et al. | Deep Learning-based approach for detection and classification of Micro/Mini drones | |
| Pino et al. | Semantic segmentation of radio-astronomical images | |
| CN109934147B (en) | Target detection method, system and device based on deep neural network | |
| CN113641852A (en) | Unmanned aerial vehicle photoelectric video target retrieval method, electronic device and medium | |
| Nugroho et al. | Comparison of deep learning-based object classification methods for detecting tomato ripeness | |
| CN110287203B (en) | Updating method and updating device for vending machine and vending machine | |
| CN111723719B (en) | Video target detection method, system and device based on category external memory |
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 |