CN113095135A - System, method, device and medium for beyond-the-horizon target detection based on GAN - Google Patents
System, method, device and medium for beyond-the-horizon target detection based on GAN Download PDFInfo
- Publication number
- CN113095135A CN113095135A CN202110252788.5A CN202110252788A CN113095135A CN 113095135 A CN113095135 A CN 113095135A CN 202110252788 A CN202110252788 A CN 202110252788A CN 113095135 A CN113095135 A CN 113095135A
- Authority
- CN
- China
- Prior art keywords
- target
- gan
- data communication
- algorithm
- road
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title abstract description 24
- 238000012545 processing Methods 0.000 claims abstract description 11
- 230000000007 visual effect Effects 0.000 claims abstract description 10
- 238000004891 communication Methods 0.000 claims description 40
- 230000003993 interaction Effects 0.000 claims description 5
- 230000007246 mechanism Effects 0.000 claims description 4
- 230000008447 perception Effects 0.000 abstract description 6
- 206010039203 Road traffic accident Diseases 0.000 abstract description 4
- 230000004044 response Effects 0.000 abstract description 3
- 238000004590 computer program Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a beyond visual range target detection system, a method, a computer device and a storage medium based on GAN, wherein the detection system comprises a machine vision module for continuously acquiring a target image from a road in a preset range in real time, a main control module for operating a GAN algorithm to carry out resolution enhancement processing on the target image, an identification module for operating a YOLOv5 target detection algorithm and identifying a traffic element target from the target image processed by the main control module. The invention can improve the accuracy of the identification and detection of the long-distance road target, enhance the beyond-the-horizon perception capability of the vehicle, better sense the long-distance small target, better predict the traffic condition of the road ahead and make a response measure in advance, thereby reducing the incidence of traffic accidents and ensuring the traffic safety. The invention is widely applied to the technical field of image processing.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a beyond visual range target detection system and method based on GAN, a computer device and a storage medium.
Background
At present, an unmanned vehicle is used as a novel intelligent vehicle, senses road condition information through an intelligent sensing system, and carries out autonomous planning decision by a computer system to complete a preset driving target. The road perception technology is a prerequisite for planning and decision making, is a key core part of a vehicle-road cooperation technology, has a good effect of perceiving and detecting targets at medium and short distances at present, but has low detection accuracy rate on small targets or fuzzy targets, and is difficult to meet industrial requirements.
The remote distance sensing technology can be used for accurately identifying the driving information of the remote vehicles, timely providing information of the remote vehicles and characteristics of environmental road conditions for drivers, reducing the occurrence of traffic accidents, improving the road passing efficiency and promoting the development of smart cities.
In reality, because traffic road condition information is complex and changeable, uncertainty factors and emergency situations are more, and beyond-the-horizon sensing of a long-distance target becomes one of key factors of safe driving of a vehicle.
Disclosure of Invention
In view of at least one of the above technical problems, it is an object of the present invention to provide a system, a method, a computer apparatus and a storage medium for detecting a beyond-the-horizon target based on GAN.
In one aspect, an embodiment of the present invention includes a method for over-the-horizon target detection based on GAN, including:
the machine vision module is used for continuously acquiring a target image from a road in a preset range in real time;
the main control module is used for operating a GAN algorithm to perform resolution enhancement processing on the target image;
and the identification module is used for running a YOLOv5 target detection algorithm to identify the traffic element target from the target image processed by the main control module.
Further, the GAN algorithm is an SRGAN algorithm that is improved by using context information and attention mechanism.
Further, the generation countermeasure network used by the GAN algorithm is trained through a small target data set TT 100K.
Further, the machine vision module includes:
the human-computer interaction unit is used for inputting refined settings; the refined setting comprises parameter updating setting, acquisition frequency setting and visual angle setting of the machine vision module;
and the image acquisition unit is used for continuously acquiring a target image from a road in a preset range in real time according to the input fine setting.
Further, the image acquisition unit is a high-definition camera.
Further, the system for detecting beyond visual range targets based on GAN further comprises:
and the communication module is used for establishing data communication between functional components in the vehicles and between the vehicles, and sharing the traffic element target identified by the identification module through the data communication.
Further, the communication module includes:
the wireless data communication units are arranged in a road area and are connected with vehicle-mounted terminals of vehicles to form a secondary data communication service network; the secondary data communication service network is used for establishing data communication among the vehicle internal functional components so as to share the traffic element target among the vehicle internal functional components;
the relay server is used for being connected with the main control module and each wireless data communication unit to form a primary data communication service network; the primary data communication service network is used for establishing data communication between vehicles so as to share the traffic element target between the vehicles.
On the other hand, the embodiment of the invention also comprises a beyond visual range target detection method based on GAN, which comprises the following steps:
continuously acquiring a target image from a road in a preset range in real time;
executing a GAN algorithm to perform resolution enhancement processing on the target image;
running a Yolov5 target detection algorithm, a traffic element target is identified from the target image processed by the host module.
In another aspect, an embodiment of the present invention further includes a computer apparatus, including a memory and a processor, where the memory is configured to store at least one program, and the processor is configured to load the at least one program to perform the GAN-based over-the-horizon object detection method in the embodiment.
In another aspect, the present invention further includes a storage medium in which a processor-executable program is stored, the processor-executable program being configured to execute the GAN-based over-the-horizon object detection method in the embodiment when executed by a processor.
The invention has the beneficial effects that: the beyond-the-horizon target detection system based on the GAN in the embodiment can improve the accuracy of long-distance road target identification and detection, enhance the beyond-the-horizon perception capability of vehicles, better sense long-distance small targets, better predict the traffic condition of the road ahead and make response measures in advance, thereby reducing the incidence of traffic accidents and ensuring the traffic safety.
Drawings
FIG. 1 is a block diagram of an embodiment of a GAN-based beyond-the-horizon object detection system;
FIG. 2 is a block diagram of a generation network used in the embodiment;
FIG. 3 is a block diagram of a discrimination network used in the embodiment;
FIG. 4 is a schematic diagram of the YOLOv5 target detection algorithm used in the examples;
FIG. 5 is a schematic diagram of an application scenario of the system for performing GAN-based beyond-the-horizon object detection in the embodiment;
FIG. 6 is a flowchart of a method for beyond-the-horizon object detection based on GAN in an embodiment.
Detailed Description
In this embodiment, referring to fig. 1, a system for detecting over-the-horizon targets based on GAN includes:
the machine vision module 1 is used for continuously acquiring a target image from a road in a preset range in real time;
the main control module 4 is used for operating a GAN algorithm to perform resolution enhancement processing on the target image;
the recognition module 6 is used for running a Yolov5 target detection algorithm and recognizing a traffic element target from the target image processed by the main control module;
and the communication module 8 is used for establishing data communication between functional components in the vehicles and between the vehicles and sharing the traffic element target identified by the identification module through the data communication.
Referring to fig. 1, a machine vision module 1 includes a human-machine interaction unit 3 and an image acquisition unit 2, and in particular, a high-definition camera may be used as the image acquisition unit. The human-computer interaction unit is used for generating and displaying a human-computer interaction interface so that an operator can input refined settings such as parameter updating setting, acquisition frequency setting and visual angle setting of the machine vision module, the refined settings are used for setting the image acquisition unit, and the image acquisition unit continuously acquires a target image from a road in a preset range in real time according to the refined settings.
The machine vision module can acquire a target image in a mode of shooting a single picture or shooting a video stream and then capturing frames in the single picture or the video stream, and then sends the target image to the main control module. In this embodiment, the captured target image may include traffic element targets such as pedestrians, vehicles, traffic signs, lane lines, and signal lights, and these traffic element targets may have characteristics of long distances and small targets, for example, the distance of these traffic element targets to the machine vision module exceeds 200m when captured in the target image.
Referring to fig. 1, the main control module 4 is configured to execute a GAN algorithm 5 to perform resolution enhancement processing on a target image. In this embodiment, the GAN algorithm run by the main control module is an SRGAN algorithm improved by using context information and an attention mechanism, and the GAN algorithm uses a generation countermeasure network to process the target image. The structure of the generation network in the generation countermeasure network is shown in fig. 2, and the structure of the discrimination network in the generation countermeasure network is shown in fig. 3. In the embodiment, an improved SRGAN algorithm is adopted, the improvement suitable for small target detection is made on the SRGAN by using context information and an attention mechanism, the features suitable for small target detection are extracted, and the weight more suitable for road small target detection is extracted by using a small target data set TT100K for training, so that the GAN algorithm can realize the amplification of a small target image by 4 times, can improve the texture details of a long-distance small target in the target image, and is beneficial to the subsequent processing by using an identification module.
Referring to fig. 1, the recognition module 6 is configured to run the YOLOv5 target detection algorithm 7 to recognize traffic element targets from the target images processed by the host module. The principle of the operated YOLOv5 target detection method is shown in fig. 4. The identification module adopts a YOLOv5 target detection algorithm, can identify the road distant target in the target image in real time, respectively identify the original image and the image subjected to resolution enhancement by the main control module, identify the type, shape and position information of the distant small target object in the video image, and the identified road distant target is various traffic element targets including but not limited to surrounding pedestrians, vehicles, traffic signs, lane lines, signal lamps and the like.
Referring to fig. 1, the communication module 8 includes a relay server 10 and a plurality of wireless data communication units 9, which are 5G mobile communication network units or communication units using more advanced communication protocols, and can achieve near real-time detection speed. The wireless data communication unit is arranged in a road area and is connected with a vehicle-mounted terminal of a vehicle to form a secondary data communication service network; the relay server is connected with the main control module and each wireless data communication unit to form a primary data communication service network. The secondary data communication service network can establish data communication among the internal functional components of each single vehicle so as to share traffic element targets among the internal functional components of the vehicles, can be used for over-the-horizon perception results of the single vehicles and select the targets with higher confidence; the primary data communication service network is used for establishing data communication between vehicles so as to share traffic element targets between the vehicles, and can share over-the-horizon perception results in workshops, realize cooperative vehicle and road scheduling in areas and promote cooperative vehicle and road development.
The GAN-based over-the-horizon target detection system in the present embodiment may be applied in the scenario as shown in fig. 5. Referring to fig. 5, the vehicle located at the leftmost side is the first vehicle, the distances between the first vehicle and the front vehicle and the pedestrian ahead are both greater than 200m, and in a general environment, the front vehicle and the pedestrian ahead are both out of the sight distance of the driver of the first vehicle, that is, the front vehicle and the pedestrian ahead belong to a small over-sight-distance target relative to the first vehicle, and are not easily observed by the driver of the first vehicle, which is not beneficial to decision making of the driver of the first vehicle. If the vehicle-mounted terminal is mounted on the first vehicle, and the high-definition cameras in the system for detecting the beyond-visual-range targets based on the GAN in the embodiment are arranged around the vehicle body, and the high-definition cameras respectively send the collected road long-distance small target images to the main control module and the recognition module for recognition, the vehicle-mounted terminal can acquire the recognized traffic element targets from the system for detecting the beyond-visual-range targets based on the GAN in the embodiment, so that the condition of the front road is sensed and predicted in advance, and a powerful guarantee is provided for safe driving of the vehicle. Specifically, the vehicle-mounted terminal can display the relative position of the traffic element target through the display screen, so that a driver of the first vehicle can make early warning and decision, road driving safety and driving comfort are improved, sudden braking and other situations are avoided, and the traffic environment is favorably improved.
The beyond-the-horizon target detection system based on the GAN in the embodiment can improve the accuracy of long-distance road target identification and detection, enhance the beyond-the-horizon perception capability of vehicles, better sense long-distance small targets, better predict the traffic condition of the road ahead and make response measures in advance, thereby reducing the incidence of traffic accidents and ensuring traffic safety. The method can efficiently identify the long-distance small target, and compared with the traditional target detection method, the method has the conclusion obtained through simulation tests that the identification accuracy rate of the long-distance small target with the distance of 200m out reaches 95%.
By operating the system for over-the-horizon target detection based on GAN in the embodiment, the method for over-the-horizon target detection based on GAN can be executed, and the method for over-the-horizon target detection based on GAN comprises the following steps:
s1, continuously acquiring a target image from a road in a preset range in real time;
s2, operating a GAN algorithm to perform resolution enhancement processing on the target image;
and S3, operating a YOLOv5 target detection algorithm, and identifying the traffic element target from the target image processed by the main control module.
The method for detecting a beyond-the-horizon target based on GAN in this embodiment may be performed by writing a computer program for executing the method for detecting a beyond-the-horizon target based on GAN in this embodiment, writing the computer program into a computer device or a storage medium, and executing the method for detecting a beyond-the-horizon target based on GAN in this embodiment when the computer program is read and run.
It should be noted that, unless otherwise specified, when a feature is referred to as being "fixed" or "connected" to another feature, it may be directly fixed or connected to the other feature or indirectly fixed or connected to the other feature. Furthermore, the descriptions of upper, lower, left, right, etc. used in the present disclosure are only relative to the mutual positional relationship of the constituent parts of the present disclosure in the drawings. As used in this disclosure, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. In addition, unless defined otherwise, all technical and scientific terms used in this example have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in the description of the embodiments herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this embodiment, the term "and/or" includes any combination of one or more of the associated listed items.
It will be understood that, although the terms first, second, third, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element of the same type from another. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of the present disclosure. The use of any and all examples, or exemplary language ("e.g.," such as "or the like") provided with this embodiment is intended merely to better illuminate embodiments of the invention and does not pose a limitation on the scope of the invention unless otherwise claimed.
It should be recognized that embodiments of the present invention can be realized and implemented by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer readable memory. The methods may be implemented in a computer program using standard programming techniques, including a non-transitory computer-readable storage medium configured with the computer program, where the storage medium so configured causes a computer to operate in a specific and predefined manner, according to the methods and figures described in the detailed description. Each program may be implemented in a high level procedural or object oriented programming language to communicate with a computer system. However, the program(s) can be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.
Further, operations of processes described in this embodiment can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described in this embodiment (or variations and/or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) collectively executed on one or more processors, by hardware, or combinations thereof. The computer program includes a plurality of instructions executable by one or more processors.
Further, the method may be implemented in any type of computing platform operatively connected to a suitable interface, including but not limited to a personal computer, mini computer, mainframe, workstation, networked or distributed computing environment, separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, and the like. Aspects of the invention may be embodied in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optically read and/or write storage medium, RAM, ROM, or the like, such that it may be read by a programmable computer, which when read by the storage medium or device, is operative to configure and operate the computer to perform the procedures described herein. Further, the machine-readable code, or portions thereof, may be transmitted over a wired or wireless network. The invention described in this embodiment includes these and other different types of non-transitory computer-readable storage media when such media include instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor. The invention also includes the computer itself when programmed according to the methods and techniques described herein.
A computer program can be applied to input data to perform the functions described in the present embodiment to convert the input data to generate output data that is stored to a non-volatile memory. The output information may also be applied to one or more output devices, such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including particular visual depictions of physical and tangible objects produced on a display.
The above description is only a preferred embodiment of the present invention, and the present invention is not limited to the above embodiment, and any modifications, equivalent substitutions, improvements, etc. within the spirit and principle of the present invention should be included in the protection scope of the present invention as long as the technical effects of the present invention are achieved by the same means. The invention is capable of other modifications and variations in its technical solution and/or its implementation, within the scope of protection of the invention.
Claims (10)
1. A beyond visual range target detection system based on GAN is characterized by comprising:
the machine vision module is used for continuously acquiring a target image from a road in a preset range in real time;
the main control module is used for operating a GAN algorithm to perform resolution enhancement processing on the target image;
and the identification module is used for running a YOLOv5 target detection algorithm to identify the traffic element target from the target image processed by the main control module.
2. The GAN-based over-the-horizon target detection system of claim 1 wherein the GAN algorithm is an SRGAN algorithm that is refined using contextual information and an attention mechanism.
3. The GAN-based over-the-horizon target detection system of claim 2 wherein the GAN algorithm uses a generative countermeasure network trained over a small target data set TT 100K.
4. The GAN-based over-the-horizon object detection system of any of claims 1-3, wherein the machine vision module comprises:
the human-computer interaction unit is used for inputting refined settings; the refined setting comprises parameter updating setting, acquisition frequency setting and visual angle setting of the machine vision module;
and the image acquisition unit is used for continuously acquiring a target image from a road in a preset range in real time according to the input fine setting.
5. The GAN-based beyond-line-of-sight target detection system of claim 4, wherein said image capture unit is a high definition camera.
6. The GAN-based over-the-horizon object detection system of any of claims 1-3, further comprising:
and the communication module is used for establishing data communication between functional components in the vehicles and between the vehicles, and sharing the traffic element target identified by the identification module through the data communication.
7. The GAN-based beyond-line-of-sight target detection system of claim 6, wherein said communication module comprises:
the wireless data communication units are arranged in a road area and are connected with vehicle-mounted terminals of vehicles to form a secondary data communication service network; the secondary data communication service network is used for establishing data communication among the vehicle internal functional components so as to share the traffic element target among the vehicle internal functional components;
the relay server is used for being connected with the main control module and each wireless data communication unit to form a primary data communication service network; the primary data communication service network is used for establishing data communication between vehicles so as to share the traffic element target between the vehicles.
8. The beyond visual range target detection method based on the GAN is characterized by comprising the following steps:
continuously acquiring a target image from a road in a preset range in real time;
executing a GAN algorithm to perform resolution enhancement processing on the target image;
running a Yolov5 target detection algorithm, a traffic element target is identified from the target image processed by the host module.
9. A computer apparatus comprising a memory for storing at least one program and a processor for loading the at least one program to perform the GAN-based over-the-horizon object detection method of claim 8.
10. A storage medium having stored therein a processor-executable program, wherein the processor-executable program, when executed by a processor, is configured to perform the GAN-based over-the-horizon object detection method of claim 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110252788.5A CN113095135A (en) | 2021-03-09 | 2021-03-09 | System, method, device and medium for beyond-the-horizon target detection based on GAN |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110252788.5A CN113095135A (en) | 2021-03-09 | 2021-03-09 | System, method, device and medium for beyond-the-horizon target detection based on GAN |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113095135A true CN113095135A (en) | 2021-07-09 |
Family
ID=76666536
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110252788.5A Pending CN113095135A (en) | 2021-03-09 | 2021-03-09 | System, method, device and medium for beyond-the-horizon target detection based on GAN |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113095135A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130088600A1 (en) * | 2011-10-05 | 2013-04-11 | Xerox Corporation | Multi-resolution video analysis and key feature preserving video reduction strategy for (real-time) vehicle tracking and speed enforcement systems |
| CN106570886A (en) * | 2016-10-27 | 2017-04-19 | 南京航空航天大学 | Target tracking method based on super-resolution reconstruction |
| CN110188807A (en) * | 2019-05-21 | 2019-08-30 | 重庆大学 | Tunnel pedestrian target detection method based on cascade super-resolution network and improvement Faster R-CNN |
| CN112150414A (en) * | 2020-09-03 | 2020-12-29 | 珠海格力电器股份有限公司 | Target object detection method and device, electronic equipment and storage medium |
| CN112446436A (en) * | 2020-12-11 | 2021-03-05 | 浙江大学 | Anti-fuzzy unmanned vehicle multi-target tracking method based on generation countermeasure network |
-
2021
- 2021-03-09 CN CN202110252788.5A patent/CN113095135A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130088600A1 (en) * | 2011-10-05 | 2013-04-11 | Xerox Corporation | Multi-resolution video analysis and key feature preserving video reduction strategy for (real-time) vehicle tracking and speed enforcement systems |
| CN106570886A (en) * | 2016-10-27 | 2017-04-19 | 南京航空航天大学 | Target tracking method based on super-resolution reconstruction |
| CN110188807A (en) * | 2019-05-21 | 2019-08-30 | 重庆大学 | Tunnel pedestrian target detection method based on cascade super-resolution network and improvement Faster R-CNN |
| CN112150414A (en) * | 2020-09-03 | 2020-12-29 | 珠海格力电器股份有限公司 | Target object detection method and device, electronic equipment and storage medium |
| CN112446436A (en) * | 2020-12-11 | 2021-03-05 | 浙江大学 | Anti-fuzzy unmanned vehicle multi-target tracking method based on generation countermeasure network |
Non-Patent Citations (1)
| Title |
|---|
| HARSH NILESH PATHAK ET AL.: "Efficient Super Resolution For Large-Scale Images Using Attentional GAN", 《ARXIV.ORG》, 13 January 2019 (2019-01-13), pages 1 - 10 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108082037B (en) | Brake light detection | |
| CN106170828B (en) | External recognition device | |
| CN106952303B (en) | Vehicle distance detection method, device and system | |
| CN107274695B (en) | Intelligent lighting system, intelligent vehicle and vehicle driving assisting system and method thereof | |
| US9679196B2 (en) | Object sensing device | |
| US11527077B2 (en) | Advanced driver assist system, method of calibrating the same, and method of detecting object in the same | |
| US11727668B2 (en) | Using captured video data to identify pose of a vehicle | |
| CN110730966B (en) | System and method for pedestrian detection | |
| EP2717219B1 (en) | Object detection device, object detection method, and object detection program | |
| JP2020502654A (en) | Human-machine hybrid decision-making method and apparatus | |
| US10824885B2 (en) | Method and apparatus for detecting braking behavior of front vehicle of autonomous vehicle | |
| KR20160135482A (en) | Apparatus and method for predicting moving of on-road obstable | |
| US11138451B2 (en) | Training image selection system | |
| EP3044549A2 (en) | System and method for augmented reality support | |
| CN111950348A (en) | Method and device for identifying wearing state of safety belt, electronic equipment and storage medium | |
| CN114119955A (en) | Method and device for detecting potential dangerous target | |
| CN111967377A (en) | Method, device and equipment for identifying state of engineering vehicle and storage medium | |
| Li et al. | A low-cost and fast vehicle detection algorithm with a monocular camera for adaptive driving beam systems | |
| CN114240816A (en) | Road environment sensing method and device, storage medium, electronic equipment and vehicle | |
| CN108881846B (en) | Information fusion method and device and computer readable storage medium | |
| KR20160093464A (en) | Apparatus for recognizing traffic sign and method thereof | |
| JP7269694B2 (en) | LEARNING DATA GENERATION METHOD/PROGRAM, LEARNING MODEL AND EVENT OCCURRENCE ESTIMATING DEVICE FOR EVENT OCCURRENCE ESTIMATION | |
| CN113095135A (en) | System, method, device and medium for beyond-the-horizon target detection based on GAN | |
| CN116563801A (en) | Traffic accident detection method, device, electronic equipment and medium | |
| CN112975989B (en) | Robot safe operation method, equipment 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210709 |