CN111985378A - Road target detection method, device and equipment and vehicle - Google Patents
Road target detection method, device and equipment and vehicle Download PDFInfo
- Publication number
- CN111985378A CN111985378A CN202010814018.0A CN202010814018A CN111985378A CN 111985378 A CN111985378 A CN 111985378A CN 202010814018 A CN202010814018 A CN 202010814018A CN 111985378 A CN111985378 A CN 111985378A
- Authority
- CN
- China
- Prior art keywords
- target
- road
- road scene
- vehicle
- detector
- 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 19
- 238000000034 method Methods 0.000 claims abstract description 33
- 230000006870 function Effects 0.000 claims description 16
- 238000007477 logistic regression Methods 0.000 claims description 11
- 238000011176 pooling Methods 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 13
- 238000013527 convolutional neural network Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 240000004050 Pentaglottis sempervirens Species 0.000 description 1
- 235000004522 Pentaglottis sempervirens Nutrition 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000006467 substitution reaction 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The embodiment of the invention discloses a method, a device and equipment for detecting a road target and a vehicle. The method comprises the following steps: analyzing the collected road image data to obtain the current target road scene category of the vehicle; determining a target detector according to the target road scene category; and processing the laser point cloud data based on the target detector to obtain a target obstacle. According to the method for detecting the road target, the corresponding detector is selected according to the type of the road scene where the vehicle is located at present, the laser point cloud data are processed, the requirement on the detection speed can be met, and the detection precision can be guaranteed.
Description
Technical Field
The embodiment of the invention relates to the technical field of unmanned driving, in particular to a method, a device, equipment and a vehicle for detecting a road target.
Background
The automatic driving technology is in a starting stage, the safety problem is the primary problem facing the realization of automatic driving, and the complicated road environment and the higher driving speed cause the automatic driving to have extremely high requirements on the precision and the real-time performance of a detection algorithm. The existing mainstream laser radar point cloud detector is roughly divided into a first-stage detector and a second-stage detector, wherein the first-stage detector has the advantages of high processing speed, high efficiency and good real-time performance, but the detection precision is slightly worse than that of the second-stage detector; the detection precision of the two-stage detector is higher, but the real-time performance is worse than that of the first stage.
Disclosure of Invention
The embodiment of the invention provides a method, a device and equipment for detecting a road target and a vehicle.
In a first aspect, an embodiment of the present invention provides a method for detecting a road target, including:
analyzing the collected road image data to obtain the current target road scene category of the vehicle;
determining a target detector according to the target road scene category;
and processing the laser point cloud data based on the target detector to obtain a target obstacle.
Further, analyzing the acquired road image data to obtain the current road scene category of the vehicle, including:
inputting the collected road image data into a road scene classifier, and outputting the probability of a plurality of road scene categories where the vehicle is currently located;
and determining the road scene category with the highest probability as the target road scene category.
Further, the road scene classifier comprises a convolution layer, a pooling layer, a full-link and logistic regression function; inputting the acquired road image data into a road scene classifier, and outputting the probability of a plurality of road scene categories in which the vehicle is currently located, wherein the probability comprises the following steps:
inputting the collected road image data into a convolution layer and a pooling layer for feature extraction;
inputting the extracted features into the full-connection layer for weighted summation;
and inputting the value obtained by weighted summation into the logistic regression function to obtain the probability of a plurality of road scene categories where the vehicle is located currently.
Further, determining a target detector according to the target road scene category includes:
if the target road scene is a simple road scene, determining that the target detector is a one-stage detector;
and if the target road scene is a complex road scene, determining that the target detector is a two-stage detector.
Further, after obtaining the target obstacle, the method further includes:
and sending the information of the target obstacle to a decision control module so as to control the vehicle.
In a second aspect, an embodiment of the present invention further provides a device for detecting a road target, including:
the target road scene category acquisition module is used for analyzing the acquired road image data to acquire the current target road scene category of the vehicle;
the target detector determining module is used for determining a target detector according to the target road scene category;
and the target obstacle acquisition module is used for processing the laser point cloud data based on the target detector to obtain a target obstacle.
Further, the target road scene category obtaining module is further configured to: inputting the collected road image data into a road scene classifier, and outputting the probability of a plurality of road scene categories where the vehicle is currently located;
and determining the road scene category with the highest probability as the target road scene category.
Further, the target road scene category obtaining module is further configured to:
inputting the collected road image data into a convolution layer and a pooling layer for feature extraction;
inputting the extracted features into the full-connection layer for weighted summation;
and inputting the value obtained by weighted summation into the logistic regression function to obtain the probability of a plurality of road scene categories where the vehicle is located currently.
In a third aspect, an embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the method for detecting a road object according to the embodiment of the present invention.
In a fourth aspect, the embodiment of the present invention further provides a vehicle, including a vehicle lateral obstacle avoidance device, where the vehicle lateral obstacle avoidance device is used to implement the method for detecting a road target according to the embodiment of the present invention.
According to the method, the device and the equipment for detecting the road target and the vehicle disclosed by the embodiment of the invention, firstly, collected road image data are analyzed to obtain the type of a target road scene where the vehicle is located at present, then, a target detector is determined according to the type of the target road scene, and finally, laser point cloud data are processed based on the target detector to obtain a target obstacle. According to the method for detecting the road target, the corresponding detector is selected according to the type of the road scene where the vehicle is located at present, the laser point cloud data are processed, the requirement on the detection speed can be met, and the detection precision can be guaranteed.
Drawings
Fig. 1 is a flowchart of a method for detecting a road target according to a first embodiment of the present invention;
FIG. 2 is a schematic diagram of a road scene classifier according to a first embodiment of the present invention;
FIG. 3 is a schematic diagram of a one-stage detector in accordance with one embodiment of the present invention;
FIG. 4 is a schematic diagram of a two-stage detector in accordance with a first embodiment of the invention;
fig. 5 is a schematic structural diagram of a road target detection device according to a second embodiment of the present invention;
FIG. 6 is a schematic structural diagram of a computer device according to a third embodiment of the present invention;
fig. 7 is a schematic structural diagram of a vehicle according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a method for detecting a road object according to an embodiment of the present invention, where the embodiment is applicable to a situation where objects around a vehicle are identified, and the method may be executed by a road object detection device, as shown in fig. 1, and the method specifically includes the following steps:
and step 110, analyzing the acquired road image data to obtain the current target road scene type of the vehicle.
Wherein, road image data can be gathered by the vehicle-mounted camera. The road scene categories may include simple road scenes (e.g., highway scenes) and complex road scenes (e.g., city road scenes).
Specifically, the manner of analyzing the acquired road image data to obtain the current road scene category of the vehicle may be: inputting the collected road image data into a road scene classifier, and outputting the probability of a plurality of road scene categories where the vehicle is currently located; and determining the road scene category with the highest probability as the target road scene category.
Wherein, the road scene classifier can be a trained neural network. The road scene classifier inputs road image data and outputs road scene categories and probabilities of the road scene categories.
In this embodiment, the road scene classifier includes a convolution layer, a pooling layer, a full-link and a logistic regression function. Wherein the logistic regression function may be a softmax function. Fig. 2 is a schematic diagram of a road scene classifier in the present embodiment, and as shown in fig. 2, the road scene classifier includes two convolution layers, two pooling layers, two full-link layers, and one softmax function.
Specifically, the process of inputting the collected road image data into the road scene classifier and outputting the probabilities of the multiple road scene categories in which the vehicle is currently located may be: inputting the collected road image data into a convolution layer and a pooling layer for feature extraction; inputting the extracted features into a full-connection layer for weighted summation; and inputting the value obtained by weighted summation into a logistic regression function to obtain the probability of a plurality of road scene categories where the vehicle is located currently. And finally, determining the road scene category with the maximum probability as the target road scene category.
Step 120, determining a target detector according to the target road scene type.
Specifically, the manner of determining the target detector according to the target road scene category may be: if the target road scene is a simple road scene, determining that the target detector is a one-stage detector; and if the target road scene is a complex road scene, determining that the target detector is a two-stage detector.
The principle of the one-stage detector is to perform regression calculation on the data directly, and the regression calculation can be realized by using algorithms such as YOLO, SSD, SECOND and YOLO 3D. The principle of the two-stage classifier can be that a series of candidate boxes are generated firstly, and classification is carried out through a convolutional neural network, and common algorithms include R-CNN, FastR-CNN, Faster R-CNN, AVOD and the like.
For example, fig. 3 is a schematic diagram of a one-stage detector in this embodiment, where the one-stage detector is a SECOND network, and as shown in fig. 3, a voxel feature and a coordinate are obtained according to laser point cloud data, and then the voxel feature and the coordinate are sequentially input into a voxel feature extractor, a sparse convolution layer, and a region suggestion network, and finally classification, frame regression, and direction classification are performed.
For example, fig. 4 is a schematic diagram of a two-stage detector in this embodiment, which is an Aggregate View Object Detection network (AVOD). The RPN structure in AVOD addresses the full resolution feature elements in the image and bird's-eye view feature maps as inputs, allowing smaller size targets to produce high recall rates.
And step 130, processing the laser point cloud data based on the target detector to obtain a target obstacle.
And when the target road scene is a simple road scene, the determined target detector is a one-stage detector, and the one-stage detector is adopted to process the laser point cloud data. And when the target road scene is a complex road scene, the determined target detector is a two-stage detector, and the two-stage detector is adopted to process the laser point cloud data.
Optionally, after obtaining the target obstacle, the method further includes the following steps: and sending the information of the target obstacle to a decision control module to control the vehicle.
According to the technical scheme of the embodiment of the invention, the collected road image data is firstly analyzed to obtain the current target road scene type of the vehicle, then the target detector is determined according to the target road scene type, and finally the laser point cloud data is processed based on the target detector to obtain the target barrier. According to the method for detecting the road target, the corresponding detector is selected according to the type of the road scene where the vehicle is located at present, the laser point cloud data are processed, the requirement on the detection speed can be met, and the detection precision can be guaranteed.
Example two
Fig. 5 is a schematic structural diagram of a road target detection device according to a second embodiment of the present invention. As shown in fig. 5, the apparatus includes: a target road scene category acquisition module 210, a target detector determination module 220 and a target obstacle acquisition module 230.
A target road scene category obtaining module 210, configured to analyze the acquired road image data to obtain a target road scene category where the vehicle is currently located;
a target detector determination module 220 for determining a target detector according to the target road scene category;
and a target obstacle obtaining module 230, configured to process the laser point cloud data based on the target detector, so as to obtain a target obstacle.
Optionally, the target road scene category obtaining module 210 is further configured to: inputting the collected road image data into a road scene classifier, and outputting the probability of a plurality of road scene categories where the vehicle is currently located;
and determining the road scene category with the highest probability as the target road scene category.
Optionally, the target road scene category obtaining module 210 is further configured to:
inputting the collected road image data into a convolution layer and a pooling layer for feature extraction;
inputting the extracted features into a full-connection layer for weighted summation;
and inputting the value obtained by weighted summation into a logistic regression function to obtain the probability of a plurality of road scene categories where the vehicle is located currently.
Optionally, the target detector determining module 220 is further configured to:
if the target road scene is a simple road scene, determining that the target detector is a one-stage detector;
and if the target road scene is a complex road scene, determining that the target detector is a two-stage detector.
Optionally, the method further includes: a vehicle control module to:
and sending the information of the target obstacle to a decision control module to control the vehicle.
The device can execute the methods provided by all the embodiments of the invention, and has corresponding functional modules and beneficial effects for executing the methods. For details not described in detail in this embodiment, reference may be made to the methods provided in all the foregoing embodiments of the present invention.
EXAMPLE III
Fig. 6 is a schematic structural diagram of a computer device according to a third embodiment of the present invention. FIG. 6 illustrates a block diagram of a computer device 312 suitable for use in implementing embodiments of the present invention. The computer device 312 shown in FIG. 6 is only an example and should not bring any limitations to the functionality or scope of use of embodiments of the present invention. The device 312 is a computing device that typically detects the detection function of a road object.
As shown in FIG. 6, computer device 312 is in the form of a general purpose computing device. The components of computer device 312 may include, but are not limited to: one or more processors 316, a storage device 328, and a bus 318 that couples the various system components including the storage device 328 and the processors 316.
The computer device 312 may also communicate with one or more external devices 314 (e.g., keyboard, pointing device, camera, display 324, etc.), with one or more devices that enable a user to interact with the computer device 312, and/or with any devices (e.g., network card, modem, etc.) that enable the computer device 312 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interfaces 322. Also, computer device 312 may communicate with one or more networks (e.g., a Local Area Network (LAN), Wide Area Network (WAN), etc.) and/or a public Network, such as the internet, via Network adapter 320. As shown, network adapter 320 communicates with the other modules of computer device 312 via bus 318. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the computer device 312, including but not limited to: microcode, device drivers, Redundant processing units, external disk drive Arrays, disk array (RAID) systems, tape drives, and data backup storage systems, to name a few.
The processor 316 executes various functional applications and data processing by executing programs stored in the storage device 328, for example, to implement the road object detection method provided by the above-described embodiment of the present invention.
Example four
Fig. 7 is a schematic structural diagram of a vehicle according to a fourth embodiment of the present invention, and as shown in fig. 7, the vehicle includes a road object detection apparatus according to the fourth embodiment of the present invention, the apparatus includes: the target road scene category acquisition module is used for analyzing the acquired road image data to acquire the current target road scene category of the vehicle; the target detector determining module is used for determining a target detector according to the target road scene category; and the target obstacle acquisition module is used for processing the laser point cloud data based on the target detector to obtain a target obstacle.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A method of detecting a road target, comprising:
analyzing the collected road image data to obtain the current target road scene category of the vehicle;
determining a target detector according to the target road scene category;
and processing the laser point cloud data based on the target detector to obtain a target obstacle.
2. The method of claim 1, wherein analyzing the collected road image data to obtain a road scene category in which the vehicle is currently located comprises:
inputting the collected road image data into a road scene classifier, and outputting the probability of a plurality of road scene categories where the vehicle is currently located;
and determining the road scene category with the highest probability as the target road scene category.
3. The method of claim 2, wherein the road scene classifier comprises convolutional layers, pooling layers, full-link, and logistic regression functions; inputting the acquired road image data into a road scene classifier, and outputting the probability of a plurality of road scene categories in which the vehicle is currently located, wherein the probability comprises the following steps:
inputting the collected road image data into a convolution layer and a pooling layer for feature extraction;
inputting the extracted features into the full-connection layer for weighted summation;
and inputting the value obtained by weighted summation into the logistic regression function to obtain the probability of a plurality of road scene categories where the vehicle is located currently.
4. The method of claim 1, wherein determining a target detector from the target road scene class comprises:
if the target road scene is a simple road scene, determining that the target detector is a one-stage detector;
and if the target road scene is a complex road scene, determining that the target detector is a two-stage detector.
5. The method of claim 1, further comprising, after obtaining the target obstacle:
and sending the information of the target obstacle to a decision control module so as to control the vehicle.
6. A road target detection device, comprising:
the target road scene category acquisition module is used for analyzing the acquired road image data to acquire the current target road scene category of the vehicle;
the target detector determining module is used for determining a target detector according to the target road scene category;
and the target obstacle acquisition module is used for processing the laser point cloud data based on the target detector to obtain a target obstacle.
7. The apparatus of claim 6, wherein the target road scene category obtaining module is further configured to: inputting the collected road image data into a road scene classifier, and outputting the probability of a plurality of road scene categories where the vehicle is currently located; and determining the road scene category with the highest probability as the target road scene category.
8. The apparatus of claim 7, wherein the road scene classifier comprises convolutional layers, pooling layers, full-connectivity, and logistic regression functions; the target road scene category obtaining module is further configured to: inputting the collected road image data into a convolution layer and a pooling layer for feature extraction;
inputting the extracted features into the full-connection layer for weighted summation;
and inputting the value obtained by weighted summation into the logistic regression function to obtain the probability of a plurality of road scene categories where the vehicle is located currently.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor, when executing the program, implements the method of detecting a road object as claimed in any one of claims 1 to 5.
10. A vehicle, characterized by comprising a vehicle lateral obstacle avoidance device for implementing a method of detecting a road object as claimed in any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010814018.0A CN111985378A (en) | 2020-08-13 | 2020-08-13 | Road target detection method, device and equipment and vehicle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010814018.0A CN111985378A (en) | 2020-08-13 | 2020-08-13 | Road target detection method, device and equipment and vehicle |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111985378A true CN111985378A (en) | 2020-11-24 |
Family
ID=73434285
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010814018.0A Pending CN111985378A (en) | 2020-08-13 | 2020-08-13 | Road target detection method, device and equipment and vehicle |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111985378A (en) |
Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080089557A1 (en) * | 2005-05-10 | 2008-04-17 | Olympus Corporation | Image processing apparatus, image processing method, and computer program product |
CN104658152A (en) * | 2015-02-15 | 2015-05-27 | 西安交通大学 | Video-based moving object intrusion alarm method |
CN105488534A (en) * | 2015-12-04 | 2016-04-13 | 中国科学院深圳先进技术研究院 | Method, device and system for deeply analyzing traffic scene |
US20160335892A1 (en) * | 2014-03-10 | 2016-11-17 | Hitachi Automotive Systems, Ltd. | System for Avoiding Collision with Multiple Moving Bodies |
CN106772434A (en) * | 2016-11-18 | 2017-05-31 | 北京联合大学 | A kind of unmanned vehicle obstacle detection method based on TegraX1 radar datas |
CN106951847A (en) * | 2017-03-13 | 2017-07-14 | 百度在线网络技术(北京)有限公司 | Obstacle detection method, device, equipment and storage medium |
CN107609602A (en) * | 2017-09-28 | 2018-01-19 | 吉林大学 | A kind of Driving Scene sorting technique based on convolutional neural networks |
CN109145680A (en) * | 2017-06-16 | 2019-01-04 | 百度在线网络技术(北京)有限公司 | A kind of method, apparatus, equipment and computer storage medium obtaining obstacle information |
CN109993082A (en) * | 2019-03-20 | 2019-07-09 | 上海理工大学 | The classification of convolutional neural networks road scene and lane segmentation method |
CN110264468A (en) * | 2019-08-14 | 2019-09-20 | 长沙智能驾驶研究院有限公司 | Point cloud data mark, parted pattern determination, object detection method and relevant device |
CN110598586A (en) * | 2019-08-27 | 2019-12-20 | 电子科技大学 | Target detection method and system |
CN110852255A (en) * | 2019-11-08 | 2020-02-28 | 福州大学 | Traffic target detection method based on U-shaped characteristic pyramid |
CN110879994A (en) * | 2019-12-02 | 2020-03-13 | 中国科学院自动化研究所 | Three-dimensional visual inspection detection method, system and device based on shape attention mechanism |
CN111079586A (en) * | 2019-12-03 | 2020-04-28 | 西安电子科技大学 | Automatic driving target detection system and method based on deep learning and binocular shooting |
CN111126278A (en) * | 2019-12-24 | 2020-05-08 | 北京邮电大学 | Target detection model optimization and acceleration method for few-category scene |
-
2020
- 2020-08-13 CN CN202010814018.0A patent/CN111985378A/en active Pending
Patent Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080089557A1 (en) * | 2005-05-10 | 2008-04-17 | Olympus Corporation | Image processing apparatus, image processing method, and computer program product |
US20160335892A1 (en) * | 2014-03-10 | 2016-11-17 | Hitachi Automotive Systems, Ltd. | System for Avoiding Collision with Multiple Moving Bodies |
CN104658152A (en) * | 2015-02-15 | 2015-05-27 | 西安交通大学 | Video-based moving object intrusion alarm method |
CN105488534A (en) * | 2015-12-04 | 2016-04-13 | 中国科学院深圳先进技术研究院 | Method, device and system for deeply analyzing traffic scene |
CN106772434A (en) * | 2016-11-18 | 2017-05-31 | 北京联合大学 | A kind of unmanned vehicle obstacle detection method based on TegraX1 radar datas |
CN106951847A (en) * | 2017-03-13 | 2017-07-14 | 百度在线网络技术(北京)有限公司 | Obstacle detection method, device, equipment and storage medium |
CN109145680A (en) * | 2017-06-16 | 2019-01-04 | 百度在线网络技术(北京)有限公司 | A kind of method, apparatus, equipment and computer storage medium obtaining obstacle information |
CN107609602A (en) * | 2017-09-28 | 2018-01-19 | 吉林大学 | A kind of Driving Scene sorting technique based on convolutional neural networks |
CN109993082A (en) * | 2019-03-20 | 2019-07-09 | 上海理工大学 | The classification of convolutional neural networks road scene and lane segmentation method |
CN110264468A (en) * | 2019-08-14 | 2019-09-20 | 长沙智能驾驶研究院有限公司 | Point cloud data mark, parted pattern determination, object detection method and relevant device |
CN110598586A (en) * | 2019-08-27 | 2019-12-20 | 电子科技大学 | Target detection method and system |
CN110852255A (en) * | 2019-11-08 | 2020-02-28 | 福州大学 | Traffic target detection method based on U-shaped characteristic pyramid |
CN110879994A (en) * | 2019-12-02 | 2020-03-13 | 中国科学院自动化研究所 | Three-dimensional visual inspection detection method, system and device based on shape attention mechanism |
CN111079586A (en) * | 2019-12-03 | 2020-04-28 | 西安电子科技大学 | Automatic driving target detection system and method based on deep learning and binocular shooting |
CN111126278A (en) * | 2019-12-24 | 2020-05-08 | 北京邮电大学 | Target detection model optimization and acceleration method for few-category scene |
Non-Patent Citations (3)
Title |
---|
ALEX_SHEN97: "目标检测中One-stage的检测算法", 《HTTPS://BLOG.CSDN.NET/SHENTANYUE/ARTICLE/DETAILS/84860600》 * |
王强 等: "基于场景匹配与可重构技术的自适应道路检测", 《传感器与微系统》 * |
王玉金 等: "车载视觉感知系统中障碍检测方法研究", 《科学技术与工程》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110084292B (en) | Target detection method based on DenseNet and multi-scale feature fusion | |
CN110991311B (en) | Target detection method based on dense connection deep network | |
US9443320B1 (en) | Multi-object tracking with generic object proposals | |
Kim et al. | Extracting vehicle trajectories using unmanned aerial vehicles in congested traffic conditions | |
KR102073162B1 (en) | Small object detection based on deep learning | |
CN110796686A (en) | Target tracking method and device and storage device | |
CN111461145B (en) | Method for detecting target based on convolutional neural network | |
CN112711034B (en) | Object detection method, device and equipment | |
WO2022206414A1 (en) | Three-dimensional target detection method and apparatus | |
EP4211651A1 (en) | Efficient three-dimensional object detection from point clouds | |
Gluhaković et al. | Vehicle detection in the autonomous vehicle environment for potential collision warning | |
CN113168558A (en) | Method, artificial neural network, device, computer program and machine-readable storage medium for semantic segmentation of image data | |
Faisal et al. | Object detection and distance measurement using AI | |
CN117218622A (en) | Road condition detection method, electronic equipment and storage medium | |
CN113838125A (en) | Target position determining method and device, electronic equipment and storage medium | |
CN115527187A (en) | Method and device for classifying obstacles | |
CN112835063B (en) | Method, device, equipment and storage medium for determining dynamic and static properties of object | |
CN111985378A (en) | Road target detection method, device and equipment and vehicle | |
CN116868239A (en) | Static occupancy tracking | |
CN113658222A (en) | Vehicle detection tracking method and device | |
US20230386222A1 (en) | Method for detecting three-dimensional objects in roadway and electronic device | |
Priya et al. | Vehicle Detection in Autonomous Vehicles Using Computer Vision Check for updates | |
CN111338336B (en) | Automatic driving method and device | |
Vellaidurai et al. | A novel OYOLOV5 model for vehicle detection and classification in adverse weather conditions | |
US10970855B1 (en) | Memory-efficient video tracking in real-time using direction vectors |
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 |
Application publication date: 20201124 |
|
RJ01 | Rejection of invention patent application after publication |