CN115690704A - LG-CenterNet model-based complex road scene target detection method and device - Google Patents
LG-CenterNet model-based complex road scene target detection method and device Download PDFInfo
- Publication number
- CN115690704A CN115690704A CN202211179337.4A CN202211179337A CN115690704A CN 115690704 A CN115690704 A CN 115690704A CN 202211179337 A CN202211179337 A CN 202211179337A CN 115690704 A CN115690704 A CN 115690704A
- Authority
- CN
- China
- Prior art keywords
- module
- model
- feature
- target
- road scene
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 5
- 238000010586 diagram Methods 0.000 claims description 20
- 238000011176 pooling Methods 0.000 claims description 16
- 208000037170 Delayed Emergence from Anesthesia Diseases 0.000 claims description 14
- 230000004913 activation Effects 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 230000000875 corresponding effect Effects 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 238000011897 real-time detection Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a complex road scene target detection method and a device based on an LG-CenterNet model, which are used for collecting an original road image data set to prepare a data set, extracting a feature pair by constructing the LG-CenterNet network model and using ResNet50 as a backsbone of the model, and guiding the features of different levels while improving the sense of the feature pattern of a main network by adopting a level guiding attention mechanism; inputting the feature graph processed by the level guide mechanism into a scaleseEncoder module for processing; performing characteristic pixel reduction by adopting a deconvolution module; a new feature enhancement module is adopted for the restored features to solve the problem of feature information loss in the pixel restoration process; and finally, inputting the enhanced feature map into a Center points prediction module for road target class identification and position positioning. The average recognition precision of the self-built complex road scene data set is 86.93%, the road scene target image detection speed reaches 50 frames/s, and the requirements on accurate detection and real-time detection of a road scene can be met.
Description
Technical Field
The invention belongs to the field of semantic segmentation, image processing and intelligent driving, and particularly relates to a complex road scene target detection method and device based on an LG-CenterNet model.
Background
The steady rise of the number of automobiles in recent years leads to frequent traffic accidents, which seriously threatens the life safety of people. Nowadays, with the development of automatic driving technology, researchers also turn to the active safety technology research of automobiles from the passive safety technology research of automobiles. The automation of automobiles must be realized by using some advanced technical means to complete part of automobile driving tasks. The key to solving the active safety technology of automobiles is to adopt a deep learning method to carry out intelligent detection on road scene targets. In the current stage, feature extraction is mainly performed on a target detection network through a backbone network, but excessive consideration is not performed on the underlying multi-scale problem, which may cause the situation that the multi-scale target detection capability is insufficient.
Disclosure of Invention
The purpose of the invention is as follows: aiming at the problems that the application effect of the complex road scene target detection is poor at the present stage, and the conventional detection method cannot meet the detection requirement of the actual road environment, the complex road scene target detection method and the complex road scene target detection device based on the LG-CenterNet model are provided.
The technical scheme is as follows: the invention provides an LG-CenterNet model-based complex road scene target detection method, which specifically comprises the following steps of:
(1) Processing images of complex road scenes to obtain road target images containing various categories, marking the categories and positions of road targets in the images, constructing a complex road scene data set and preprocessing the complex road scene data set;
(2) Constructing an LG-CenterNet model for target detection, and training the road target data set through the LG-CenterNet model to obtain a model S; the LG-CenterNet model comprises a Backbone module, a hierarchical attention directing module, a Scales Encoder module, a deconvolution module, a feature enhancement module and a Centerpoints prediction module;
(3) And (3) performing target positioning, frame size division and category prediction on the complex road target in a thermodynamic diagram mode by using the trained model S through a Center points prediction module, and displaying the obtained result on a video or an image to input a corresponding effect.
Further, the preprocessing of the road scene data set in the step (1) is to normalize the image of the complex road scene with different pixels, normalize the size of the image to 512 × 512 pixels, and obtain the uniformly distributed feature target samples through batch normalization, the ReLU activation function and the maximum pooling operation.
Further, the step (2) is realized as follows:
(21) A new Mresneit50 is proposed in the LG-CenterNet model to serve as a Backbone module, the Mresneit50 is composed of a plurality of residual blocks, a feature diagram extracted by 4 residual blocks is marked as E1, and the number of channels is 512; marking a feature map extracted by the 6 residual blocks as E2, wherein the number of channels is 1024; the feature map extracted by the number of 3 channels is marked as E3, and the number of the channels is 2048;
(22) The characteristics E1, E2 and E3 extracted by the Backbone are input into a hierarchy guide attention module, and the main structure of the hierarchy guide attention module comprises two branches: the method comprises the steps of global pooling branching and level guiding branching, inputting a feature map E1 with the channel number being 512 into the global pooling branching, and obtaining EC1 through operation of a global maximum pooling layer and an upper sampling layer; inputting feature maps E1, E2 and E3 with the channel numbers of 512, 1024 and 2048 into a hierarchical guide branch, and obtaining EC2 through a series of average pooling and convolution operations and matching with upsampling; performing feature combination on EC1 and EC2 by using add to obtain EC3, thereby reducing calculation parameters;
(23) Inputting the extracted EC3 into a Scales Encoder module, and carrying out a series of convolution and residual module operations to obtain EC4;
(24) Inputting the extracted EC4 into a deconvolution module, wherein the deconvolution module consists of 3 deconv groups, the size of the feature graph is continuously enlarged through convolution operation of the deconv groups each time, and the number of channels is continuously reduced at the same time, so that a feature graph with the scale of 128 multiplied by 64 is obtained and marked as EC5;
(25) Inputting the feature map EC5 into a feature enhancement module to carry out Convolution operation to obtain a feature map EC6 with the dimension of 128 × 128 × 64, wherein the P-FEM is composed of 3 × 3 Poly-Scale conversion, batch standardization, reLU activation function and Sigmoid activation function, and is mainly used for improving the correlation of local information in the feature map and enhancing the expression capability of the feature map on the features.
Further, the step (3) is realized as follows:
the Centerpoints prediction module classifies and predicts the input pictures through the trained model S, generates a heatmap image with the scale consistent with the size of EC6 from the original image, and then records the loss value of the original image as L through respectively calculating the thermodynamic diagrams h The loss value of the target length and width is expressed as L s And the loss value of the center point offset is recorded as L f To determine the position and size of the target and to generate a final sorted positioned heatmap; where the overall network loss is:
L d ＝L k +λ s L s +λ f L f
wherein λ is s ＝0.1，λ f =1; for an image with an input picture size of 512 × 215, the feature map generated by the network is H × W × C, and L k 、L s And L f The calculation formulas are respectively as follows:
wherein, A HWC Is the true value, A ', of the target annotation in the image' HWC Is a predicted value of the picture, alpha and beta are 2 and 4 respectively, N is the number of key points in the picture, s' pk To predict the size, s k For the true size, p is the position of the center point of the object in the image.
Based on the same inventive concept, the invention also provides an LG-centret model-based complex road scene object detection device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the computer program realizes the LG-centret model-based complex road scene object detection method when being loaded to the processor.
Has the beneficial effects that: compared with the prior art, the invention has the beneficial effects that: 1. by improving a backbone network of the LG-CenterNet model, an Mresneit50 enhanced feature extraction effect is provided; 2. providing a hierarchical attention guiding module for carrying out feature fusion on feature maps extracted by a backbone network; 3. a new Scales Encoder module and a new feature enhancement module are provided, which pay attention to the extraction of local features, and the problem of feature loss in a deconvolution module is avoided; 4. the improved LG-CenterNet target detection model is improved by 5 percent compared with the average precision mAP (meanAverageprecision) of the original CenterNet framework; 5. the invention has higher detection precision in dealing with complex road scenes.
Drawings
FIG. 1 is a flow chart of a complex road scene object detection method based on LG-CenterNet model;
FIG. 2 is a schematic diagram of an LG-CenterNet-based target detection model proposed by the present invention;
FIG. 3 is a diagram of a residual block structure Mlock according to the present invention;
FIG. 4 is a schematic diagram of a hierarchical guidance attention model structure;
FIG. 5 is a schematic diagram of the structure of the Scales Encoder module;
FIG. 6 is a schematic diagram of a feature enhancement module structure;
FIG. 7 is a graph showing the detection effect obtained by using the LG-CenterNet target detection model.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
A large number of variables are involved in the present embodiment, and each variable will now be described as follows. As shown in table 1.
Table 1 description of variables
| Variables of | Description of variables |
| S | Convolution kernel with 3 x 3 and 1024 channels |
| E1 | Characteristic diagram extracted from 4 residual blocks in Backbone module |
| E2 | Characteristic diagram extracted from 6 residual blocks in Backbone module |
| E3 | Characteristic diagram extracted from 3 residual blocks in Backbone module |
| EC1 | E1 feature map obtained by global pooling branching |
| EC2 | Characteristic diagram obtained by E1, E2 and E3 through hierarchical guide branches |
| EC3 | Feature map EC2 processed by ScalesEncoder Module |
| EC4 | Feature map EC3 processed by ScalesEncoder module |
| EC5 | The feature map EC4 is processed by the deconvolution module |
| EC6 | Feature map EC5 processed by the feature enhancement module |
The invention provides a complex road scene target detection method based on an LG-CenterNet model, which comprises the steps of collecting different target images of a road scene and marking the target images to manufacture a complex road scene data set, utilizing proposed Mresneit50 as a backbone network to extract features, inputting feature maps of different Scales extracted from the backbone network into a hierarchy guide attention module, then obtaining a plurality of receptive field features through a Scales Encoder module, then utilizing a deconvolution module to restore feature pixels, and utilizing a Poly-Scale contribution (PSConv for short) to construct a feature enhancement module to improve the information correlation of local features. And finally, predicting the position of the central point of the target, the dimension of the prediction frame and the offset of the central point by using a Center points prediction module, and identifying the type of the target. As shown in fig. 1, the method specifically comprises the following steps:
step 1: and processing the image of the complex road scene, acquiring a road target image containing multiple categories, preprocessing the road target image, marking the categories and the positions of the road targets in the image, and constructing a complex road scene data set.
The road scene data set is preprocessed mainly by normalizing images of different pixels and complex road scenes, normalizing the size of the images to be 512 x 512 pixels, and then performing Batch normalization, reLU activation function and maximum pooling to obtain that target samples are distributed more uniformly in the images.
And 2, constructing an LG-CenterNet model for target detection, wherein the structure of the LG-CenterNet model is shown in fig. 2, and training the road target data set through the LG-CenterNet model to obtain a model S, wherein the LG-CenterNet model mainly comprises a Back bone module, a level guide attention module (LGA for short), a Scales Encoder module, a deconvolution module, a Feature enhancement module (P-Feature enhancement module, P-FEM) and a Centerpoints prediction module.
(21) A new Mresneit50 is proposed in the LG-CenterNet model to serve as a backhaul module, the Mresneit50 is composed of a plurality of residual blocks Mblock, the structure of the residual blocks Mblock is shown in FIG. 3, a characteristic diagram obtained by extracting 4 residual blocks is marked as E1, and the number of channels is 512; the feature map extracted by the 6 residual blocks is marked as E2, and the number of channels is 1024; the feature map extracted by the number of 3 channels is marked as E3, and the number of channels is 2048.
(22) The characteristic diagrams E1, E2, and E3 extracted from the backhaul are input into a level guide attention module (LGA), the structure of which is shown in fig. 4, and the main structure of the LGA module includes two branches: the method comprises the steps of global pooling branching and level guiding branching, inputting a feature map E1 with the channel number being 512 into the global pooling branching, and obtaining EC1 through operation of a global maximum pooling layer and an upper sampling layer; inputting the feature maps E1, E2 and E3 with the channel numbers of 512, 1024 and 2048 into the hierarchical guide branch, and obtaining EC2 through a series of average pooling and convolution operations in cooperation with upsampling. And (4) carrying out feature combination on EC1 and EC2 by using add to obtain EC3, thereby reducing the calculation parameters.
(23) And inputting the extracted EC3 into a Scales Encoder module, wherein the Scales Encoder module has a structure shown in FIG. 5, and performing a series of convolution and residual module operations to obtain EC4.
(24) And inputting the extracted EC4 into a deconvolution module, wherein the deconvolution module consists of 3 deconv groups, the size of the characteristic graph is continuously enlarged through convolution operation of the deconv groups each time, and the number of channels is continuously reduced, so that the characteristic graph with the dimension of 128 multiplied by 64 is obtained and recorded as EC5.
(25) The feature map EC5 is input into a P-FEM to be subjected to Convolution operation to obtain a feature map EC6 with the dimension of 128 x 64, wherein the P-FEM is composed of 3 x 3 Poly-Scale constraint (PSConv for short), batch normalization (Batchnormalization), reLU activation function and Sigmoid activation function, and the feature map EC6 is mainly used for improving the correlation of local information in the feature map and enhancing the expression capability of the feature map on the features. The P-FEM structure is shown in fig. 6.
And step 3: and (3) carrying out target positioning, frame size division and category prediction on the road scene target in a thermodynamic diagram form by using the trained model S through a Centerpoints prediction module, and displaying the obtained result on a video or an image to input a corresponding effect.
The Centerpoints prediction module classifies and predicts the input pictures through the trained model S, generates a heatmap image with the scale consistent with the size of EC6 from the original image, and then records the loss value of the original image as L through respectively calculating the thermodynamic diagrams h The loss value of the target length and width (size) is denoted as L s And the loss value of the center point offset (offset) is noted as L f To determine the targetAnd generates a heatmap of the final classified position. Wherein the total network loss is L d 。
L d ＝L k +λ s L s +λ f L f
Wherein λ s ＝0.1，λ f And =1. For an image with an input picture size of 512 × 215, the feature map generated by the network is H × W × C, and L k 、L s And L f The calculation formulas are respectively as follows:
wherein A is HWC True value, A 'of object annotation in image' HWC Is a predicted value of the image, alpha and beta are respectively 2 and 4, N is the number of key points in the image, s' pk To predict the size, s k For the true size, p is the position of the center point of the object in the image.
Based on the same inventive concept, the invention also provides an LG-centret model-based complex road scene object detection device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the computer program realizes the LG-centret model-based complex road scene object detection method when being loaded to the processor. As shown in fig. 7.
Training the self-built complex scene data set through the LG-CenterNet network to obtain a model capable of identifying the complex scene target, and performing model performance verification through a verification set in the data set, as shown in FIG. 7. The identification average precision of the self-built complex road scene data set is 86.93%, the road scene target image detection speed reaches 50 frames/s, and the requirements of accurate detection and real-time detection of the road scene can be met.
Wherein Precision is Precision, recall is Recall, AP is Precision, mAP is average Precision, FPS is frame number, and t is time for detecting a single picture. There are more sample classes in the dataset (e.g., car, person, etc.), n represents the number of samples, and TP (True samples) is the number of positive samples and is considered as the number of positive samples (i.e., the total number of samples considered as car for car); TN (True neighbors) identifies the total number of negative samples for the negative sample model as well; FP (False Positives) is the total number of positive samples that the negative sample model considers as (i.e., the samples are not car and the model considers as the total number of car); FN (False Negatives) identifies the negative sample model as the total number of positive samples.
The embodiments of the present invention have been described in detail with reference to the drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (5)
1. A complex road scene target detection method based on an LG-CenterNet model is characterized by comprising the following steps:
(1) Processing images of complex road scenes to obtain road target images containing various categories, marking the categories and positions of road targets in the images, constructing a complex road scene data set and preprocessing the complex road scene data set;
(2) Constructing an LG-CenterNet model for target detection, and training the road target data set through the LG-CenterNet model to obtain a model S; the LG-CenterNet model comprises a Backbone module, a hierarchy attention-directing module, a Scales Encoder module, a deconvolution module, a feature enhancement module and a Centerpoints prediction module;
(3) And (3) performing target positioning, frame size division and category prediction on the complex road target in a thermodynamic diagram mode by using the trained model S through a Center points prediction module, and displaying and inputting the obtained result on a video or an image to obtain a corresponding effect.
2. The method for detecting the complex road scene target based on the LG-centrnet model as claimed in claim 1, wherein the preprocessing of the road scene data set in step (1) is to normalize the image of the complex road scene by pixel inconsistency, normalize the image size to 512 x 512 pixel size, and obtain the uniformly distributed feature target samples by batch normalization, reLU activation function and max pooling.
3. The LG-CenterNet model-based complex road scene target detection method according to claim 1, wherein the step (2) is realized by the following steps:
(21) A new Mresneit50 is proposed in the LG-CenterNet model to serve as a Backbone module, the Mresneit50 is composed of a plurality of residual blocks, a feature diagram extracted by 4 residual blocks is marked as E1, and the number of channels is 512; marking a feature map extracted by the 6 residual blocks as E2, wherein the number of channels is 1024; the feature map extracted by the number of 3 channels is marked as E3, and the number of the channels is 2048;
(22) The character diagrams E1, E2 and E3 extracted from the Backbone are input into a hierarchical attention-directing module, and the main structure of the hierarchical attention-directing module comprises two branches: the method comprises the steps of global pooling branching and level guiding branching, inputting a feature map E1 with the channel number being 512 into the global pooling branching, and obtaining EC1 through operation of a global maximum pooling layer and an upper sampling layer; inputting feature maps E1, E2 and E3 with the channel numbers of 512, 1024 and 2048 into a hierarchical guide branch, and obtaining EC2 through a series of average pooling and convolution operations and matching with upsampling; performing feature combination on EC1 and EC2 by using add to obtain EC3, thereby reducing calculation parameters;
(23) Inputting the extracted EC3 into a Scales Encoder module, and carrying out a series of convolution and residual module operations to obtain EC4;
(24) Inputting the extracted EC4 into a deconvolution module, wherein the deconvolution module consists of 3 deconv groups, the size of the characteristic graph is continuously enlarged through convolution operation of the deconv groups each time, and the number of channels is continuously reduced at the same time, so that the characteristic graph with the dimension of 128 multiplied by 64 is obtained and recorded as EC5;
(25) Inputting the feature map EC5 into a feature enhancement module to carry out Convolution operation to obtain a feature map EC6 with the dimension of 128 × 128 × 64, wherein the P-FEM is composed of 3 × 3 Poly-Scale conversion, batch standardization, reLU activation function and Sigmoid activation function, and is mainly used for improving the correlation of local information in the feature map and enhancing the expression capability of the feature map on the features.
4. The LG-CenterNet model-based complex road scene target detection method according to claim 1, characterized in that the step (3) is realized by the following steps:
the Centerpoints prediction module classifies and predicts the input pictures through the trained model S, generates a heatmap image with the scale consistent with the size of EC6 from the original image, and then records the loss value of the original image as L through respectively calculating the thermodynamic diagrams h The loss value of the target length and width is expressed as L s And the loss value of the center point offset is recorded as L f To determine the position and size of the target and to generate a final sorted positioned heatmap; where the overall network loss is:
L d ＝L k +λ s L s +λ f L f
wherein λ s ＝0.1，λ f =1; for an image with an input picture size of 512 × 215, the feature map generated by the network is H × W × C, and L k 、L s And L f The calculation formulas are respectively as follows:
wherein, A HWC Is the true value, A ', of the target annotation in the image' HWC Is a predicted value of the image, alpha and beta are respectively 2 and 4, N is the number of key points in the image, s' pk To predict the size, s k For true size, p is the location of the center point of the object in the image.
5. An LG-cenernet model-based complex road scene object detection device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the computer program when loaded into the processor implements the LG-cenernet model-based complex road scene object detection method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211179337.4A CN115690704B (en) | 2022-09-27 | 2022-09-27 | LG-CenterNet model-based complex road scene target detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211179337.4A CN115690704B (en) | 2022-09-27 | 2022-09-27 | LG-CenterNet model-based complex road scene target detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115690704A true CN115690704A (en) | 2023-02-03 |
| CN115690704B CN115690704B (en) | 2023-08-22 |
Family
ID=85063352
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211179337.4A Active CN115690704B (en) | 2022-09-27 | 2022-09-27 | LG-CenterNet model-based complex road scene target detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115690704B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117690165A (en) * | 2024-02-02 | 2024-03-12 | 四川泓宝润业工程技术有限公司 | Method and device for detecting personnel passing between drill rod and hydraulic pliers |
Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108717537A (en) * | 2018-05-30 | 2018-10-30 | 淮阴工学院 | A kind of face identification method and system of the complex scene based on pattern-recognition |
| CN110543895A (en) * | 2019-08-08 | 2019-12-06 | 淮阴工学院 | image classification method based on VGGNet and ResNet |
| CN111382714A (en) * | 2020-03-13 | 2020-07-07 | Oppo广东移动通信有限公司 | Image detection method, device, terminal and storage medium |
| CN111709895A (en) * | 2020-06-17 | 2020-09-25 | 中国科学院微小卫星创新研究院 | Image blind deblurring method and system based on attention mechanism |
| CN111814889A (en) * | 2020-07-14 | 2020-10-23 | 大连理工大学人工智能大连研究院 | Single-stage target detection method using anchor-frame-free module and enhanced classifier |
| CN111932553A (en) * | 2020-07-27 | 2020-11-13 | 北京航空航天大学 | Remote sensing image semantic segmentation method based on area description self-attention mechanism |
| CN112329800A (en) * | 2020-12-03 | 2021-02-05 | 河南大学 | Salient object detection method based on global information guiding residual attention |
| CN112580443A (en) * | 2020-12-02 | 2021-03-30 | 燕山大学 | Pedestrian detection method based on embedded device improved CenterNet |
| CN112686207A (en) * | 2021-01-22 | 2021-04-20 | 北京同方软件有限公司 | Urban street scene target detection method based on regional information enhancement |
| CN112700444A (en) * | 2021-02-19 | 2021-04-23 | 中国铁道科学研究院集团有限公司铁道建筑研究所 | Bridge bolt detection method based on self-attention and central point regression model |
| CN113378815A (en) * | 2021-06-16 | 2021-09-10 | 南京信息工程大学 | Model for scene text positioning recognition and training and recognition method thereof |
| CN113408498A (en) * | 2021-08-05 | 2021-09-17 | 广东众聚人工智能科技有限公司 | Crowd counting system and method, equipment and storage medium |
| CN113657326A (en) * | 2021-08-24 | 2021-11-16 | 陕西科技大学 | Weed detection method based on multi-scale fusion module and feature enhancement |
| WO2021244621A1 (en) * | 2020-06-04 | 2021-12-09 | 华为技术有限公司 | Scenario semantic parsing method based on global guidance selective context network |
| CN114359153A (en) * | 2021-12-07 | 2022-04-15 | 湖北工业大学 | Insulator defect detection method based on improved CenterNet |
| CN114419589A (en) * | 2022-01-17 | 2022-04-29 | 东南大学 | Road target detection method based on attention feature enhancement module |
| CN114581866A (en) * | 2022-01-24 | 2022-06-03 | 江苏大学 | Multi-target visual detection algorithm for automatic driving scene based on improved CenterNet |
| CN114638836A (en) * | 2022-02-18 | 2022-06-17 | 湖北工业大学 | Urban street view segmentation method based on highly effective drive and multi-level feature fusion |
| US20220204035A1 (en) * | 2020-12-28 | 2022-06-30 | Hyundai Mobis Co., Ltd. | Driver management system and method of operating same |
| US20220237403A1 (en) * | 2021-01-28 | 2022-07-28 | Salesforce.Com, Inc. | Neural network based scene text recognition |
| CN114863368A (en) * | 2022-07-05 | 2022-08-05 | 城云科技（中国）有限公司 | Multi-scale target detection model and method for road damage detection |
| CN115035361A (en) * | 2022-05-11 | 2022-09-09 | 中国科学院声学研究所南海研究站 | Target detection method and system based on attention mechanism and feature cross fusion |
-
2022
- 2022-09-27 CN CN202211179337.4A patent/CN115690704B/en active Active
Patent Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108717537A (en) * | 2018-05-30 | 2018-10-30 | 淮阴工学院 | A kind of face identification method and system of the complex scene based on pattern-recognition |
| CN110543895A (en) * | 2019-08-08 | 2019-12-06 | 淮阴工学院 | image classification method based on VGGNet and ResNet |
| CN111382714A (en) * | 2020-03-13 | 2020-07-07 | Oppo广东移动通信有限公司 | Image detection method, device, terminal and storage medium |
| WO2021244621A1 (en) * | 2020-06-04 | 2021-12-09 | 华为技术有限公司 | Scenario semantic parsing method based on global guidance selective context network |
| CN111709895A (en) * | 2020-06-17 | 2020-09-25 | 中国科学院微小卫星创新研究院 | Image blind deblurring method and system based on attention mechanism |
| CN111814889A (en) * | 2020-07-14 | 2020-10-23 | 大连理工大学人工智能大连研究院 | Single-stage target detection method using anchor-frame-free module and enhanced classifier |
| CN111932553A (en) * | 2020-07-27 | 2020-11-13 | 北京航空航天大学 | Remote sensing image semantic segmentation method based on area description self-attention mechanism |
| CN112580443A (en) * | 2020-12-02 | 2021-03-30 | 燕山大学 | Pedestrian detection method based on embedded device improved CenterNet |
| CN112329800A (en) * | 2020-12-03 | 2021-02-05 | 河南大学 | Salient object detection method based on global information guiding residual attention |
| US20220204035A1 (en) * | 2020-12-28 | 2022-06-30 | Hyundai Mobis Co., Ltd. | Driver management system and method of operating same |
| CN112686207A (en) * | 2021-01-22 | 2021-04-20 | 北京同方软件有限公司 | Urban street scene target detection method based on regional information enhancement |
| US20220237403A1 (en) * | 2021-01-28 | 2022-07-28 | Salesforce.Com, Inc. | Neural network based scene text recognition |
| CN112700444A (en) * | 2021-02-19 | 2021-04-23 | 中国铁道科学研究院集团有限公司铁道建筑研究所 | Bridge bolt detection method based on self-attention and central point regression model |
| CN113378815A (en) * | 2021-06-16 | 2021-09-10 | 南京信息工程大学 | Model for scene text positioning recognition and training and recognition method thereof |
| CN113408498A (en) * | 2021-08-05 | 2021-09-17 | 广东众聚人工智能科技有限公司 | Crowd counting system and method, equipment and storage medium |
| CN113657326A (en) * | 2021-08-24 | 2021-11-16 | 陕西科技大学 | Weed detection method based on multi-scale fusion module and feature enhancement |
| CN114359153A (en) * | 2021-12-07 | 2022-04-15 | 湖北工业大学 | Insulator defect detection method based on improved CenterNet |
| CN114419589A (en) * | 2022-01-17 | 2022-04-29 | 东南大学 | Road target detection method based on attention feature enhancement module |
| CN114581866A (en) * | 2022-01-24 | 2022-06-03 | 江苏大学 | Multi-target visual detection algorithm for automatic driving scene based on improved CenterNet |
| CN114638836A (en) * | 2022-02-18 | 2022-06-17 | 湖北工业大学 | Urban street view segmentation method based on highly effective drive and multi-level feature fusion |
| CN115035361A (en) * | 2022-05-11 | 2022-09-09 | 中国科学院声学研究所南海研究站 | Target detection method and system based on attention mechanism and feature cross fusion |
| CN114863368A (en) * | 2022-07-05 | 2022-08-05 | 城云科技（中国）有限公司 | Multi-scale target detection model and method for road damage detection |
Non-Patent Citations (3)
| Title |
|---|
| 于方程 等: "基于改进CenterNet的自动驾驶小目标检测", 《HTTP://KNS.CNKI.NET/KCMS/DETAIL/11.2175.TN.20220719.1838.026.HTML》, pages 1 - 8 * |
| 于方程 等: "基于改进CenterNet的自动驾驶小目标检测", 《电子测量技术》, vol. 45, no. 15, pages 115 - 122 * |
| 成怡 等: "改进CenterNet的交通标志检测算法", 《信号处理》, vol. 38, no. 3, pages 511 - 518 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117690165A (en) * | 2024-02-02 | 2024-03-12 | 四川泓宝润业工程技术有限公司 | Method and device for detecting personnel passing between drill rod and hydraulic pliers |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115690704B (en) | 2023-08-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111696094B (en) | Immunohistochemical PD-L1 membrane staining pathological section image processing method, device and equipment | |
| CN111968150B (en) | Weak surveillance video target segmentation method based on full convolution neural network | |
| CN110175613A (en) | Street view image semantic segmentation method based on Analysis On Multi-scale Features and codec models | |
| CN111340123A (en) | Image score label prediction method based on deep convolutional neural network | |
| CN111369581A (en) | Image processing method, device, equipment and storage medium | |
| CN111027539B (en) | License plate character segmentation method based on spatial position information | |
| CN113033604A (en) | Vehicle detection method, system and storage medium based on SF-YOLOv4 network model | |
| CN114266794B (en) | Pathological section image cancer region segmentation system based on full convolution neural network | |
| CN109982088B (en) | Image processing method and device | |
| CN112990331A (en) | Image processing method, electronic device, and storage medium | |
| CN110689518A (en) | Cervical cell image screening method and device, computer equipment and storage medium | |
| CN115690704B (en) | LG-CenterNet model-based complex road scene target detection method and device | |
| CN115880529A (en) | Method and system for classifying fine granularity of birds based on attention and decoupling knowledge distillation | |
| CN111079543B (en) | Efficient vehicle color identification method based on deep learning | |
| CN112990041B (en) | Remote sensing image building extraction method based on improved U-net | |
| CN112580616B (en) | Crowd quantity determination method, device, equipment and storage medium | |
| CN112348011B (en) | Vehicle damage assessment method and device and storage medium | |
| CN117853803A (en) | Small sample motor car anomaly detection method and system based on feature enhancement and communication network | |
| CN111401360B (en) | Method and system for optimizing license plate detection model, license plate detection method and system | |
| CN116543162B (en) | Image segmentation method and system based on feature difference and context awareness consistency | |
| CN113012167A (en) | Combined segmentation method for cell nucleus and cytoplasm | |
| CN113192018B (en) | Water-cooled wall surface defect video identification method based on fast segmentation convolutional neural network | |
| CN114511845A (en) | License plate character classification and recognition method and medium based on deep learning | |
| CN115661676A (en) | Building segmentation system and method based on serial attention module and parallel attention module | |
| CN118172724A (en) | Target counting method based on reinforcement learning |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20230203 Assignee: Jiangsu Kesheng Xuanyi Technology Co.,Ltd. Assignor: HUAIYIN INSTITUTE OF TECHNOLOGY Contract record no.: X2023980048436 Denomination of invention: Method and device for complex road scene object detection based on LG CenterNet model Granted publication date: 20230822 License type: Common License Record date: 20231129 |
|
| EE01 | Entry into force of recordation of patent licensing contract |