CN109977812A - A kind of Vehicular video object detection method based on deep learning - Google Patents
A kind of Vehicular video object detection method based on deep learning Download PDFInfo
- Publication number
- CN109977812A CN109977812A CN201910185300.4A CN201910185300A CN109977812A CN 109977812 A CN109977812 A CN 109977812A CN 201910185300 A CN201910185300 A CN 201910185300A CN 109977812 A CN109977812 A CN 109977812A
- Authority
- CN
- China
- Prior art keywords
- training
- network
- cnn
- detection method
- method based
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
- G06V10/449—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters
- G06V10/451—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters with interaction between the filter responses, e.g. cortical complex cells
- G06V10/454—Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- 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
Abstract
The invention discloses a kind of Vehicular video object detection method based on deep learning realizes the target detection in complicated traffic environment using improved Faster R-CNN algorithm, provides traffic safety miscellaneous function.There is serious Small object missing inspection in existing target tracking algorism, the present invention is by increasing a depth information channel, it is in parallel with original color image channel, and it is merged on channel dimension, candidate frame extraction and target detection are carried out on fused characteristic image, the verification and measurement ratio of Small object is improved, in addition training of the addition to difficult sample in training improves the object recognition rate of algorithm entirety.The present invention can fully consider Small object missing inspection problem existing for Faster R-CNN algorithm, by depth image Fusion Features and difficult sample method for digging, improve the accuracy rate of vehicle identification in vehicles in complex traffic scene.
Description
Technical field
The present invention relates to a kind of Vehicular video object detection method based on deep learning, belongs to video image processing technology
Field.
Background technique
When driving, to the vehicle of vehicle front, pedestrian and other barriers progress object detecting and tracking, and
The behavioural analysis that front truck is carried out on the basis of this, is the basis of Driving assistant system.The main step of conventional target detection method
It is rapid general are as follows: extraction target signature, the corresponding classifier of training, sliding window search repeat and wrong report filtered.This target inspection
The sliding window selection strategy of survey does not have specific aim, and time complexity is high, window redundancy, and the feature robustness of hand-designed is poor,
Classifier is unreliable;Simultaneously existing algorithm of target detection can not neatly training data it is effective to be learnt according to different demands
Feature complete specific Detection task.
Summary of the invention
It is an object of the invention to solve the above the deficiencies in the prior art, a kind of Vehicular video based on deep learning is provided
Object detection method.
In order to achieve the above objectives, the present invention adopts the following technical scheme that:
A kind of Vehicular video object detection method based on deep learning, includes the following steps:
Step 1) snaps to the pixel under depth coordinate under color coordinate;Depth image and color image are respectively led to again
It crosses CNN and carries out feature extraction, and the characteristic pattern that respective convolutional layer exports is subjected to fused in tandem on channel dimension and is obtained finally
RGB-D feature as the convolution Feature Mapping after convolution;
Step 2) constructs region and suggests network RPN, and the region suggests that network RPN includes one 3 × 3 convolutional layer and two
A 1 × 1 parallel-convolution layer;By the convolutional layer of fused convolution Feature Mapping input 3 × 3, in the Feature Mapping of input
The network of default size is slided as unit of pixel, then each sliding position generates the anchor point of particular dimensions;
The parallel-convolution layer that the anchor point of generation inputs two 1 × 1 is subjected to position recurrence and the judgement of front and back scape, is exported respectively
Before the front and back scape confidence level of anchor point and all candidate frame positions and selecting after resulting rectangle according to preset condition filters out in frame
The highest preceding certain amount of region of scape confidence level, obtains final region set of suggestions C;
Fast R-CNN model is constructed, the Fast R-CNN model is by two pond ROI layers, a full articulamentum and two
The full articulamentum of a parallel connection forms, the confidence level for exporting the region respectively and the candidate frame position after frame recurrence;It will melt
Convolution feature after conjunction inputs Fast R-CNN model, exports the position of target and its classification and confidence level in image;
Step 3): the cost function of training RPN network and the cost function of training Fast R-CNN network are constructed;
Step 4) passes through the standard variance from setting using the ZF model training of standard and the parameters of trim network
Weight, which is extracted, in zero-mean gaussian distribution carrys out all mew layers of random initializtion;
Step 5) utilizes back-propagation algorithm and stochastic gradient descent algorithm, using to two nets of RPN and Fast R-CNN
The mode of network alternating training is trained model, and the weight of every layer of neural network is sequentially adjusted according to pre-set parameter;
Step 6) the Faster R-CNN model good using the training set test initial training being obtained ahead of time, according to difficult sample
Discrimination formula filter out difficult sample;
The difficult sample generated in step 6) is added in training set step 7), is trained again to network, repeats step
5)-step 7) finally obtains optimal Faster R-CNN model;
Step 8) handles the Vehicular video image acquired in practice, inputs trained Faster R-CNN model
In, export target category, confidence level and target position in the image.
Advantageous effects of the invention:
First, the present invention proposes a kind of based on depth information benefit on the basis of the convolutional neural networks model based on suggestion
Full target detection model, improved Faster R-CNN is added to a depth information channel, by color image and depth map
CNN as passing through structure respectively carries out feature extraction, and two CNN are using structure in parallel, then by original color image
Feature Mapping and depth image Feature Mapping carry out fused in tandem, obtain final characteristics of image, compared with original algorithm, this hair
Bright obtained characteristics of image is more abundant, the detailed information supplemented with vehicle, and not will increase time overhead, meets and improves again
The requirement of target detection under miscellaneous scene.
Second, the present invention is by increasing difficult sample Mining Strategy in the training stage, so that model is on the original basis more
Difficult sample is paid close attention to, the background of vehicle and doubtful vehicle is preferably distinguished, achievees the purpose that improve accuracy;
Third, the present invention extract the Faster R-CNN algorithm of suggestion candidate frame in real-time using shared convolutional network
On have been significantly improved, which has abandoned traditional region proposed algorithm, is mentioned using the convolutional layer in depth network
Candidate frame is taken, plenty of time expense has been saved.
Detailed description of the invention
Fig. 1 is the flow diagram of specific embodiment of the invention method.
Fig. 2 is the training flow chart of improved Faster R-CN algorithm in the specific embodiment of the invention.
Specific embodiment
The invention will be further described below in conjunction with the accompanying drawings.Following embodiment is only used for clearly illustrating the present invention
Technical solution, and not intended to limit the protection scope of the present invention.
Present invention aims at a kind of Vehicular video object detection method based on deep learning is proposed, in Faster
On the basis of R-CNN, the Feature Mapping of depth image is added to supplement Vehicle Detail information, selects and extracts color image feature
Identical convolutional neural networks, color image channel use structure in parallel with depth image channel, and the feature extracted is passed through
Fused in tandem obtains final RGB-D feature, and difficult sample Mining Strategy is added in training, improves algorithm in complicated traffic field
To the detection accuracy of Small object and difficult target in scape.
It is as shown in Figure 1 the method flow diagram of the specific embodiment of the invention.
Can be based on the training set sample set and test set sample obtained in advance when implementing the method for the present invention, it can also
To make training set and test set according to demand.In the present embodiment, training sample set and test are constructed using KITTI data set
Sample set includes the following steps 1: using the format and evaluation algorithms tool of PASCAL VOC data set.Firstly, conversion KITTI
Classification: a total of 20 classifications of PASCAL VOC, in urban transportation scene, emphasis test object be vehicle, pedestrian, traffic
Mark, therefore data set is divided into above-mentioned 3 kinds of classifications;Secondly, conversion markup information: xml is converted from txt by mark file,
Remove the other information in mark, leaves behind 3 classes;Finally, generating training verifying collection and test set.
As described in Figure 1, the method for the present invention includes the following steps:
Step 2) constructs a kind of improved Faster R-CNN model, which combines region and suggest network
(Regional Proposal Network, RPN) and Fast R-CNN network;
2.1) convolutional neural networks (Convolutional Neural Networks, CNN)
Firstly, the pixel under depth coordinate is snapped under color coordinate;CNN chooses the net of feature extraction in ZF model
Network, the identical CNN of two structures is carried out parallel connection, and (original color image channel is channel 1, and depth image channel in parallel is
Channel 2);After two class images pass through CNN feature extraction, characteristic pattern size is that (h, w respectively indicate characteristic pattern to hwc here
High, wide, c is tri- channels RGB), Fusion Features are carried out using color image feature and depth image feature as two channels, are melted
Characteristic pattern size after conjunction is 2hwc;
2.2) region suggests that network RPN includes one 3 × 3 convolutional layer and two 1 × 1 parallel-convolution layers;
By the convolutional layer of fused convolution Feature Mapping input 3 × 3, as unit of in the Feature Mapping of input by pixel
A small network is slided, 3 scales and 3 length-width ratios are respectively adopted in the present embodiment, then each sliding position generates k=3 × 3
The anchor point of=9 different scales then generates hwk anchor point in total, obtains hwk rectangle candidate frame;
Two 1 × 1 parallel-convolution layers carry out position recurrence to upper one layer of anchor point and front and back scape judges, export anchor respectively
The front and back scape confidence level of point and candidate frame position.Candidate frame position includes candidate frame center point coordinate x and y, and width w ' and height
H ' totally four parameters;
2.2) 2.1) resulting rectangle candidate frame is filtered out to the predetermined quantity for meeting preset condition according to preset condition
Region.Descending sort is carried out according to the score of softmax to resulting rectangle candidate frame in the present embodiment, retains preceding 2000 areas
Domain, further with non-maxima suppression algorithm (Non-Maximum Suppression, NMS), the prospect confidence level of filtering out is most
High preceding 300 regions, obtain final region set of suggestions C;
2.3) Fast R-CNN is made of two pond ROI layers, a full articulamentum and two full articulamentums in parallel, point
The confidence level for not exporting the region and the candidate frame position after frame recurrence;
Pooling layers of ROI carry out pondization operation, ROI to region set of suggestions C and fused convolution Feature Mapping
ROI is mapped to the corresponding position of Feature Mapping by the pooling layers of image according to input, is phase by the region division after mapping
With the sections of size, maximum pondization operation is carried out to each section;
Full articulamentum merges pooling layers of ROI of output result, recently enters two full articulamentums in parallel,
Territorial classification is carried out to candidate frame and frame returns, exports the position of target and its classification, confidence level in image;
Step 3) constructs the cost function of training RPN network and the cost function of training Fast R-CNN network:
The cost function of training RPN network in the present embodiment are as follows:
Wherein, the friendship of anchor point and ground truth (i.e. calibrated truthful data) and than (Intersection over
Union, IoU) it is maximum or be designated as positive sample, P not less than 0.7iFor forecast confidence;For mark value, positive sample is indicated when taking 1
This, indicates negative sample when taking 0;The index of i expression anchor point;NclsFor anchor point total quantity;NregFor the quantity of positive sample;tiFor prediction
Anchor point bounding box correction value;For actual anchor point bounding box correction value;LclsFor cost of classifying;LregGeneration is returned for frame
Valence;λ is balance weight;
The cost function of training Fast R-CNN network in the present embodiment are as follows:
L(p,u,tu, v) and=Lcls(p,u)+λ[u≥1]Lreg(tu,v)
Wherein, u is u class;tuFor the correction value of u class frame regression forecasting;V is actual correction value;LclsFor generation of classifying
Valence;LregCost is returned for frame;λ is balance weight;
Step 4) passes through the standard variance from setting using the ZF model training of standard and the parameters of trim network
Weight, which is extracted, in zero-mean gaussian distribution carrys out all mew layers of random initializtion;
Step 5) utilizes back-propagation algorithm and stochastic gradient descent algorithm, using to two nets of RPN and Fast R-CNN
The mode of network alternating training is trained model, is sequentially adjusted in the weight of every layer of neural network, the initial learning rate of network is set as
0.01, minimum learning rate is set as 0.0001, and momentum is set as 0.9, and weight attenuation coefficient is that 0.0005, Dropout value is set as
0.5, the specific steps are as follows:
(1) using back-propagation algorithm and stochastic gradient algorithm's training RPN model, the stage iteration 80000 times;
(2) input of the candidate frame for using RPN to generate as Fast R-CNN, and stand-alone training is carried out, the stage iteration
40000 times;
(3) RPN network structure is initialized using the result in (2), fixed shared convolutional layer is (by shared convolutional layer
Learning rate be set as 0), update RPN network parameter, the stage iteration 80000 times;
(4) fixed shared convolutional layer (setting 0 for the learning rate of shared convolutional layer), finely tunes Fast R-CNN network knot
Structure updates the parameter of its full articulamentum, the stage iteration 40000 times;
Step 6) the Faster R-CNN model good using training set test initial training, hardly possible sample according to the present invention are sentenced
Other formula filters out difficult sample;
The difficult sample generated in step 6) is added in training set step 7), is trained again to network, repeats step
5), so that Strengthens network finally obtains optimal Faster R-CNN model to the discriminating power of difficult sample;Training process can join
See Fig. 2.
Step 8) handles the Vehicular video image acquired in practice, inputs trained Faster R-CNN model
In, export target category, confidence level and target position in the image.
The present invention can fully consider Small object missing inspection problem existing for Faster R-CNN algorithm, pass through depth image spy
Sign fusion and difficult sample method for digging, improve the accuracy rate of vehicle identification in vehicles in complex traffic scene.
The algorithm of target detection based on convolutional neural networks that the present invention uses can be the flexible training data the case where
Under, learn effective feature according to different demands to complete specific Detection task.R-CNN algorithm be based on candidate frame suggestion with
A kind of algorithm of target detection that convolutional neural networks combine, since the large number of suggestion that region proposed algorithm generates is candidate
Frame and biggish time overhead, the algorithm still have biggish room for promotion in terms of real-time and accuracy.Utilize shared volume
Product network has been significantly improved in real-time to extract the Faster R-CNN algorithm of suggestion candidate frame, which abandons
Traditional region proposed algorithm, extracts candidate frame using the convolutional layer in depth network, has saved plenty of time expense, but
In the more and more complex scene of Small object, the case where missing inspection, is more serious, still there is biggish room for improvement.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, without departing from the technical principles of the invention, several improvement and deformations can also be made, these improvement and deformations
Also it should be regarded as protection scope of the present invention.
Claims (10)
1. a kind of Vehicular video object detection method based on deep learning, characterized in that include the following steps:
Step 1) snaps to the pixel under depth coordinate under color coordinate;Again by depth image and color image each by
CNN carry out feature extraction, and by the characteristic pattern that respective convolutional layer exports carried out on channel dimension fused in tandem obtain it is final
RGB-D feature is as the convolution Feature Mapping after convolution;
Construct region and suggest network RPN, the region suggest network RPN include one 3 × 3 convolutional layer and two 1 × 1 and
Row convolutional layer;By the convolutional layer of fused convolution Feature Mapping input 3 × 3, with pixel for singly in the Feature Mapping of input
The network of default size is slided in position, then each sliding position generates the anchor point of particular dimensions;
The parallel-convolution layer that the anchor point of generation inputs two 1 × 1 is subjected to position recurrence and the judgement of front and back scape, exports anchor point respectively
Front and back scape confidence level and all candidate frame positions and to select in frame screening to meet after resulting rectangle according to preset condition specific
The region of the preset quantity of condition obtains final region set of suggestions C;
Step 2) constructs Fast R-CNN model:
The Fast R-CNN model is made of two pond ROI layers, a full articulamentum and two full articulamentums in parallel, point
The confidence level for not exporting the region and the candidate frame position after frame recurrence;Fused convolution feature is inputted into Fast
R-CNN model exports the position of target and its classification and confidence level in image;
Step 3): the cost function of training RPN network and the cost function of training Fast R-CNN network are constructed;
Step 4) is equal by zero of the standard variance from setting using the ZF model training of standard and the parameters of trim network
Weight is extracted in value Gaussian Profile carrys out all mew layers of random initializtion;
Step 5) utilizes back-propagation algorithm and stochastic gradient descent algorithm, hands over using to two networks of RPN and Fast R-CNN
Model is trained for trained mode, the weight of every layer of neural network is sequentially adjusted according to pre-set parameter;
Step 6) the Faster R-CNN model good using the training set test initial training being obtained ahead of time, according to sentencing for difficult sample
Other formula filters out difficult sample;
The difficult sample generated in step 6) is added in training set step 7), is trained again to network, repeats step 5)-step
It is rapid 7), obtain optimal Faster R-CNN model;
Step 8) handles the Vehicular video image acquired in practice, inputs in trained Faster R-CNN model,
Export target category, confidence level and target position in the image.
2. a kind of Vehicular video object detection method based on deep learning according to claim 1, characterized in that described
The convolution Feature Mapping that RGB-D feature described in step 2) is shared as RPN and Fast R-CNN, matrix form are as follows:
Wherein, i, j, k are intermediate variable, i~[0, h-1], j~[0, w-1 [, k~[0,2c-1], h is characterized the height of figure, and w is
The width of characteristic pattern, c are tri- channels RGB;YRGB(i, j, k) is the characteristics of image after Tandem;Ydepth(i, j, k-c) is color
Color characteristics of image;Ymerge(i, j, k) is depth image feature.
3. a kind of Vehicular video object detection method based on deep learning according to claim 1, characterized in that described
The cost function of training RPN network are as follows:
Wherein, it is designated as positive sample by the friendship with calibrated truthful data and than maximum or not less than 0.7 anchor point, PiFor prediction
Confidence level;For mark value, positive sample is indicated when taking 1, indicates negative sample when taking 0;The index of i expression anchor point;NclsFor anchor point
Total quantity;NregFor the quantity of positive sample;tiFor the anchor point bounding box correction value of prediction;For the amendment of actual anchor point bounding box
Value;LclsFor cost of classifying;LregCost is returned for frame;λ is balance weight.
4. a kind of Vehicular video object detection method based on deep learning according to claim 1, characterized in that described
The cost function of training Fast R-CNN network are as follows:
L(p,u,tu, v) and=Lcls(p,u)+λ[u≥1]Lreg(tu,v)
Wherein, u is u class;tuFor the correction value of u class frame regression forecasting;V is actual correction value;LregGeneration is returned for frame
Valence, p are classification prediction results.
5. a kind of Vehicular video object detection method based on deep learning according to claim 1, characterized in that described
In step 6), the hardly possible sample discriminant function is as follows:
L (o, p)=LIoU(o)+Lscore(p),
Lscore(p)=(1-p),
Wherein, LIoUFor frame error;LscoreFor error in classification;O is the intersection rate of sample and target;K is to be to the sensitivity of threshold value
Number;The value range of o and p is 0~1.
6. a kind of Vehicular video object detection method based on deep learning according to claim 1, characterized in that step
5) specific step is as follows:
(1) using back-propagation algorithm and stochastic gradient algorithm's training RPN model, the stage iteration 80000 times;
(2) input of the candidate frame for using RPN to generate as Fast R-CNN, and stand-alone training is carried out, the stage iteration 40000
It is secondary;
(3) RPN network structure is initialized using the result in (2), fixed shared convolutional layer is (by shared convolutional layer
Habit rate is set as 0), updating the parameter of RPN network, the stage iteration 80000 times;
(4) fixed shared convolutional layer (setting 0 for the learning rate of shared convolutional layer), finely tunes Fast R-CNN network structure, more
The parameter of its new full articulamentum, the stage iteration 40000 times.
7. a kind of Vehicular video object detection method based on deep learning according to claim 1, characterized in that step
5) parameter setting includes that the initial learning rate of network is set as 0.01 in, and minimum learning rate is set as 0.0001, and momentum is set as 0.9, power
Weight attenuation coefficient is that 0.0005, Dropout value is set as 0.5.
8. a kind of Vehicular video object detection method based on deep learning according to claim 1, characterized in that in advance
The method for obtaining training set and test set includes the following steps:
Training sample set and test sample collection are constructed using KITTI data set;
According to the classification of PASCAL VOC format conversion KITTI, KITTI data set is divided into 3 type of vehicle, pedestrian and traffic
Not;
Conversion markup information: xml is converted from txt by mark file, removes the other information in mark, leaves behind 3 classes;Most
Afterwards, training verifying collection and test set are generated.
9. a kind of Vehicular video object detection method based on deep learning according to claim 1, characterized in that screening
The method for meeting the region of the preset quantity of specified conditions out is as follows:
Resulting rectangle candidate frame is subjected to descending sort according to the score of softmax, retains preceding 2000 regions, further
The highest preceding certain amount of region of prospect confidence level is filtered out with non-maxima suppression algorithm.
10. a kind of Vehicular video object detection method based on deep learning according to claim 1, characterized in that step
Rapid 4) the described standard variance set is 0.01.
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910185300.4A CN109977812B (en) | 2019-03-12 | 2019-03-12 | Vehicle-mounted video target detection method based on deep learning |
PCT/CN2019/092749 WO2020181685A1 (en) | 2019-03-12 | 2019-06-25 | Vehicle-mounted video target detection method based on deep learning |
JP2021502766A JP7120689B2 (en) | 2019-03-12 | 2019-06-25 | In-Vehicle Video Target Detection Method Based on Deep Learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910185300.4A CN109977812B (en) | 2019-03-12 | 2019-03-12 | Vehicle-mounted video target detection method based on deep learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109977812A true CN109977812A (en) | 2019-07-05 |
CN109977812B CN109977812B (en) | 2023-02-24 |
Family
ID=67078633
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910185300.4A Active CN109977812B (en) | 2019-03-12 | 2019-03-12 | Vehicle-mounted video target detection method based on deep learning |
Country Status (3)
Country | Link |
---|---|
JP (1) | JP7120689B2 (en) |
CN (1) | CN109977812B (en) |
WO (1) | WO2020181685A1 (en) |
Cited By (46)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110399884A (en) * | 2019-07-10 | 2019-11-01 | 浙江理工大学 | A kind of adaptive anchor frame model vehicle checking method of Fusion Features |
CN110414389A (en) * | 2019-07-12 | 2019-11-05 | 黑龙江御林湾科技有限公司 | A kind of object detection method of the fast area search based on deep learning |
CN110464611A (en) * | 2019-07-23 | 2019-11-19 | 苏州国科视清医疗科技有限公司 | A kind of digitlization amblyopia enhancing training device and system and its related algorithm |
CN110503112A (en) * | 2019-08-27 | 2019-11-26 | 电子科技大学 | A kind of small target deteection of Enhanced feature study and recognition methods |
CN110689021A (en) * | 2019-10-17 | 2020-01-14 | 哈尔滨理工大学 | Real-time target detection method in low-visibility environment based on deep learning |
CN110743818A (en) * | 2019-11-29 | 2020-02-04 | 苏州嘉诺环境工程有限公司 | Garbage sorting system and garbage sorting method based on vision and deep learning |
CN110826391A (en) * | 2019-09-10 | 2020-02-21 | 中国三峡建设管理有限公司 | Bleeding area detection method, bleeding area detection system, computer device and storage medium |
CN111091144A (en) * | 2019-11-27 | 2020-05-01 | 云南电网有限责任公司电力科学研究院 | Image feature point matching method and device based on depth pseudo-twin network |
CN111104903A (en) * | 2019-12-19 | 2020-05-05 | 南京邮电大学 | Depth perception traffic scene multi-target detection method and system |
CN111104885A (en) * | 2019-12-10 | 2020-05-05 | 南京邮电大学 | Vehicle identification method based on video deep learning |
CN111145239A (en) * | 2019-12-30 | 2020-05-12 | 南京航空航天大学 | Aircraft fuel tank redundancy automatic detection method based on deep learning |
CN111182491A (en) * | 2019-12-31 | 2020-05-19 | 淮安中科晶上智能网联研究院有限公司 | Radio frequency tomography-based equipment-free target positioning method and device |
CN111291747A (en) * | 2020-01-10 | 2020-06-16 | 大连理工大学 | Depth map-based color small target detection method in complex scene |
CN111291820A (en) * | 2020-02-19 | 2020-06-16 | 中国电子科技集团公司第二十八研究所 | Target detection method combining positioning information and classification information |
CN111292349A (en) * | 2020-01-17 | 2020-06-16 | 北京大学深圳研究生院 | Data enhancement method for target detection based on fusion of recommendation candidate boxes |
CN111310850A (en) * | 2020-03-02 | 2020-06-19 | 杭州雄迈集成电路技术股份有限公司 | License plate detection model construction method and system and license plate detection method and system |
CN111310828A (en) * | 2020-02-14 | 2020-06-19 | 开易(北京)科技有限公司 | Target detection model fine-tuning method and device for ADAS scene |
CN111310607A (en) * | 2020-01-22 | 2020-06-19 | 交通运输部公路科学研究所 | Highway safety risk identification method and system based on computer vision and artificial intelligence |
CN111310660A (en) * | 2020-02-14 | 2020-06-19 | 开易(北京)科技有限公司 | Target detection false alarm suppression method and device for ADAS scene |
CN111444973A (en) * | 2020-03-31 | 2020-07-24 | 西安交通大学 | Method for detecting commodities on unmanned retail shopping table |
CN111444816A (en) * | 2020-01-14 | 2020-07-24 | 北京银河信通科技有限公司 | Multi-scale dense pedestrian detection method based on fast RCNN |
CN111507738A (en) * | 2020-05-04 | 2020-08-07 | 武汉积墨包装印刷有限公司 | Ink tracing and recycling process method based on block chain and 5G communication |
CN111666839A (en) * | 2020-05-25 | 2020-09-15 | 东华大学 | Road pedestrian detection system based on improved Faster RCNN |
CN111724392A (en) * | 2020-05-25 | 2020-09-29 | 浙江工业大学 | Data processing method for deep learning feature attention transfer |
CN111738164A (en) * | 2020-06-24 | 2020-10-02 | 广西计算中心有限责任公司 | Pedestrian detection method based on deep learning |
CN111881932A (en) * | 2020-06-11 | 2020-11-03 | 中国人民解放军战略支援部队信息工程大学 | FasterRCNN target detection algorithm for military aircraft |
CN112016449A (en) * | 2020-08-27 | 2020-12-01 | 西华大学 | Vehicle identification and detection method based on deep learning |
CN112085126A (en) * | 2020-09-30 | 2020-12-15 | 浙江大学 | Single-sample target detection method focusing on classification task |
CN112183485A (en) * | 2020-11-02 | 2021-01-05 | 北京信息科技大学 | Deep learning-based traffic cone detection positioning method and system and storage medium |
CN112446429A (en) * | 2020-11-27 | 2021-03-05 | 广东电网有限责任公司肇庆供电局 | CGAN (Carrier grade Access network) -based routing inspection image data small sample expansion method |
CN112668585A (en) * | 2020-11-26 | 2021-04-16 | 厦门大学 | Object identification and positioning method in dynamic environment |
CN112750194A (en) * | 2020-05-15 | 2021-05-04 | 奕目(上海)科技有限公司 | Obstacle avoidance method and device for unmanned automobile |
CN112766176A (en) * | 2021-01-21 | 2021-05-07 | 深圳市安软科技股份有限公司 | Training method of lightweight convolutional neural network and face attribute recognition method |
CN112818932A (en) * | 2021-02-26 | 2021-05-18 | 北京车和家信息技术有限公司 | Image processing method, obstacle detection device, medium, and vehicle |
CN112964693A (en) * | 2021-02-19 | 2021-06-15 | 山东捷讯通信技术有限公司 | Raman spectrum band region segmentation method |
CN113052184A (en) * | 2021-03-12 | 2021-06-29 | 电子科技大学 | Target detection method based on two-stage local feature alignment |
CN113128564A (en) * | 2021-03-23 | 2021-07-16 | 武汉泰沃滋信息技术有限公司 | Typical target detection method and system based on deep learning under complex background |
CN113159198A (en) * | 2021-04-27 | 2021-07-23 | 上海芯物科技有限公司 | Target detection method, device, equipment and storage medium |
CN113177133A (en) * | 2021-04-23 | 2021-07-27 | 深圳依时货拉拉科技有限公司 | Image retrieval method, device, equipment and storage medium |
CN113173502A (en) * | 2021-01-15 | 2021-07-27 | 福建电子口岸股份有限公司 | Anti-collision method and system based on laser visual fusion and deep learning |
CN113240611A (en) * | 2021-05-28 | 2021-08-10 | 中建材信息技术股份有限公司 | Foreign matter detection method based on picture sequence |
CN113569702A (en) * | 2021-07-23 | 2021-10-29 | 闽江学院 | Deep learning-based truck single-tire and double-tire identification method |
CN113591668A (en) * | 2021-07-26 | 2021-11-02 | 南京大学 | Wide-area unknown dam automatic detection method using deep learning and spatial analysis |
CN114220053A (en) * | 2021-12-15 | 2022-03-22 | 北京建筑大学 | Unmanned aerial vehicle video vehicle retrieval method based on vehicle feature matching |
WO2022205329A1 (en) * | 2021-04-01 | 2022-10-06 | 京东方科技集团股份有限公司 | Object detection method, object detection apparatus, and object detection system |
CN115529475A (en) * | 2021-12-29 | 2022-12-27 | 北京智美互联科技有限公司 | Method and system for detecting video flow content and controlling wind |
Families Citing this family (196)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112183274A (en) * | 2020-09-21 | 2021-01-05 | 深圳中兴网信科技有限公司 | Mud car detection method and computer-readable storage medium |
CN112132804B (en) * | 2020-09-22 | 2023-10-31 | 苏州巨能图像检测技术有限公司 | Anti-lifting detection method for hub of hub card |
CN112132042B (en) * | 2020-09-24 | 2023-08-01 | 西安电子科技大学 | SAR image target detection method based on contrast domain adaptation |
CN112233175B (en) * | 2020-09-24 | 2023-10-24 | 西安交通大学 | Chip positioning method and integrated positioning platform based on YOLOv3-tiny algorithm |
CN112164017B (en) * | 2020-09-27 | 2023-11-17 | 中国兵器工业集团第二一四研究所苏州研发中心 | Polarization colorization method based on deep learning |
CN112115913B (en) * | 2020-09-28 | 2023-08-25 | 杭州海康威视数字技术股份有限公司 | Image processing method, device and equipment and storage medium |
CN112364687A (en) * | 2020-09-29 | 2021-02-12 | 上善智城(苏州)信息科技有限公司 | Improved Faster R-CNN gas station electrostatic sign identification method and system |
CN112580424B (en) * | 2020-09-29 | 2023-08-11 | 长安大学 | Polarization characteristic multi-scale pooling classification algorithm for complex vehicle-road environment |
CN112541389B (en) * | 2020-09-29 | 2023-08-22 | 西安交通大学 | Transmission line fault detection method based on EfficientDet network |
CN112330591B (en) * | 2020-09-30 | 2023-01-24 | 中国国家铁路集团有限公司 | Steel rail surface defect detection method and device capable of achieving sample-less learning |
CN112215128B (en) * | 2020-10-09 | 2024-04-05 | 武汉理工大学 | FCOS-fused R-CNN urban road environment recognition method and device |
CN112233090B (en) * | 2020-10-15 | 2023-05-30 | 浙江工商大学 | Film flaw detection method based on improved attention mechanism |
CN112232214A (en) * | 2020-10-16 | 2021-01-15 | 天津大学 | Real-time target detection method based on depth feature fusion and attention mechanism |
CN112329558B (en) * | 2020-10-22 | 2022-10-25 | 上海交通大学 | FeO content prediction method based on sintering machine tail section video |
CN112329588B (en) * | 2020-10-30 | 2024-01-05 | 中海石油(中国)有限公司 | Pipeline fault detection method based on Faster R-CNN |
CN112287854A (en) * | 2020-11-02 | 2021-01-29 | 湖北大学 | Building indoor personnel detection method and system based on deep neural network |
CN112200803B (en) * | 2020-11-04 | 2023-10-10 | 成都朴华科技有限公司 | Sperm nucleoprotein maturity detection method and device |
CN112380962A (en) * | 2020-11-11 | 2021-02-19 | 成都摘果子科技有限公司 | Animal image identification method and system based on deep learning |
CN112329871B (en) * | 2020-11-11 | 2022-03-08 | 河北工业大学 | Pulmonary nodule detection method based on self-correction convolution and channel attention mechanism |
CN112381005A (en) * | 2020-11-17 | 2021-02-19 | 温州大学 | Safety helmet detection system for complex scene |
CN112395987B (en) * | 2020-11-18 | 2023-07-28 | 西安电子科技大学 | SAR image target detection method based on unsupervised domain adaptive CNN |
CN112580778A (en) * | 2020-11-25 | 2021-03-30 | 江苏集萃未来城市应用技术研究所有限公司 | Job worker mobile phone use detection method based on YOLOv5 and Pose-animation |
CN112434740A (en) * | 2020-11-26 | 2021-03-02 | 西北大学 | Depth learning-based Qin tomb warriors fragment classification method |
CN112418114A (en) * | 2020-11-27 | 2021-02-26 | 广州华多网络科技有限公司 | Time sequence behavior detection and response method and device, equipment and medium |
CN112396017B (en) * | 2020-11-27 | 2023-04-07 | 上海建科工程咨询有限公司 | Engineering potential safety hazard identification method and system based on image identification |
CN112418117B (en) * | 2020-11-27 | 2023-05-12 | 北京工商大学 | Small target detection method based on unmanned aerial vehicle image |
CN112434745B (en) * | 2020-11-27 | 2023-01-24 | 西安电子科技大学 | Occlusion target detection and identification method based on multi-source cognitive fusion |
CN112528782B (en) * | 2020-11-30 | 2024-02-23 | 北京农业信息技术研究中心 | Underwater fish target detection method and device |
CN112508091B (en) * | 2020-12-03 | 2024-01-19 | 大连海事大学 | Low-quality image classification method based on convolutional neural network |
CN112507862B (en) * | 2020-12-04 | 2023-05-26 | 东风汽车集团有限公司 | Vehicle orientation detection method and system based on multitasking convolutional neural network |
CN112464851A (en) * | 2020-12-08 | 2021-03-09 | 国网陕西省电力公司电力科学研究院 | Smart power grid foreign matter intrusion detection method and system based on visual perception |
CN112488229B (en) * | 2020-12-10 | 2024-04-05 | 西安交通大学 | Domain self-adaptive unsupervised target detection method based on feature separation and alignment |
CN112528862B (en) * | 2020-12-10 | 2023-02-10 | 西安电子科技大学 | Remote sensing image target detection method based on improved cross entropy loss function |
CN112598165B (en) * | 2020-12-11 | 2023-09-26 | 湖南大学 | Urban functional area transfer flow prediction method and device based on private car data |
CN112580647A (en) * | 2020-12-11 | 2021-03-30 | 湖北工业大学 | Stacked object oriented identification method and system |
CN112507898B (en) * | 2020-12-14 | 2022-07-01 | 重庆邮电大学 | Multi-modal dynamic gesture recognition method based on lightweight 3D residual error network and TCN |
CN112488066A (en) * | 2020-12-18 | 2021-03-12 | 航天时代飞鸿技术有限公司 | Real-time target detection method under unmanned aerial vehicle multi-machine cooperative reconnaissance |
CN112528995B (en) * | 2020-12-22 | 2023-08-04 | 北京百度网讯科技有限公司 | Method for training target detection model, target detection method and device |
CN112633177A (en) * | 2020-12-24 | 2021-04-09 | 浙江大学 | Lane line detection segmentation method based on attention space convolution neural network |
CN112668696A (en) * | 2020-12-25 | 2021-04-16 | 杭州中科先进技术研究院有限公司 | Unmanned aerial vehicle power grid inspection method and system based on embedded deep learning |
CN112699782A (en) * | 2020-12-29 | 2021-04-23 | 杭州电子科技大学 | Radar HRRP target identification method based on N2N and Bert |
CN112861849B (en) * | 2020-12-29 | 2023-01-10 | 北京航空航天大学 | Tissue identification method in spinal deformity correction surgery |
CN112712503B (en) * | 2020-12-30 | 2023-05-02 | 厦门福信光电集成有限公司 | Display panel appearance detection method based on deep learning |
CN112651458B (en) * | 2020-12-31 | 2024-04-02 | 深圳云天励飞技术股份有限公司 | Classification model training method and device, electronic equipment and storage medium |
CN112686188B (en) * | 2021-01-05 | 2024-02-06 | 西安理工大学 | Front windshield and driver area positioning method based on deep learning method |
CN112668536B (en) * | 2021-01-06 | 2023-08-25 | 北京理工大学 | Lightweight rotary target detection and identification method based on airborne photoelectric video |
CN113011417B (en) * | 2021-01-08 | 2023-02-10 | 湖南大学 | Target matching method based on intersection ratio coverage rate loss and repositioning strategy |
CN112669312A (en) * | 2021-01-12 | 2021-04-16 | 中国计量大学 | Chest radiography pneumonia detection method and system based on depth feature symmetric fusion |
CN112835008B (en) * | 2021-01-12 | 2022-03-04 | 西安电子科技大学 | High-resolution range profile target identification method based on attitude self-adaptive convolutional network |
CN112733742B (en) * | 2021-01-14 | 2022-02-01 | 哈尔滨市科佳通用机电股份有限公司 | Deep learning-based fault detection method for round pin of lower pull rod of railway wagon |
CN112733741A (en) * | 2021-01-14 | 2021-04-30 | 苏州挚途科技有限公司 | Traffic signboard identification method and device and electronic equipment |
CN112784723A (en) * | 2021-01-14 | 2021-05-11 | 金陵科技学院 | Road traffic safety protection model based on IFast-RCNN algorithm |
CN112861932B (en) * | 2021-01-21 | 2024-02-02 | 上海应用技术大学 | Rail plate crack detection method |
CN112766170B (en) * | 2021-01-21 | 2024-04-16 | 广西财经学院 | Self-adaptive segmentation detection method and device based on cluster unmanned aerial vehicle image |
CN112766188A (en) * | 2021-01-25 | 2021-05-07 | 浙江科技学院 | Small-target pedestrian detection method based on improved YOLO algorithm |
CN112949849B (en) * | 2021-01-27 | 2024-03-26 | 武汉星巡智能科技有限公司 | Method and device for optimizing intelligent camera detection model by adopting edge calculation |
CN112818837B (en) * | 2021-01-29 | 2022-11-11 | 山东大学 | Aerial photography vehicle weight recognition method based on attitude correction and difficult sample perception |
CN112801187B (en) * | 2021-01-29 | 2023-01-31 | 广东省科学院智能制造研究所 | Hyperspectral data analysis method and system based on attention mechanism and ensemble learning |
CN112766274B (en) * | 2021-02-01 | 2023-07-07 | 长沙市盛唐科技有限公司 | Water gauge image water level automatic reading method and system based on Mask RCNN algorithm |
CN112861700B (en) * | 2021-02-03 | 2023-11-03 | 西安仁义智机电科技有限公司 | Lane network identification model establishment and vehicle speed detection method based on deep Labv3+ |
CN112802006B (en) * | 2021-02-07 | 2024-03-22 | 南通大学 | Edge calculation motor oil stain identification method based on deep learning |
CN112556682B (en) * | 2021-02-07 | 2023-06-23 | 天津蓝鳍海洋工程有限公司 | Automatic detection algorithm for underwater composite sensor target |
CN112986210B (en) * | 2021-02-10 | 2021-12-17 | 四川大学 | Scale-adaptive microbial Raman spectrum detection method and system |
CN113033609B (en) * | 2021-02-16 | 2022-11-29 | 浙江大学 | SAR image classification method based on multitask DCGAN |
CN112907621B (en) * | 2021-02-24 | 2023-02-14 | 华南理工大学 | Moving object extraction method based on difference and semantic information fusion |
CN112926652B (en) * | 2021-02-25 | 2023-10-24 | 青岛科技大学 | Fish fine granularity image recognition method based on deep learning |
CN112927264B (en) * | 2021-02-25 | 2022-12-16 | 华南理工大学 | Unmanned aerial vehicle tracking shooting system and RGBD tracking method thereof |
CN112926457B (en) * | 2021-02-26 | 2022-09-06 | 中国电子科技集团公司第二十八研究所 | SAR image recognition method based on fusion frequency domain and space domain network model |
CN112966747A (en) * | 2021-03-04 | 2021-06-15 | 北京联合大学 | Improved vehicle detection method based on anchor-frame-free detection network |
CN112966598B (en) * | 2021-03-04 | 2022-08-30 | 河南大学 | Hyperspectral image classification method of dual-path small convolution network |
CN112837315B (en) * | 2021-03-05 | 2023-11-21 | 云南电网有限责任公司电力科学研究院 | Deep learning-based transmission line insulator defect detection method |
CN112966611A (en) * | 2021-03-09 | 2021-06-15 | 中国科学技术大学 | Energy trace noise self-adaption method of DWT attention mechanism |
CN113129225A (en) * | 2021-03-09 | 2021-07-16 | 西安理工大学 | Computed ghost imaging reconstruction recovery method based on Dense Net network |
CN113128335A (en) * | 2021-03-09 | 2021-07-16 | 西北大学 | Method, system and application for detecting, classifying and discovering micro-body paleontological fossil image |
CN113159021A (en) * | 2021-03-10 | 2021-07-23 | 国网河北省电力有限公司 | Text detection method based on context information |
CN113032612B (en) * | 2021-03-12 | 2023-04-11 | 西北大学 | Construction method of multi-target image retrieval model, retrieval method and device |
CN112990230B (en) * | 2021-03-12 | 2023-05-09 | 西安电子科技大学 | Spectral image compression reconstruction method based on two-stage grouping attention residual error mechanism |
CN113095152B (en) * | 2021-03-18 | 2023-08-22 | 西安交通大学 | Regression-based lane line detection method and system |
CN113011338B (en) * | 2021-03-19 | 2023-08-22 | 华南理工大学 | Lane line detection method and system |
CN113128563B (en) * | 2021-03-23 | 2023-11-17 | 武汉泰沃滋信息技术有限公司 | Method, device, equipment and storage medium for detecting high-speed engineering vehicle |
CN112990065B (en) * | 2021-03-31 | 2024-03-22 | 上海海事大学 | Vehicle classification detection method based on optimized YOLOv5 model |
CN113256507B (en) * | 2021-04-01 | 2023-11-21 | 南京信息工程大学 | Attention enhancement method for generating image aiming at binary flow data |
CN113077491B (en) * | 2021-04-02 | 2023-05-02 | 安徽大学 | RGBT target tracking method based on cross-modal sharing and specific representation form |
CN113076898B (en) * | 2021-04-09 | 2023-09-15 | 长安大学 | Traffic vehicle target detection method, device, equipment and readable storage medium |
CN113159159B (en) * | 2021-04-15 | 2023-09-29 | 东北大学 | Small sample image classification method based on improved CNN |
CN113095417B (en) * | 2021-04-16 | 2023-07-28 | 西安电子科技大学 | SAR target recognition method based on fusion graph convolution and convolution neural network |
CN113221668B (en) * | 2021-04-20 | 2023-04-07 | 西安翔迅科技有限责任公司 | Frame extraction method in wind generating set blade video monitoring |
CN113191235A (en) * | 2021-04-22 | 2021-07-30 | 上海东普信息科技有限公司 | Sundry detection method, device, equipment and storage medium |
CN113205026B (en) * | 2021-04-26 | 2022-08-16 | 武汉大学 | Improved vehicle type recognition method based on fast RCNN deep learning network |
CN113255737B (en) * | 2021-04-30 | 2023-08-08 | 超节点创新科技(深圳)有限公司 | Method for sorting baggage in folded package on civil aviation sorting line, electronic equipment and storage medium |
CN113221993B (en) * | 2021-05-06 | 2023-08-01 | 西安电子科技大学 | Large-view-field small-sample target detection method based on meta-learning and cross-stage hourglass |
CN113139497B (en) * | 2021-05-08 | 2023-04-28 | 广东工业大学 | System and method for identifying object on water surface and application based on 5G MEC |
CN113139615A (en) * | 2021-05-08 | 2021-07-20 | 北京联合大学 | Unmanned environment target detection method based on embedded equipment |
CN113327227B (en) * | 2021-05-10 | 2022-11-11 | 桂林理工大学 | MobileneetV 3-based wheat head rapid detection method |
CN113240017B (en) * | 2021-05-18 | 2023-09-12 | 西安理工大学 | Multispectral and panchromatic image classification method based on attention mechanism |
CN113269073B (en) * | 2021-05-19 | 2022-11-15 | 青岛科技大学 | Ship multi-target tracking method based on YOLO V5 algorithm |
CN113408584B (en) * | 2021-05-19 | 2022-07-26 | 成都理工大学 | RGB-D multi-modal feature fusion 3D target detection method |
CN113421222B (en) * | 2021-05-21 | 2023-06-23 | 西安科技大学 | Lightweight coal gangue target detection method |
CN113379761B (en) * | 2021-05-25 | 2023-04-28 | 重庆顺多利机车有限责任公司 | Linkage method and system of multiple AGVs and automatic doors based on artificial intelligence |
CN113343821B (en) * | 2021-05-31 | 2022-08-30 | 合肥工业大学 | Non-contact heart rate measurement method based on space-time attention network and input optimization |
CN113240039B (en) * | 2021-05-31 | 2023-08-15 | 西安电子科技大学 | Small sample target detection method and system based on spatial position feature re-weighting |
CN113255797B (en) * | 2021-06-02 | 2024-04-05 | 通号智慧城市研究设计院有限公司 | Dangerous goods detection method and system based on deep learning model |
CN113468967B (en) * | 2021-06-02 | 2023-08-18 | 北京邮电大学 | Attention mechanism-based lane line detection method, attention mechanism-based lane line detection device, attention mechanism-based lane line detection equipment and attention mechanism-based lane line detection medium |
CN113255682B (en) * | 2021-06-04 | 2021-11-16 | 浙江智慧视频安防创新中心有限公司 | Target detection system, method, device, equipment and medium |
CN113506317B (en) * | 2021-06-07 | 2022-04-22 | 北京百卓网络技术有限公司 | Multi-target tracking method based on Mask R-CNN and apparent feature fusion |
CN113362389B (en) * | 2021-06-08 | 2024-02-27 | 长安大学 | Shield tunnel deformation prediction method based on CNN-RNN coupling number-shape fusion |
CN113378918B (en) * | 2021-06-09 | 2022-06-07 | 武汉大学 | Insulator binding wire state detection method based on metric learning |
CN113378936B (en) * | 2021-06-11 | 2024-03-08 | 长沙军民先进技术研究有限公司 | Faster RCNN-based few-sample target detection method |
CN113343863B (en) * | 2021-06-11 | 2023-01-03 | 北京邮电大学 | Fusion characterization network model training method, fingerprint characterization method and equipment thereof |
CN113313058B (en) * | 2021-06-16 | 2022-08-02 | 北京航空航天大学 | Unmanned aerial vehicle aerial image target detection method based on self-adaptive model integration |
CN113421235B (en) * | 2021-06-17 | 2023-06-20 | 中国电子科技集团公司第四十一研究所 | Cigarette positioning device and method based on deep learning |
CN113239899A (en) * | 2021-06-17 | 2021-08-10 | 阿波罗智联(北京)科技有限公司 | Method for processing image and generating convolution kernel, road side equipment and cloud control platform |
CN113420643B (en) * | 2021-06-21 | 2023-02-10 | 西北工业大学 | Lightweight underwater target detection method based on depth separable cavity convolution |
CN113408423B (en) * | 2021-06-21 | 2023-09-05 | 西安工业大学 | Aquatic product target real-time detection method suitable for TX2 embedded platform |
CN113449738B (en) * | 2021-07-06 | 2023-06-23 | 国网信息通信产业集团有限公司 | Priori frame parameter self-adaptive improved FRC detection method based on sample characteristics |
CN113469071B (en) * | 2021-07-06 | 2024-03-29 | 西安科技大学 | Video detection method for foreign matters of coal conveying belt aiming at embedded equipment |
CN113361483B (en) * | 2021-07-07 | 2023-04-14 | 合肥英睿系统技术有限公司 | Traffic speed limit sign detection method, device, equipment and storage medium |
CN113449675B (en) * | 2021-07-12 | 2024-03-29 | 西安科技大学 | Method for detecting crossing of coal mine personnel |
CN113592906B (en) * | 2021-07-12 | 2024-02-13 | 华中科技大学 | Long video target tracking method and system based on annotation frame feature fusion |
CN113673323B (en) * | 2021-07-13 | 2023-10-27 | 中国船舶重工集团公司第七一五研究所 | Aquatic target identification method based on multi-deep learning model joint judgment system |
CN113591617B (en) * | 2021-07-14 | 2023-11-28 | 武汉理工大学 | Deep learning-based water surface small target detection and classification method |
CN113537098A (en) * | 2021-07-21 | 2021-10-22 | 北京航空航天大学 | Method for detecting and identifying impact pits in landing image |
CN113537105A (en) * | 2021-07-23 | 2021-10-22 | 北京经纬恒润科技股份有限公司 | Parking space detection method and device |
CN113534146B (en) * | 2021-07-26 | 2023-12-01 | 中国人民解放军海军航空大学 | Automatic detection method and system for radar video image target |
CN113674216A (en) * | 2021-07-27 | 2021-11-19 | 南京航空航天大学 | Subway tunnel disease detection method based on deep learning |
CN113537119B (en) * | 2021-07-28 | 2022-08-30 | 国网河南省电力公司电力科学研究院 | Transmission line connecting part detection method based on improved Yolov4-tiny |
CN113808202A (en) * | 2021-08-11 | 2021-12-17 | 浙江工商大学 | Multi-target detection and space positioning method and system thereof |
CN113569835A (en) * | 2021-08-16 | 2021-10-29 | 浙江广厦建设职业技术大学 | Water meter numerical value reading method based on target detection and segmentation identification |
CN113658131A (en) * | 2021-08-16 | 2021-11-16 | 东华大学 | Tour type ring spinning broken yarn detection method based on machine vision |
CN113643327B (en) * | 2021-08-18 | 2023-10-20 | 江西理工大学 | Nuclear correlation filtering target tracking method for response confidence coefficient multi-feature fusion |
CN113706496B (en) * | 2021-08-23 | 2024-04-12 | 中国飞机强度研究所 | Aircraft structure crack detection method based on deep learning model |
CN113689928B (en) * | 2021-08-24 | 2023-06-20 | 深圳平安智慧医健科技有限公司 | Recommended method, apparatus, device and storage medium for maintenance and prevention of illness |
CN113688734B (en) * | 2021-08-25 | 2023-09-22 | 燕山大学 | FPGA heterogeneous acceleration-based old people falling detection method |
CN113484908B (en) * | 2021-08-25 | 2023-07-14 | 成都理工大学 | Missing seismic data reconstruction method for deep learning network by combining partial convolution and attention mechanism |
CN113688740B (en) * | 2021-08-26 | 2024-02-27 | 燕山大学 | Indoor gesture detection method based on multi-sensor fusion vision |
CN113792774B (en) * | 2021-09-01 | 2024-01-12 | 西北工业大学 | Intelligent fusion sensing method for underwater targets |
CN113689470B (en) * | 2021-09-02 | 2023-08-11 | 重庆大学 | Pedestrian motion trail prediction method under multi-scene fusion |
CN113705716B (en) * | 2021-09-03 | 2023-10-10 | 北京百度网讯科技有限公司 | Image recognition model training method and device, cloud control platform and automatic driving vehicle |
CN113763235A (en) * | 2021-09-08 | 2021-12-07 | 北京琥珀创想科技有限公司 | Method for converting picture into scanning piece and intelligent mobile terminal |
CN113762200B (en) * | 2021-09-16 | 2023-06-30 | 深圳大学 | Mask detection method based on LFD |
CN113792684B (en) * | 2021-09-17 | 2024-03-29 | 中国科学技术大学 | Multi-mode visual flame detection method for fire-fighting robot under weak alignment condition |
CN113824658B (en) * | 2021-09-22 | 2023-06-20 | 西华大学 | Deep migration learning channel estimation method adopting DNSP scheme in OFDM system |
CN113780462B (en) * | 2021-09-24 | 2024-03-19 | 华中科技大学 | Vehicle detection network establishment method based on unmanned aerial vehicle aerial image and application thereof |
CN113705729A (en) * | 2021-09-27 | 2021-11-26 | 中原动力智能机器人有限公司 | Garbage classification model modeling method, garbage classification device and garbage classification medium |
CN113808123B (en) * | 2021-09-27 | 2024-03-29 | 杭州跨视科技有限公司 | Dynamic detection method for liquid medicine bag based on machine vision |
CN113807463B (en) * | 2021-09-28 | 2023-10-17 | 中电万维信息技术有限责任公司 | Method for detecting BI icon questions based on Faster-RCNN |
CN113947774A (en) * | 2021-10-08 | 2022-01-18 | 东北大学 | Lightweight vehicle target detection system |
CN114120246B (en) * | 2021-10-12 | 2024-04-16 | 吉林大学 | Front vehicle detection algorithm based on complex environment |
CN113850799A (en) * | 2021-10-14 | 2021-12-28 | 长春工业大学 | YOLOv 5-based trace DNA extraction workstation workpiece detection method |
CN113808128B (en) * | 2021-10-14 | 2023-07-28 | 河北工业大学 | Intelligent compaction whole process visualization control method based on relative coordinate positioning algorithm |
CN113792827B (en) * | 2021-11-18 | 2022-03-25 | 北京的卢深视科技有限公司 | Target object recognition method, electronic device, and computer-readable storage medium |
CN114092448B (en) * | 2021-11-22 | 2023-12-01 | 浙大城市学院 | Plug-in electrolytic capacitor mixed detection method based on deep learning |
CN114419925B (en) * | 2021-12-01 | 2022-11-04 | 合肥工业大学 | Vehicle-road cooperative collision-prevention early warning system and method |
CN113947766B (en) * | 2021-12-21 | 2022-04-22 | 之江实验室 | Real-time license plate detection method based on convolutional neural network |
CN114528911A (en) * | 2022-01-10 | 2022-05-24 | 西北大学 | Multi-label image classification method and model construction method and device for multi-branch structure |
CN114445689A (en) * | 2022-01-29 | 2022-05-06 | 福州大学 | Multi-scale weighted fusion target detection method and system guided by target prior information |
CN114519819B (en) * | 2022-02-10 | 2024-04-02 | 西北工业大学 | Remote sensing image target detection method based on global context awareness |
CN114529951B (en) * | 2022-02-22 | 2024-04-02 | 北京工业大学 | On-site fingerprint feature point extraction method based on deep learning |
CN114692487B (en) * | 2022-03-11 | 2023-05-26 | 中国电子科技集团公司第二十九研究所 | Electronic equipment maintenance spare part pre-casting method, device, equipment and storage medium |
CN114842220B (en) * | 2022-03-24 | 2024-02-27 | 西北工业大学 | Unmanned aerial vehicle visual positioning method based on multi-source image matching |
CN114743045B (en) * | 2022-03-31 | 2023-09-26 | 电子科技大学 | Small sample target detection method based on double-branch area suggestion network |
CN114882376B (en) * | 2022-05-06 | 2024-03-22 | 自然资源部第一海洋研究所 | Convolutional neural network remote sensing image target detection method based on optimal anchor point scale |
CN114913419B (en) * | 2022-05-10 | 2023-07-18 | 西南石油大学 | Intelligent parking target detection method and system |
CN114742822A (en) * | 2022-05-20 | 2022-07-12 | 青岛农业大学 | Construction method and application of strawberry identification and counting model |
CN115131622B (en) * | 2022-05-22 | 2024-03-29 | 北京工业大学 | Night open fire detection method based on video time sequence correlation |
CN115014748B (en) * | 2022-05-31 | 2023-05-23 | 南京林业大学 | Fault diagnosis method for seed cotton sorting spray valve |
CN114943922B (en) * | 2022-06-02 | 2024-04-02 | 浙大城市学院 | Machine examination suspicious behavior identification method based on deep learning |
CN114913587B (en) * | 2022-06-14 | 2024-02-13 | 合肥工业大学 | Non-contact heart rate measurement uncertainty quantization method based on Bayesian deep learning |
CN115050028B (en) * | 2022-06-15 | 2024-03-29 | 松立控股集团股份有限公司 | Small sample license plate detection method in severe weather |
CN114818838B (en) * | 2022-06-30 | 2022-09-13 | 中国科学院国家空间科学中心 | Low signal-to-noise ratio moving point target detection method based on pixel time domain distribution learning |
CN115273044B (en) * | 2022-07-15 | 2023-04-07 | 哈尔滨市科佳通用机电股份有限公司 | Vehicle door damage fault identification and detection method based on improved graph convolution network |
CN114982739A (en) * | 2022-07-18 | 2022-09-02 | 江苏合力四通智能科技股份有限公司 | Intelligent laser bird repelling device and method based on deep learning |
CN115393634B (en) * | 2022-08-11 | 2023-12-26 | 重庆邮电大学 | Small sample target real-time detection method based on migration learning strategy |
CN115294244B (en) * | 2022-08-11 | 2023-10-31 | 北京理工大学 | Honeycomb structure patterning self-adaptive filling method based on machine learning |
CN115331086B (en) * | 2022-08-17 | 2023-08-08 | 哈尔滨市科佳通用机电股份有限公司 | Brake shoe breakage and rivet loss fault detection method |
CN115359094B (en) * | 2022-09-05 | 2023-04-18 | 珠海安联锐视科技股份有限公司 | Moving target detection method based on deep learning |
CN115484410B (en) * | 2022-09-15 | 2023-11-24 | 天津大学 | Event camera video reconstruction method based on deep learning |
CN115578615B (en) * | 2022-10-31 | 2023-05-09 | 成都信息工程大学 | Night traffic sign image detection model building method based on deep learning |
CN115641510B (en) * | 2022-11-18 | 2023-08-08 | 中国人民解放军战略支援部队航天工程大学士官学校 | Remote sensing image ship detection and identification method |
CN115601688B (en) * | 2022-12-15 | 2023-02-21 | 中译文娱科技(青岛)有限公司 | Video main content detection method and system based on deep learning |
CN116385953B (en) * | 2023-01-11 | 2023-12-15 | 哈尔滨市科佳通用机电股份有限公司 | Railway wagon door hinge breaking fault image identification method |
CN116524017B (en) * | 2023-03-13 | 2023-09-19 | 明创慧远科技集团有限公司 | Underground detection, identification and positioning system for mine |
CN115953405B (en) * | 2023-03-14 | 2023-05-26 | 中国科学院计算机网络信息中心 | Bridge crack identification method and device for augmented reality equipment |
CN116403071B (en) * | 2023-03-23 | 2024-03-26 | 河海大学 | Method and device for detecting few-sample concrete defects based on feature reconstruction |
CN116106899B (en) * | 2023-04-14 | 2023-06-23 | 青岛杰瑞工控技术有限公司 | Port channel small target identification method based on machine learning |
CN116452878B (en) * | 2023-04-20 | 2024-02-02 | 广东工业大学 | Attendance checking method and system based on deep learning algorithm and binocular vision |
CN116434124B (en) * | 2023-06-13 | 2023-09-05 | 江西云眼视界科技股份有限公司 | Video motion enhancement detection method based on space-time filtering |
CN116778362B (en) * | 2023-06-21 | 2024-03-05 | 广东电网有限责任公司汕尾供电局 | Electric power tower acceptance component identification method based on field knowledge and deep learning |
CN116843907B (en) * | 2023-06-26 | 2024-02-13 | 中国信息通信研究院 | Enhancement and target detection method and system based on deep learning |
CN116503517B (en) * | 2023-06-27 | 2023-09-05 | 江西农业大学 | Method and system for generating image by long text |
CN116524474B (en) * | 2023-07-04 | 2023-09-15 | 武汉大学 | Vehicle target detection method and system based on artificial intelligence |
CN117011772A (en) * | 2023-07-31 | 2023-11-07 | 广东电网有限责任公司 | Risk prompting method, device and storage medium for power transmission line |
CN116993779A (en) * | 2023-08-03 | 2023-11-03 | 重庆大学 | Vehicle target tracking method suitable for monitoring video |
CN116912238B (en) * | 2023-09-11 | 2023-11-28 | 湖北工业大学 | Weld joint pipeline identification method and system based on multidimensional identification network cascade fusion |
CN117237369B (en) * | 2023-11-16 | 2024-02-27 | 苏州视智冶科技有限公司 | Blast furnace iron notch opening depth measurement method based on computer vision |
CN117372935B (en) * | 2023-12-07 | 2024-02-20 | 神思电子技术股份有限公司 | Video target detection method, device and medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170206431A1 (en) * | 2016-01-20 | 2017-07-20 | Microsoft Technology Licensing, Llc | Object detection and classification in images |
CN108416287A (en) * | 2018-03-04 | 2018-08-17 | 南京理工大学 | A kind of pedestrian detection method excavated based on omission negative sample |
CN108830188A (en) * | 2018-05-30 | 2018-11-16 | 西安理工大学 | Vehicle checking method based on deep learning |
CN109377555A (en) * | 2018-11-14 | 2019-02-22 | 江苏科技大学 | Autonomous underwater robot prospect visual field three-dimensional reconstruction target's feature-extraction recognition methods |
CN109447018A (en) * | 2018-11-08 | 2019-03-08 | 天津理工大学 | A kind of road environment visual perception method based on improvement Faster R-CNN |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9881234B2 (en) * | 2015-11-25 | 2018-01-30 | Baidu Usa Llc. | Systems and methods for end-to-end object detection |
CN107507172A (en) * | 2017-08-08 | 2017-12-22 | 国网上海市电力公司 | Merge the extra high voltage line insulator chain deep learning recognition methods of infrared visible ray |
CN107680106A (en) * | 2017-10-13 | 2018-02-09 | 南京航空航天大学 | A kind of conspicuousness object detection method based on Faster R CNN |
CN108563977A (en) * | 2017-12-18 | 2018-09-21 | 华南理工大学 | A kind of the pedestrian's method for early warning and system of expressway entrance and exit |
CN108648233B (en) * | 2018-03-24 | 2022-04-12 | 北京工业大学 | Target identification and capture positioning method based on deep learning |
-
2019
- 2019-03-12 CN CN201910185300.4A patent/CN109977812B/en active Active
- 2019-06-25 JP JP2021502766A patent/JP7120689B2/en active Active
- 2019-06-25 WO PCT/CN2019/092749 patent/WO2020181685A1/en active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170206431A1 (en) * | 2016-01-20 | 2017-07-20 | Microsoft Technology Licensing, Llc | Object detection and classification in images |
CN108416287A (en) * | 2018-03-04 | 2018-08-17 | 南京理工大学 | A kind of pedestrian detection method excavated based on omission negative sample |
CN108830188A (en) * | 2018-05-30 | 2018-11-16 | 西安理工大学 | Vehicle checking method based on deep learning |
CN109447018A (en) * | 2018-11-08 | 2019-03-08 | 天津理工大学 | A kind of road environment visual perception method based on improvement Faster R-CNN |
CN109377555A (en) * | 2018-11-14 | 2019-02-22 | 江苏科技大学 | Autonomous underwater robot prospect visual field three-dimensional reconstruction target's feature-extraction recognition methods |
Cited By (67)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110399884B (en) * | 2019-07-10 | 2021-08-20 | 浙江理工大学 | Feature fusion self-adaptive anchor frame model vehicle detection method |
CN110399884A (en) * | 2019-07-10 | 2019-11-01 | 浙江理工大学 | A kind of adaptive anchor frame model vehicle checking method of Fusion Features |
CN110414389A (en) * | 2019-07-12 | 2019-11-05 | 黑龙江御林湾科技有限公司 | A kind of object detection method of the fast area search based on deep learning |
CN110464611A (en) * | 2019-07-23 | 2019-11-19 | 苏州国科视清医疗科技有限公司 | A kind of digitlization amblyopia enhancing training device and system and its related algorithm |
CN110503112A (en) * | 2019-08-27 | 2019-11-26 | 电子科技大学 | A kind of small target deteection of Enhanced feature study and recognition methods |
CN110503112B (en) * | 2019-08-27 | 2023-02-03 | 电子科技大学 | Small target detection and identification method for enhancing feature learning |
CN110826391A (en) * | 2019-09-10 | 2020-02-21 | 中国三峡建设管理有限公司 | Bleeding area detection method, bleeding area detection system, computer device and storage medium |
CN110689021A (en) * | 2019-10-17 | 2020-01-14 | 哈尔滨理工大学 | Real-time target detection method in low-visibility environment based on deep learning |
CN111091144B (en) * | 2019-11-27 | 2023-06-27 | 云南电网有限责任公司电力科学研究院 | Image feature point matching method and device based on depth pseudo-twin network |
CN111091144A (en) * | 2019-11-27 | 2020-05-01 | 云南电网有限责任公司电力科学研究院 | Image feature point matching method and device based on depth pseudo-twin network |
CN110743818A (en) * | 2019-11-29 | 2020-02-04 | 苏州嘉诺环境工程有限公司 | Garbage sorting system and garbage sorting method based on vision and deep learning |
CN111104885A (en) * | 2019-12-10 | 2020-05-05 | 南京邮电大学 | Vehicle identification method based on video deep learning |
CN111104903A (en) * | 2019-12-19 | 2020-05-05 | 南京邮电大学 | Depth perception traffic scene multi-target detection method and system |
CN111145239A (en) * | 2019-12-30 | 2020-05-12 | 南京航空航天大学 | Aircraft fuel tank redundancy automatic detection method based on deep learning |
CN111145239B (en) * | 2019-12-30 | 2022-02-11 | 南京航空航天大学 | Aircraft fuel tank redundancy automatic detection method based on deep learning |
CN111182491A (en) * | 2019-12-31 | 2020-05-19 | 淮安中科晶上智能网联研究院有限公司 | Radio frequency tomography-based equipment-free target positioning method and device |
CN111182491B (en) * | 2019-12-31 | 2022-03-22 | 淮安中科晶上智能网联研究院有限公司 | Radio frequency tomography-based equipment-free target positioning method and device |
CN111291747A (en) * | 2020-01-10 | 2020-06-16 | 大连理工大学 | Depth map-based color small target detection method in complex scene |
CN111291747B (en) * | 2020-01-10 | 2023-06-13 | 大连理工大学 | Depth map-based color small target detection method in complex scene |
CN111444816A (en) * | 2020-01-14 | 2020-07-24 | 北京银河信通科技有限公司 | Multi-scale dense pedestrian detection method based on fast RCNN |
CN111292349B (en) * | 2020-01-17 | 2023-04-18 | 北京大学深圳研究生院 | Data enhancement method for target detection based on fusion of recommendation candidate boxes |
CN111292349A (en) * | 2020-01-17 | 2020-06-16 | 北京大学深圳研究生院 | Data enhancement method for target detection based on fusion of recommendation candidate boxes |
CN111310607A (en) * | 2020-01-22 | 2020-06-19 | 交通运输部公路科学研究所 | Highway safety risk identification method and system based on computer vision and artificial intelligence |
CN111310828A (en) * | 2020-02-14 | 2020-06-19 | 开易(北京)科技有限公司 | Target detection model fine-tuning method and device for ADAS scene |
CN111310660A (en) * | 2020-02-14 | 2020-06-19 | 开易(北京)科技有限公司 | Target detection false alarm suppression method and device for ADAS scene |
CN111310828B (en) * | 2020-02-14 | 2023-01-03 | 开易(北京)科技有限公司 | Target detection model fine-tuning method and device for ADAS scene |
CN111291820B (en) * | 2020-02-19 | 2023-05-30 | 中国电子科技集团公司第二十八研究所 | Target detection method combining positioning information and classification information |
CN111291820A (en) * | 2020-02-19 | 2020-06-16 | 中国电子科技集团公司第二十八研究所 | Target detection method combining positioning information and classification information |
CN111310850A (en) * | 2020-03-02 | 2020-06-19 | 杭州雄迈集成电路技术股份有限公司 | License plate detection model construction method and system and license plate detection method and system |
CN111310850B (en) * | 2020-03-02 | 2023-06-16 | 杭州雄迈集成电路技术股份有限公司 | License plate detection model construction method and system, license plate detection method and system |
CN111444973A (en) * | 2020-03-31 | 2020-07-24 | 西安交通大学 | Method for detecting commodities on unmanned retail shopping table |
CN111444973B (en) * | 2020-03-31 | 2022-05-20 | 西安交通大学 | Method for detecting commodities on unmanned retail shopping table |
CN111507738A (en) * | 2020-05-04 | 2020-08-07 | 武汉积墨包装印刷有限公司 | Ink tracing and recycling process method based on block chain and 5G communication |
CN112750194A (en) * | 2020-05-15 | 2021-05-04 | 奕目(上海)科技有限公司 | Obstacle avoidance method and device for unmanned automobile |
CN111724392A (en) * | 2020-05-25 | 2020-09-29 | 浙江工业大学 | Data processing method for deep learning feature attention transfer |
CN111666839A (en) * | 2020-05-25 | 2020-09-15 | 东华大学 | Road pedestrian detection system based on improved Faster RCNN |
CN111881932B (en) * | 2020-06-11 | 2023-09-15 | 中国人民解放军战略支援部队信息工程大学 | FasterRCNN target detection algorithm for military aircraft |
CN111881932A (en) * | 2020-06-11 | 2020-11-03 | 中国人民解放军战略支援部队信息工程大学 | FasterRCNN target detection algorithm for military aircraft |
CN111738164A (en) * | 2020-06-24 | 2020-10-02 | 广西计算中心有限责任公司 | Pedestrian detection method based on deep learning |
CN112016449A (en) * | 2020-08-27 | 2020-12-01 | 西华大学 | Vehicle identification and detection method based on deep learning |
CN112085126B (en) * | 2020-09-30 | 2023-12-12 | 浙江大学 | Single sample target detection method focusing on classification task |
CN112085126A (en) * | 2020-09-30 | 2020-12-15 | 浙江大学 | Single-sample target detection method focusing on classification task |
CN112183485B (en) * | 2020-11-02 | 2024-03-05 | 北京信息科技大学 | Deep learning-based traffic cone detection positioning method, system and storage medium |
CN112183485A (en) * | 2020-11-02 | 2021-01-05 | 北京信息科技大学 | Deep learning-based traffic cone detection positioning method and system and storage medium |
CN112668585B (en) * | 2020-11-26 | 2024-04-09 | 厦门大学 | Object identification and positioning method in dynamic environment |
CN112668585A (en) * | 2020-11-26 | 2021-04-16 | 厦门大学 | Object identification and positioning method in dynamic environment |
CN112446429A (en) * | 2020-11-27 | 2021-03-05 | 广东电网有限责任公司肇庆供电局 | CGAN (Carrier grade Access network) -based routing inspection image data small sample expansion method |
CN113173502A (en) * | 2021-01-15 | 2021-07-27 | 福建电子口岸股份有限公司 | Anti-collision method and system based on laser visual fusion and deep learning |
CN113173502B (en) * | 2021-01-15 | 2023-06-06 | 福建电子口岸股份有限公司 | Anticollision method and system based on laser vision fusion and deep learning |
CN112766176A (en) * | 2021-01-21 | 2021-05-07 | 深圳市安软科技股份有限公司 | Training method of lightweight convolutional neural network and face attribute recognition method |
CN112766176B (en) * | 2021-01-21 | 2023-12-01 | 深圳市安软科技股份有限公司 | Training method of lightweight convolutional neural network and face attribute recognition method |
CN112964693A (en) * | 2021-02-19 | 2021-06-15 | 山东捷讯通信技术有限公司 | Raman spectrum band region segmentation method |
CN112818932A (en) * | 2021-02-26 | 2021-05-18 | 北京车和家信息技术有限公司 | Image processing method, obstacle detection device, medium, and vehicle |
CN113052184B (en) * | 2021-03-12 | 2022-11-18 | 电子科技大学 | Target detection method based on two-stage local feature alignment |
CN113052184A (en) * | 2021-03-12 | 2021-06-29 | 电子科技大学 | Target detection method based on two-stage local feature alignment |
CN113128564A (en) * | 2021-03-23 | 2021-07-16 | 武汉泰沃滋信息技术有限公司 | Typical target detection method and system based on deep learning under complex background |
WO2022205329A1 (en) * | 2021-04-01 | 2022-10-06 | 京东方科技集团股份有限公司 | Object detection method, object detection apparatus, and object detection system |
CN113177133B (en) * | 2021-04-23 | 2024-03-29 | 深圳依时货拉拉科技有限公司 | Image retrieval method, device, equipment and storage medium |
CN113177133A (en) * | 2021-04-23 | 2021-07-27 | 深圳依时货拉拉科技有限公司 | Image retrieval method, device, equipment and storage medium |
CN113159198A (en) * | 2021-04-27 | 2021-07-23 | 上海芯物科技有限公司 | Target detection method, device, equipment and storage medium |
CN113240611A (en) * | 2021-05-28 | 2021-08-10 | 中建材信息技术股份有限公司 | Foreign matter detection method based on picture sequence |
CN113569702B (en) * | 2021-07-23 | 2023-10-27 | 闽江学院 | Truck single-double tire identification method based on deep learning |
CN113569702A (en) * | 2021-07-23 | 2021-10-29 | 闽江学院 | Deep learning-based truck single-tire and double-tire identification method |
CN113591668B (en) * | 2021-07-26 | 2023-11-21 | 南京大学 | Wide area unknown dam automatic detection method using deep learning and space analysis |
CN113591668A (en) * | 2021-07-26 | 2021-11-02 | 南京大学 | Wide-area unknown dam automatic detection method using deep learning and spatial analysis |
CN114220053A (en) * | 2021-12-15 | 2022-03-22 | 北京建筑大学 | Unmanned aerial vehicle video vehicle retrieval method based on vehicle feature matching |
CN115529475A (en) * | 2021-12-29 | 2022-12-27 | 北京智美互联科技有限公司 | Method and system for detecting video flow content and controlling wind |
Also Published As
Publication number | Publication date |
---|---|
WO2020181685A1 (en) | 2020-09-17 |
JP2021530062A (en) | 2021-11-04 |
JP7120689B2 (en) | 2022-08-17 |
CN109977812B (en) | 2023-02-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109977812A (en) | A kind of Vehicular video object detection method based on deep learning | |
CN110164128B (en) | City-level intelligent traffic simulation system | |
CN108304787A (en) | Road target detection method based on convolutional neural networks | |
CN111583639B (en) | Road traffic jam early warning method and system | |
CN103034836B (en) | Road sign detection method and road sign checkout equipment | |
JPWO2020181685A5 (en) | ||
CN109447033A (en) | Vehicle front obstacle detection method based on YOLO | |
CN109508710A (en) | Based on the unmanned vehicle night-environment cognitive method for improving YOLOv3 network | |
CN110135296A (en) | Airfield runway FOD detection method based on convolutional neural networks | |
CN108509954A (en) | A kind of more car plate dynamic identifying methods of real-time traffic scene | |
CN107609602A (en) | A kind of Driving Scene sorting technique based on convolutional neural networks | |
CN106650913A (en) | Deep convolution neural network-based traffic flow density estimation method | |
CN107609525A (en) | Remote Sensing Target detection method based on Pruning strategy structure convolutional neural networks | |
CN107871126A (en) | Model recognizing method and system based on deep-neural-network | |
CN111553201B (en) | Traffic light detection method based on YOLOv3 optimization algorithm | |
CN105427309A (en) | Multiscale hierarchical processing method for extracting object-oriented high-spatial resolution remote sensing information | |
CN102902956B (en) | A kind of ground visible cloud image identifying processing method | |
CN107133974A (en) | The vehicle type classification method that Gaussian Background modeling is combined with Recognition with Recurrent Neural Network | |
CN108875593A (en) | Visible images weather recognition methods based on convolutional neural networks | |
CN109766936A (en) | Image change detection method based on information transmitting and attention mechanism | |
CN110197152A (en) | A kind of road target recognition methods for automated driving system | |
CN106845387A (en) | Pedestrian detection method based on self study | |
CN102169543B (en) | People counting method based on multiple source information fusion and on-line learning | |
CN109492596A (en) | A kind of pedestrian detection method and system based on K-means cluster and region recommendation network | |
CN109948690A (en) | A kind of high-speed rail scene perception method based on deep learning and structural information |
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 |