CN112329768A - Improved YOLO-based method for identifying fuel-discharging stop sign of gas station - Google Patents
Improved YOLO-based method for identifying fuel-discharging stop sign of gas station Download PDFInfo
- Publication number
- CN112329768A CN112329768A CN202011148161.7A CN202011148161A CN112329768A CN 112329768 A CN112329768 A CN 112329768A CN 202011148161 A CN202011148161 A CN 202011148161A CN 112329768 A CN112329768 A CN 112329768A
- Authority
- CN
- China
- Prior art keywords
- yolo
- neural network
- gas station
- iou
- region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000007599 discharging Methods 0.000 title claims description 9
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 15
- 238000001514 detection method Methods 0.000 claims abstract description 15
- 238000013528 artificial neural network Methods 0.000 claims abstract description 9
- 239000000446 fuel Substances 0.000 claims description 5
- 238000013145 classification model Methods 0.000 claims description 3
- 239000000463 material Substances 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 2
- 230000001629 suppression Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 6
- 238000013136 deep learning model Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/63—Scene text, e.g. street names
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Biology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method for identifying a gas station oil discharge stop sign based on improved YOLO, which comprises the following steps: s1, collecting videos and photos of the oil unloading stop board on an oil unloading operation site of a gas station, and making the videos and the photos into a sample data set; s2, dividing the picture and dividing the regions, and detecting whether the central point is a target in each region; s3, constructing a YOLO convolutional neural network, and extracting features by using the YOLO convolutional neural network; s4, training the YOLO neural network according to the data set prepared in the step S1; s5: and predicting the trained YOLO neural network by using the collected photos to obtain the recognition result of the oil-discharge stop sign of the gas station. The invention provides improved YOLO-based gas station oil discharge stop board sign recognition based on a deep learning model, which not only retains the advantage of high detection speed of a YOLO algorithm, but also greatly improves the detection accuracy and detection effect on the basis.
Description
Technical Field
The invention relates to the technical field of computer vision target recognition, in particular to a method for recognizing a gas station oil discharge stop board sign based on improved YOLO.
Background
Early methods of object detection, which are typically predicted by using a sliding window, are very time consuming and are not very accurate; the object prosal method is presented later, compared with a sliding window mode, the calculation amount is greatly reduced, and the performance is greatly improved; later on, Fast R-CNN and other methods were developed by using selective search in combination with the R-CNN of the convolutional neural network, but the speed of the methods still needs to be improved.
The YOLO is a convolutional neural network for predicting the positions and the types of a plurality of BOX at one time, can realize end-to-end target detection and identification, and has the greatest advantage of high speed. In fact, the nature of target detection is regression, so a CNN implementing the regression function does not require a too complex involved process. The YOLO does not select a sliding window or a method for extracting propusal to train the network, but directly selects a whole graph training model, and the method has the advantage that a target area and a background area can be better distinguished; however, the YOLO algorithm has defects, the accuracy of the YOLO algorithm is lower than that of other R-CNN algorithms, the detection effect of the object is to be improved, and the YOLO algorithm is improved according to the defects, so that the YOLO algorithm can perform better target identification.
Disclosure of Invention
The invention aims to overcome the defects and shortcomings of the prior art, and provides a method and a system for identifying a gas station oil discharge stop sign based on improved YOLO, which can improve the accuracy of the traditional YOLO and improve the target detection effect.
In order to achieve the purpose, the technical scheme of the invention comprises the following steps:
s1, collecting videos and photos of the oil unloading stop board on an oil unloading operation site of a gas station, and making the videos and the photos into a sample data set;
s2, dividing the picture and dividing the regions, and detecting whether the central point is a target in each region;
s3, constructing a YOLO convolutional neural network, extracting features by using the YOLO convolutional neural network, extracting different scales by using the feature map in the step S3, generating predictions of different proportions by using the feature map of different scales, and then definitely performing separation prediction according to length ratios;
s4, training the YOLO neural network according to the data set prepared in the step S1;
s5: and predicting the trained YOLO neural network by using the collected photos to obtain the recognition result of the oil-discharge stop sign of the gas station.
The further setting is that the photos and videos collected in step S1 are obtained from different angles and different heights, and all material shooting needs to be performed in batch according to different states of whether the vehicle is parked in the vehicle parking area.
It is further configured that the segmentation and division in S2 is that the CNN network in YOLO segments the inputted picture into 4 × 4 grids, and further generates 9 possible regions with different sizes based on the grids.
It is further set that detecting at each area whether the center point is an object falling within the area in said S2 includes the steps of:
a. detecting the probability size Pr (object) that the region contains the object;
b. the accuracy of this region;
when no object is contained in the region, pr (object) is 0; when the region includes an object, pr (object) is 1; the accuracy of the region is represented by the intersection of the predicted box and the actual box and the IOU, so the confidence is represented by pr (object) IOU.
Further setting is that the network training in S4 is to train the first 20 convolutional layers, an average-pool layer, and a full-link layer of the classification model on ImageNet, and the loss function of the training is:
each bounding box comprises 5 values of x, y, w, h and confidence, wherein (x, y) coordinates represent the center of a 2-bounding box relative to a grid unit bounding box, the width and the height are predicted relative to the whole image, the confidence represents the IOU between the predicted box and an actual bounding box, 1iobj represents whether an object appears in a grid unit i, and whether the object is 1 or 0 is determined according to whether the unit actually has the object; 1ijobj indicates that the j-th bounding box predictor of grid cell i is responsible for the prediction, if the cell really has a target and the bounding box IOU is largest, then the value is 1, or not 0.
The step 5 of predicting the fuel-filling station fuel-discharging stop sign is further arranged to find the areas with higher confidence from the areas in the step S2, calculate the IOU of the areas, compare the value with the set threshold, delete the areas with the value larger than the set threshold, repeat the steps until the areas are processed, and finally obtain the final detection result by the NMS algorithm.
The invention has the technical effects and advantages that: compared with the existing YOLO algorithm, the improved YOLO algorithm not only retains the advantage of high detection speed of the YOLO algorithm, but also greatly improves the detection accuracy and detection effect on the basis.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is within the scope of the present invention for those skilled in the art to obtain other drawings based on the drawings without inventive exercise.
FIG. 1 is a flow chart of an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings.
As shown in fig. 1, in an embodiment of the present invention, a method for identifying a fuel discharge stop sign based on a YOLO refueling factory includes the following steps:
s1, collecting the stop board mark, collecting the video material and the photo of the oil-discharging stop board on the oil-discharging operation site of the gas station and making the photo into a data set;
the specific process is that the photos and videos collected in step S1 are obtained from different angles and different heights as much as possible, and all materials are shot in batches according to different states of whether vehicles are parked in the vehicle parking area.
S2, dividing the picture and the regions, and using each region to detect whether the central point is in the target of the region;
the specific process is that the segmentation and division of the regions in step S2 is that the CNN network in YOLO segments the input picture into 4 × 4 meshes, and further generates 9 possible regions with different sizes based on the meshes; the method for detecting whether the central points of the objects fall in the area comprises two steps: firstly, detecting the possibility size Pr (object) of the object contained in the area; second, the accuracy of this region (IOU).
When the region does not contain the target, Pr (object) is 0; when the region includes an object, pr (object) is 1. The accuracy of the region may be determined by the intersection ratio of the predicted box to the actual box (IOU). The confidence may therefore be expressed as pr (object) IOU.
S3, constructing a YOLO convolution neural network, and extracting features by using the convolution network;
the specific process is that the characteristic diagram in the step 3 needs to be extracted with different scales, the characteristic diagrams with different scales are used for generating predictions with different proportions, and then the characteristic diagrams are definitely separated and predicted according to the length ratio, so that the detection effect of the object can be improved by extracting the characteristic diagrams in the mode.
S4, training the YOLO neural network according to the data set prepared in the step S1;
the specific process is that the network training of the step 4 is to train the first 20 convolutional layers, an average-pool layer and a full-link layer of the classification model on ImageNet. The loss function of the training:
wherein each bounding box contains 5 values x, y, w, h and confidence. The (x, y) coordinates indicate that 2 the bounding box is centered with respect to the grid cell bounding box, the width and height are predicted with respect to the entire image, confidence indicates the IOU between the predicted box and the actual bounding box, 1iobj indicates whether an object appears in grid cell i (1, 0, determined by whether the cell actually has an object), and 1ijobj indicates that the jth bounding box predictor of grid cell i is "responsible" for the prediction (if the cell does have an object and the bounding box IOU is largest, the value is 1, 0).
S5: and predicting the trained YOLO neural network by using the collected photos to obtain the recognition result of the oil-discharge stop sign of the gas station.
The fuel filling station fuel discharge stop board prediction of S5 finds regions with high confidence from the regions in step S2, calculates the IOU of these regions, compares the value with a set threshold, deletes regions with values greater than the set threshold, repeats the above steps until the regions are processed, and finally obtains the final detection result by using a non-maximum suppression (NMS) algorithm.
It will be understood by those skilled in the art that all or part of the steps in the method for implementing the above embodiments may be implemented by relevant hardware instructed by a program, and the program may be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc.
The above disclosure is only for the purpose of illustrating the preferred embodiments of the present invention, and it is therefore to be understood that the invention is not limited by the scope of the appended claims.
It should be noted that the embodiments of the present invention can be realized in hardware, software, or a combination of software and hardware. The hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the apparatus and methods described above may be implemented using computer executable instructions and/or embodied in processor control code, such code being provided, for example, in programmable memory or on a data carrier such as an optical or electronic signal carrier.
Claims (6)
1. A method for identifying a fuel-discharging stop sign of a gas station based on improved YOLO is characterized by comprising the following steps:
s1, collecting videos and photos of the oil unloading stop board on an oil unloading operation site of a gas station, and making the videos and the photos into a sample data set;
s2, dividing the picture and dividing the regions, and detecting whether the central point is a target in each region;
s3, constructing a YOLO convolutional neural network, extracting features by using the YOLO convolutional neural network, extracting different scales by using the feature map in the step S3, generating predictions of different proportions by using the feature map of different scales, and then definitely performing separation prediction according to length ratios;
s4, training the YOLO neural network according to the data set prepared in the step S1;
s5: and predicting the trained YOLO neural network by using the collected photos to obtain the recognition result of the oil-discharge stop sign of the gas station.
2. The method for identifying the signs of the fuel-discharging stop signs of the gas stations based on the improved YOLO as claimed in claim 1, wherein: the pictures and videos collected in step S1 are obtained from different angles and at different heights, and all material shooting needs to be performed in batch according to different states of whether the vehicle is parked in the vehicle parking area.
3. The method for identifying the signs of the fuel-discharging stop signs of the gas stations based on the improved YOLO as claimed in claim 1, wherein: the segmentation and division in S2 is that the convolutional neural network in YOLO segments the input picture into 4 × 4 grids, and then 9 possible regions with different sizes are further generated.
4. The improved YOLO-based method for identifying signs of fuel discharge stop boards at gas stations as claimed in claim 3, wherein the step of detecting whether the center point is a target falling within each area in S2 comprises the steps of:
a. detecting the probability size Pr (object) that the region contains the object;
b. the accuracy of this region;
when no object is contained in the region, pr (object) is 0; when the region includes an object, pr (object) is 1; the accuracy of the region is represented by the intersection of the predicted box and the actual box and the IOU, so the confidence is represented by pr (object) IOU.
5. The method for identifying the signs of the fuel-discharging stop signs of the gas stations based on the improved YOLO as claimed in claim 1, wherein:
the network training in S4 is to train the first 20 convolutional layers, an average-pool layer, and a full-link layer of the classification model on ImageNet, and the loss function of the training is:
each bounding box comprises 5 values of x, y, w, h and confidence, wherein (x, y) coordinates represent the center of a 2-bounding box relative to a grid unit bounding box, the width and the height are predicted relative to the whole image, the confidence represents the IOU between the predicted box and an actual bounding box, 1iobj represents whether an object appears in a grid unit i, and whether the object is 1 or 0 is determined according to whether the unit actually has the object; 1ijobj indicates that the j-th bounding box predictor of grid cell i is responsible for the prediction, if the cell really has a target and the bounding box IOU is largest, then the value is 1, or not 0.
6. The method as claimed in claim 1, wherein the step S5 of predicting the gasoline station fuel discharge stop sign includes finding areas with high confidence from the areas in step S2, calculating IOU of the areas, comparing the IOU value with a set threshold, deleting the areas with higher confidence, repeating the above steps until all the areas are processed, and finally obtaining the final detection result by using a non-maximum suppression algorithm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011148161.7A CN112329768A (en) | 2020-10-23 | 2020-10-23 | Improved YOLO-based method for identifying fuel-discharging stop sign of gas station |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011148161.7A CN112329768A (en) | 2020-10-23 | 2020-10-23 | Improved YOLO-based method for identifying fuel-discharging stop sign of gas station |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112329768A true CN112329768A (en) | 2021-02-05 |
Family
ID=74310948
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011148161.7A Pending CN112329768A (en) | 2020-10-23 | 2020-10-23 | Improved YOLO-based method for identifying fuel-discharging stop sign of gas station |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112329768A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113469178A (en) * | 2021-07-05 | 2021-10-01 | 安徽南瑞继远电网技术有限公司 | Electric power meter identification method based on deep learning |
CN113609891A (en) * | 2021-06-15 | 2021-11-05 | 北京瞭望神州科技有限公司 | Ship identification monitoring method and system |
Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108509954A (en) * | 2018-04-23 | 2018-09-07 | 合肥湛达智能科技有限公司 | A kind of more car plate dynamic identifying methods of real-time traffic scene |
CN109086792A (en) * | 2018-06-26 | 2018-12-25 | 上海理工大学 | Based on the fine granularity image classification method for detecting and identifying the network architecture |
CN109255286A (en) * | 2018-07-21 | 2019-01-22 | 哈尔滨工业大学 | A kind of quick detection recognition method of unmanned plane optics based on YOLO deep learning network frame |
CN109543617A (en) * | 2018-11-23 | 2019-03-29 | 于兴虎 | The detection method of intelligent vehicle movement traffic information based on YOLO target detection technique |
CN109815998A (en) * | 2019-01-08 | 2019-05-28 | 科大国创软件股份有限公司 | A kind of AI dress dimension method for inspecting and system based on YOLO algorithm |
CN110472467A (en) * | 2019-04-08 | 2019-11-19 | 江西理工大学 | The detection method for transport hub critical object based on YOLO v3 |
CN110598637A (en) * | 2019-09-12 | 2019-12-20 | 齐鲁工业大学 | Unmanned driving system and method based on vision and deep learning |
CN110765865A (en) * | 2019-09-18 | 2020-02-07 | 北京理工大学 | Underwater target detection method based on improved YOLO algorithm |
CN110781882A (en) * | 2019-09-11 | 2020-02-11 | 南京钰质智能科技有限公司 | License plate positioning and identifying method based on YOLO model |
CN110796186A (en) * | 2019-10-22 | 2020-02-14 | 华中科技大学无锡研究院 | Dry and wet garbage identification and classification method based on improved YOLOv3 network |
CN110796168A (en) * | 2019-09-26 | 2020-02-14 | 江苏大学 | Improved YOLOv 3-based vehicle detection method |
CN111038888A (en) * | 2019-12-26 | 2020-04-21 | 上海电力大学 | Plastic bottle recycling robot based on machine vision |
CN111401148A (en) * | 2020-02-27 | 2020-07-10 | 江苏大学 | Road multi-target detection method based on improved multilevel YO L Ov3 |
CN111582056A (en) * | 2020-04-17 | 2020-08-25 | 上善智城(苏州)信息科技有限公司 | Automatic detection method for fire-fighting equipment in oil unloading operation site of gas station |
CN111612002A (en) * | 2020-06-04 | 2020-09-01 | 广州市锲致智能技术有限公司 | Multi-target object motion tracking method based on neural network |
CN111738258A (en) * | 2020-06-24 | 2020-10-02 | 东方电子股份有限公司 | Pointer instrument reading identification method based on robot inspection |
-
2020
- 2020-10-23 CN CN202011148161.7A patent/CN112329768A/en active Pending
Patent Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108509954A (en) * | 2018-04-23 | 2018-09-07 | 合肥湛达智能科技有限公司 | A kind of more car plate dynamic identifying methods of real-time traffic scene |
CN109086792A (en) * | 2018-06-26 | 2018-12-25 | 上海理工大学 | Based on the fine granularity image classification method for detecting and identifying the network architecture |
CN109255286A (en) * | 2018-07-21 | 2019-01-22 | 哈尔滨工业大学 | A kind of quick detection recognition method of unmanned plane optics based on YOLO deep learning network frame |
CN109543617A (en) * | 2018-11-23 | 2019-03-29 | 于兴虎 | The detection method of intelligent vehicle movement traffic information based on YOLO target detection technique |
CN109815998A (en) * | 2019-01-08 | 2019-05-28 | 科大国创软件股份有限公司 | A kind of AI dress dimension method for inspecting and system based on YOLO algorithm |
CN110472467A (en) * | 2019-04-08 | 2019-11-19 | 江西理工大学 | The detection method for transport hub critical object based on YOLO v3 |
CN110781882A (en) * | 2019-09-11 | 2020-02-11 | 南京钰质智能科技有限公司 | License plate positioning and identifying method based on YOLO model |
CN110598637A (en) * | 2019-09-12 | 2019-12-20 | 齐鲁工业大学 | Unmanned driving system and method based on vision and deep learning |
CN110765865A (en) * | 2019-09-18 | 2020-02-07 | 北京理工大学 | Underwater target detection method based on improved YOLO algorithm |
CN110796168A (en) * | 2019-09-26 | 2020-02-14 | 江苏大学 | Improved YOLOv 3-based vehicle detection method |
CN110796186A (en) * | 2019-10-22 | 2020-02-14 | 华中科技大学无锡研究院 | Dry and wet garbage identification and classification method based on improved YOLOv3 network |
CN111038888A (en) * | 2019-12-26 | 2020-04-21 | 上海电力大学 | Plastic bottle recycling robot based on machine vision |
CN111401148A (en) * | 2020-02-27 | 2020-07-10 | 江苏大学 | Road multi-target detection method based on improved multilevel YO L Ov3 |
CN111582056A (en) * | 2020-04-17 | 2020-08-25 | 上善智城(苏州)信息科技有限公司 | Automatic detection method for fire-fighting equipment in oil unloading operation site of gas station |
CN111612002A (en) * | 2020-06-04 | 2020-09-01 | 广州市锲致智能技术有限公司 | Multi-target object motion tracking method based on neural network |
CN111738258A (en) * | 2020-06-24 | 2020-10-02 | 东方电子股份有限公司 | Pointer instrument reading identification method based on robot inspection |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113609891A (en) * | 2021-06-15 | 2021-11-05 | 北京瞭望神州科技有限公司 | Ship identification monitoring method and system |
CN113469178A (en) * | 2021-07-05 | 2021-10-01 | 安徽南瑞继远电网技术有限公司 | Electric power meter identification method based on deep learning |
CN113469178B (en) * | 2021-07-05 | 2024-03-01 | 安徽南瑞继远电网技术有限公司 | Power meter identification method based on deep learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111784685B (en) | Power transmission line defect image identification method based on cloud edge cooperative detection | |
CN111709416B (en) | License plate positioning method, device, system and storage medium | |
CN113468967B (en) | 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 | |
CN113822247B (en) | Method and system for identifying illegal building based on aerial image | |
CN104239867B (en) | License plate locating method and system | |
CN110188797B (en) | Intelligent automobile rapid test method based on Bayesian optimization | |
CN114140683A (en) | Aerial image target detection method, equipment and medium | |
CN111738114B (en) | Vehicle target detection method based on anchor-free accurate sampling remote sensing image | |
CN112364855A (en) | Video target detection method and system based on multi-scale feature fusion | |
CN114708437B (en) | Training method of target detection model, target detection method, device and medium | |
CN112766170B (en) | Self-adaptive segmentation detection method and device based on cluster unmanned aerial vehicle image | |
CN112633149A (en) | Domain-adaptive foggy-day image target detection method and device | |
CN110991447B (en) | Train number accurate positioning and identifying method based on deep learning | |
CN112329768A (en) | Improved YOLO-based method for identifying fuel-discharging stop sign of gas station | |
CN113313706A (en) | Power equipment defect image detection method based on detection reference point offset analysis | |
Fan et al. | Covered vehicle detection in autonomous driving based on faster rcnn | |
CN112785610B (en) | Lane line semantic segmentation method integrating low-level features | |
CN112560799B (en) | Unmanned aerial vehicle intelligent vehicle target detection method based on adaptive target area search and game and application | |
CN112949584A (en) | Image screening method and device, electronic equipment and storage medium | |
CN116630904B (en) | Small target vehicle detection method integrating non-adjacent jump connection and multi-scale residual error structure | |
CN111160274A (en) | Pedestrian detection method based on binaryzation fast RCNN (radar cross-correlation neural network) | |
CN112215042A (en) | Parking space limiter identification method and system and computer equipment | |
CN116863134A (en) | Method and system for detecting and dividing length and width of tunnel lining crack | |
CN112084815A (en) | Target detection method based on camera focal length conversion, storage medium and processor | |
CN116596895A (en) | Substation equipment image defect identification method and system |
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 |