WO2021208502A1 - Remote-sensing image target detection method based on smooth bounding box regression function - Google Patents
Remote-sensing image target detection method based on smooth bounding box regression function Download PDFInfo
- Publication number
- WO2021208502A1 WO2021208502A1 PCT/CN2020/140022 CN2020140022W WO2021208502A1 WO 2021208502 A1 WO2021208502 A1 WO 2021208502A1 CN 2020140022 W CN2020140022 W CN 2020140022W WO 2021208502 A1 WO2021208502 A1 WO 2021208502A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- target detection
- regression
- region
- interest
- network
- Prior art date
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 claims abstract description 28
- 238000012549 training Methods 0.000 claims abstract description 19
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 17
- 230000008569 process Effects 0.000 claims abstract description 14
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 238000011176 pooling Methods 0.000 claims abstract description 6
- 238000012937 correction Methods 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 description 45
- 238000010586 diagram Methods 0.000 description 6
- 238000012360 testing method Methods 0.000 description 5
- 102100031315 AP-2 complex subunit mu Human genes 0.000 description 4
- 101000796047 Homo sapiens AP-2 complex subunit mu Proteins 0.000 description 4
- WDLRUFUQRNWCPK-UHFFFAOYSA-N Tetraxetan Chemical compound OC(=O)CN1CCN(CC(O)=O)CCN(CC(O)=O)CCN(CC(O)=O)CC1 WDLRUFUQRNWCPK-UHFFFAOYSA-N 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 230000011218 segmentation Effects 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
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
Definitions
- the invention belongs to the field of image processing and machine learning, and relates to a remote sensing image target detection method based on a smooth border regression function.
- Remote sensing image target detection is one of the core tasks in remote sensing image understanding. Its main purpose is to quickly find and accurately locate the target of interest in remote sensing images. Target detection itself is an important task, and it is also the basis of many tasks. Such as instance segmentation, image understanding, etc.
- the detection accuracy of remote sensing images was low before, and only the intersection ratio between the position of the prediction frame and the target real reference frame is greater than 0.5, it can be considered as a correct detection.
- people need to change Detect targets under precise positioning to achieve high-quality detection.
- Deep learning is the most popular and cutting-edge basic artificial intelligence technology. Its powerful representation learning ability can automatically learn features from big data and has strong robustness.
- the network first uses a deep neural network to extract the features of the picture, and then uses a detector based on the feature to detect, but because the detector is sensitive to feature fluctuations, the robustness is not good enough, resulting in poor regression results.
- the regression process is mainly realized by the border regression function.
- Frame regression is to make the candidate frame return to a position closer to the true reference frame.
- Box regression is achieved by minimizing the gap with the real candidate box.
- the L2 loss function used in RCNN is improved to a smooth L1 loss function in Fast RCNN.
- the quality of the candidate frame is gradually improved, getting closer and closer to the real frame, at this time the gap will become smaller, and the volatility is greater, the more difficult it is to stabilize the regression, especially at the zero point Nearby will cause the failure of the regression due to continuous oscillations, resulting in low accuracy of the regression.
- the present invention provides a remote sensing image target detection method based on a smooth frame regression function.
- the technical problem to be solved is to provide a smooth frame regression function, so that the candidate frame and the real reference frame will fluctuate due to the small gap between them.
- the regression process becomes more stable, so as to obtain higher regression accuracy and detection accuracy.
- the present invention provides a target detection method based on a smooth border regression function, which includes the following steps:
- Step 1 Image preprocessing: Perform necessary preprocessing on training images, including image rotation, mirroring and other enhancement operations, image normalization operations, image size adjustment operations, and setting of hyperparameters for network training;
- Step 2 Feature extraction: input the image into the target detection class convolutional neural network to obtain the feature map; then input the feature map into the regional suggestion network to obtain the candidate frame; then send the candidate frame and the feature map to the sensor In the region of interest pooling layer, the characteristics of the region of interest are obtained;
- Step three classification: send the region of interest features obtained in step two to the softmax classifier for classification;
- Step 4 Send the features of the region of interest obtained in step 3 to the fully connected layer to get the predicted offset, and send the predicted offset to the smooth border regression function to get the actual offset. Move the amount to correct the candidate frame to a new position;
- Step 5 Use the bounding box of the candidate box after regression correction as the new candidate box, and send it to the region of interest layer together with the feature map to obtain the region of interest feature, repeat step 3, step 4, and step 5. Until the training process is over, a trained network is obtained;
- Step 6 Input the image to be detected into the trained network after preprocessing to obtain the target detection result.
- sgn represents the coincidence function, to ensure that there is no error in the operation of negative numbers
- exp is an exponential function
- c x , c y , c w , c h are the weight adjustment values of the regression
- t x , t y , t h , t w are The offset predicted by the convolutional neural network
- p x , p y are the position coordinates of the center point of the candidate box
- p w , p h are the width and height of the candidate box
- G x , G y are the center of the bounding box after regression correction
- G w , G h are the width and height of the bounding box after regression correction.
- the target detection convolutional neural network includes but is not limited to Faster RCNN, YOLO v1, YOLO v2, YOLO v3, SSD, FPN, RetinaNet, and Cascade RCNN.
- the beneficial effect of the present invention is that by constructing a smooth frame regression function, the stability of the regression process can be enhanced, the regression process where the gap between the candidate frame and the real reference frame is too small and the fluctuations will become more stable, and the solution to the problem of continuous occurrence near the zero point
- the oscillating causes the problem of regression failure, which makes the detection accuracy higher under the high IoU threshold, so as to obtain higher target detection accuracy.
- Figure 1 is a comparison diagram of the adjustment range of the smooth frame regression function and the original frame regression function
- Figure 2 is an enlarged comparison diagram of the smooth border regression function and the original border regression function near the zero point;
- Figure 3 is a visual display of the feature map output by the convolutional neural network
- Figure 4 is a schematic diagram of the regional proposal network structure
- Figure 5 is a schematic diagram of the structure of a cascade detector
- Figure 6 is the result of the Cascade RCNN method using the original frame regression function
- Fig. 7 is a detection result diagram of the Cascade RCNN method using the smooth border regression function provided by the present invention.
- FIG. 8 is a schematic diagram of a workflow of a hyperspectral image retrieval method according to an embodiment of the present invention.
- sgn represents the conformance function to ensure that there is no error in the operation of negative numbers.
- exp is an exponential function
- c x , c y , c w , c h are the weight adjustment values of the regression, and its value usually defaults to (10, 10, 5, 5)
- t x , t y , t h , t w are The offset predicted by the convolutional neural network
- p x , p y are the position coordinates of the center point of the candidate box
- p w , p h are the width and height of the candidate box
- G x , G y are the center of the bounding box after regression correction
- Point position coordinates G w , G h are the width and height of the bounding box after regression correction.
- the straight line represents the original regression function
- the curve represents the improved frame function.
- Figure 2 is an enlarged view of Figure 1 when it approaches zero. It can be seen that the improved regression function is smoother near the true value, so that the frame tends to move to the true frame after the regression, and does not easily cross the true frame, which enhances the nature of convergence.
- Cascade RCNN uses three cascaded detectors to achieve target detection.
- the original DOTA data set is large in size and contains many objects. According to the requirements of the present invention, the focus is on selecting pictures containing a large number of densely arranged small targets such as airplanes, ships, cars, etc., and then doing the pictures With a certain amount of cropping, the pictures are cropped to between 600-800, and the data set we need is obtained.
- the training set contains 15,070 pictures, and the test set contains 2,700 pictures.
- Send the picture to the network first perform operations such as horizontal mirroring and rotation on the picture to enhance the data set; then normalize the gray value of the picture, and then scale it according to the size of the training setting, usually the smallest edge is set
- the size is 600, and the maximum side size is 1000; then the picture is filtered, and if there is no target on the picture, the picture is excluded.
- the framework used is caffe2
- the backbone network is resnet101
- the minimum edge of the image is set to 600 during training
- the maximum edge is limited to 1000.
- the training method uses SGD with momentum, and the momentum is set to 0.9
- the initial learning rate is set to 0.01
- the penalty term coefficient is 0.0001.
- This article uses segmented training, a total of 360,000 iterations, and the learning rate decays to 0.001 and 0.0001 at 240,000 and 320,000 times, respectively.
- the pre-processed pictures are sequentially sent to the convolutional neural network layer, and the image data is convolved and pooled through the convolutional network neural to extract the characteristics of the picture for use in the subsequent Cascade RCNN detector Detection.
- Figure 3 shows the visual display of the feature map output by the convolutional neural network layer.
- the features extracted from the convolutional neural network are input into the regional suggestion network.
- the regional suggestion network a series of anchor points are preset for all regions on the picture by means of a sliding window, as shown in Figure 4. By filtering all preset anchor points according to the foreground confidence ranking method, the anchor point with the highest confidence is finally obtained as the candidate frame.
- the feature map is sent to the detector to detect the target object.
- B0 is the candidate area selected in the region suggestion network
- conv represents the convolutional neural network
- the candidate area is sent together with the feature map obtained from the convolutional neural network.
- Enter the RoI Pooling layer to obtain the features of the region of interest, and then send the features to the fully connected layer (H1), and then send the features output from the fully connected layer to the classifier (C1) for classification and smoothing provided by the present invention Fine-tune the positioning in the border regression function (B1).
- the network has three detectors.
- the candidate frame B1 which has been fine-tuned by the smooth frame regression function provided by the present invention from the previous layer, is used as a new input and sent to the detector of the next layer until the candidate frame B3 is obtained. Calculate the error between B3 and the real frame as a loss, carry out backward propagation, and adjust the parameters of the convolutional neural network. Repeat the above process until the end of the training process.
- preprocess the test picture scale it to the size set by the network, and normalize the gray value.
- the pictures are sequentially sent to the convolutional neural network to extract features to obtain feature maps.
- the extracted feature map is input into the region suggestion network to obtain a candidate frame, and then the candidate frame and the feature map are input into the region of interest pooling layer together to obtain the feature of the region of interest.
- the features of the region of interest are sent to the first layer of the cascade detector to obtain the offset of the regression, and then calculate according to the smooth border regression function to obtain the corrected position of the bounding box, and use the bounding box as a new candidate
- the box and the feature map are input into the region of interest pooling layer together to obtain the new region of interest feature, and then the new region of interest feature is input to the detector of the second layer, and this operation is repeated until the last layer detector.
- the bounding box obtained by the last layer of detectors after bounding regression correction is the final bounding box of the network.
- input the features of the region of interest of the last layer into the classifier of each layer of the detector to obtain the classification result, and then synthesize the classification results of each classifier to obtain the final classification result of the network.
- the above-mentioned DOTA data set is used for testing.
- the YOLO v2, SSD, Faster RCNN, YOLO v3, RetinaNet, FPN, Cascade RCNN methods are used for testing.
- the frame regression function of the original method is used for calculation, and then the original method
- the border regression function replaces the smooth border regression function provided by the invention, and then recalculates.
- evaluating the performance of a classifier is generally measured by two quantities: Precision and Recall.
- the samples can be divided into four categories according to the situation between the true value and the predicted value of the sample: True Positives (TP): Predict the positive sample as a positive case; False Positives , FP): predict positive samples as negative examples; True Negatives (TN): predict negative samples as negative examples; False Negatives (FN): predict negative samples as positive examples; through the confusion matrix (Confusion Matrix ) Can clearly present these four types of relationships.
- the performance of the detector in target detection is measured by AP and mAP.
- the average precision (Average Precision, AP) is usually taken as the evaluation index.
- the AP for single-type target detection is to calculate the "P-R curve" and the area enclosed by the horizontal and vertical axes of this type.
- target detection to determine the four types of samples TP, FP, TN and FN, it is necessary to calculate the IoU between each prediction frame and the true reference frame. Only when the threshold is greater than the set threshold, the sample can be judged as a positive sample .
- indicators such as AP, AP50, AP75, AP60, AP70, AP80, and AP90 are used to evaluate the accuracy of target detection for each comparison method used.
- AP50 refers to the AP value when IoU is set to 0.5, and the meaning of other indicators is similar to AP50. It can be seen that the higher the IoU, the higher the accuracy of target detection and the greater the difficulty.
- Figures 6 and 7 show the target detection results using Cascade RCNN as the basic network architecture, using the original border regression function and the smooth border regression function provided by the present invention.
- Fig. 6 is the result of the original frame regression function
- Fig. 7 is the result of the smooth frame regression function provided by the present invention. It can be clearly seen that the positioning accuracy of the method of the present invention is higher than that of the original frame regression function.
- Table 1 shows the comparison between the detection results of the method of the present invention and the original method under other network architectures. Where ⁇ indicates the accuracy of using the smooth frame regression function provided by the present invention under a given network architecture, and if there is no ⁇ , it indicates that the original frame regression function is used.
- AP represents the overall average accuracy index
- AP50 represents the average accuracy under the threshold where the IoU is greater than 0.5
- AP750 represents the average accuracy under the threshold where the IoU is greater than 0.75
- the frame regression process in target detection can be better realized based on the smooth frame regression function. Under the condition of high IoU threshold, the accuracy of the detected target frame is better. Compared with the original frame regression function, the original frame regression function is more accurate.
- the smooth border regression function provided by the invention can realize target detection with higher precision.
- the smooth border regression function provided by the present invention can be used in any target detection network framework.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Multimedia (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)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims (3)
- 一种基于平滑边框回归函数的遥感图像目标检测方法,其特征在于,包括以下步骤:A remote sensing image target detection method based on a smooth border regression function is characterized in that it includes the following steps:步骤一、图像预处理:对训练图像进行必要的预处理,包括图像旋转、镜像等增强操作,图像归一化操作,图像大小调整操作,并设置网络训练的超参数;Step 1. Image preprocessing: Perform necessary preprocessing on training images, including image rotation, mirroring and other enhancement operations, image normalization operations, image size adjustment operations, and setting of hyperparameters for network training;步骤二、特征提取:将图片输入到目标检测类卷积神经网络中,得到特征图;然后将特征图输入到区域建议网络中,得到候选框;再将候选框与特征图一同送入到感兴趣区域池化层中,得到感兴趣区域特征;Step 2. Feature extraction: input the image into the target detection class convolutional neural network to obtain the feature map; then input the feature map into the regional suggestion network to obtain the candidate frame; then send the candidate frame and the feature map to the sensor In the region of interest pooling layer, the characteristics of the region of interest are obtained;步骤三、分类:将步骤二得到的感兴趣区域特征送入到softmax分类器中进行分类;Step three, classification: send the region of interest features obtained in step two to the softmax classifier for classification;步骤四、回归:将步骤三得到的感兴趣区域特征送入到全连接层中得到预测的偏移量,将预测的偏移量送入到平滑边框回归函数中得到实际偏移量,依据偏移量,将候选框修正至新的位置;Step 4. Regression: Send the features of the region of interest obtained in step 3 to the fully connected layer to get the predicted offset, and send the predicted offset to the smooth border regression function to get the actual offset. Move the amount to correct the candidate frame to a new position;步骤五、修正:将候选框经过回归修正后的边界框作为新的候选框,与特征图一同送入到感兴趣区域层中,得到感兴趣区域特征,重复步骤三、步骤四、步骤五,直到训练过程结束,得到训练好的网络;Step 5. Correction: Use the bounding box of the candidate box after regression correction as the new candidate box, and send it to the region of interest layer together with the feature map to obtain the region of interest feature, repeat step 3, step 4, and step 5. Until the training process is over, a trained network is obtained;步骤六、将待检测图像经过预处理后输入到训练好的网络中,得到目标检测结果。Step 6. Input the image to be detected into the trained network after preprocessing to obtain the target detection result.
- 根据权利要求1所述的一种基于平滑边框回归函数的遥感图像目标检测方法,其特征在于,所述的用于回归的平滑边框回归函数为:A remote sensing image target detection method based on a smooth frame regression function according to claim 1, wherein the smooth frame regression function used for regression is:(sgn((t x/c x))×|(t x/c x)|) 4/3×p w+p x=G x (sgn((t x /c x ))×|(t x /c x )|) 4/3 ×p w +p x =G x(sgn((t y/c y))×|(t y/c y)|) 4/3×p h+p y=G y (sgn((t y /c y ))×|(t y /c y )|) 4/3 ×p h +p y =G yexp(sgn((t w/c w))×|(t w/c w)|) 4/3×p w=G w exp(sgn((t w /c w ))×|(t w /c w )|) 4/3 ×p w =G wexp(sgn((t h/c h))×|(t h/c h)|) 4/3×p h=G h exp(sgn((t h /c h ))×|(t h /c h )|) 4/3 × p h =G h其中,sgn表示符合函数,保证负数运算的时候不出错,exp是指数函数,c x,c y,c w,c h为回归的权重调节值,t x,t y,t h,t w是卷积神经网络预测的偏移量,p x,p y是候选框中心点的位置坐标,p w,p h是候选框的宽和高,G x,G y是回归修正之后的边界框中心点位置坐标,G w,G h是回归修正之后的边界框的宽和高。 Among them, sgn represents the coincidence function, to ensure that there is no error in the operation of negative numbers, exp is an exponential function, c x , c y , c w , c h are the weight adjustment values of the regression, t x , t y , t h , t w are The offset predicted by the convolutional neural network, p x , p y are the position coordinates of the center point of the candidate box, p w , p h are the width and height of the candidate box, G x , G y are the center of the bounding box after regression correction Point position coordinates, G w , G h are the width and height of the bounding box after regression correction.
- 根据权利要求1所述的一种基于平滑边框回归函数的遥感图像目标检测方法,其特征在于,所述的目标检测类卷积神经网络包括但不限于Faster RCNN,YOLO v1,YOLO v2,YOLO v3,SSD,FPN,RetinaNet,Cascade RCNN。A remote sensing image target detection method based on a smooth border regression function according to claim 1, wherein the target detection convolutional neural network includes but not limited to Faster RCNN, YOLO v1, YOLO v2, YOLO v3 , SSD, FPN, RetinaNet, Cascade RCNN.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010302996.7 | 2020-04-16 | ||
CN202010302996.7A CN111553212B (en) | 2020-04-16 | 2020-04-16 | Remote sensing image target detection method based on smooth frame regression function |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021208502A1 true WO2021208502A1 (en) | 2021-10-21 |
Family
ID=72005720
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2020/140022 WO2021208502A1 (en) | 2020-04-16 | 2020-12-28 | Remote-sensing image target detection method based on smooth bounding box regression function |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN111553212B (en) |
WO (1) | WO2021208502A1 (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113920375A (en) * | 2021-11-01 | 2022-01-11 | 国网新疆电力有限公司营销服务中心(资金集约中心、计量中心) | Fusion characteristic typical load recognition method and system based on combination of Faster R-CNN and SVM |
CN114529552A (en) * | 2022-03-03 | 2022-05-24 | 北京航空航天大学 | Remote sensing image building segmentation method based on geometric contour vertex prediction |
CN114707532A (en) * | 2022-01-11 | 2022-07-05 | 中铁隧道局集团有限公司 | Ground penetrating radar tunnel disease target detection method based on improved Cascade R-CNN |
CN114757970A (en) * | 2022-04-15 | 2022-07-15 | 合肥工业大学 | Multi-level regression target tracking method and system based on sample balance |
CN114792300A (en) * | 2022-01-27 | 2022-07-26 | 河南大学 | Multi-scale attention X-ray broken needle detection method |
CN114925387A (en) * | 2022-04-02 | 2022-08-19 | 北方工业大学 | Sorting system and method based on end edge cloud architecture and readable storage medium |
CN115170883A (en) * | 2022-07-19 | 2022-10-11 | 哈尔滨市科佳通用机电股份有限公司 | Method for detecting loss fault of brake cylinder piston push rod open pin |
CN116645523A (en) * | 2023-07-24 | 2023-08-25 | 济南大学 | Rapid target detection method based on improved RetinaNet |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111553212B (en) * | 2020-04-16 | 2022-02-22 | 中国科学院深圳先进技术研究院 | Remote sensing image target detection method based on smooth frame regression function |
CN112132033B (en) * | 2020-09-23 | 2023-10-10 | 平安国际智慧城市科技股份有限公司 | Vehicle type recognition method and device, electronic equipment and storage medium |
CN112232180A (en) * | 2020-10-14 | 2021-01-15 | 上海海洋大学 | Night underwater fish target detection method |
CN112464769A (en) * | 2020-11-18 | 2021-03-09 | 西北工业大学 | High-resolution remote sensing image target detection method based on consistent multi-stage detection |
CN112560682A (en) * | 2020-12-16 | 2021-03-26 | 重庆守愚科技有限公司 | Valve automatic detection method based on deep learning |
CN115035552B (en) * | 2022-08-11 | 2023-01-17 | 深圳市爱深盈通信息技术有限公司 | Fall detection method and device, equipment terminal and readable storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020012451A1 (en) * | 2000-06-13 | 2002-01-31 | Ching-Fang Lin | Method for target detection and identification by using proximity pixel information |
CN108052940A (en) * | 2017-12-17 | 2018-05-18 | 南京理工大学 | SAR remote sensing images waterborne target detection methods based on deep learning |
CN108564109A (en) * | 2018-03-21 | 2018-09-21 | 天津大学 | A kind of Remote Sensing Target detection method based on deep learning |
CN109800755A (en) * | 2018-12-14 | 2019-05-24 | 中国科学院深圳先进技术研究院 | A kind of remote sensing image small target detecting method based on Analysis On Multi-scale Features |
CN110288017A (en) * | 2019-06-21 | 2019-09-27 | 河北数云堂智能科技有限公司 | High-precision cascade object detection method and device based on dynamic structure optimization |
CN110956157A (en) * | 2019-12-14 | 2020-04-03 | 深圳先进技术研究院 | Deep learning remote sensing image target detection method and device based on candidate frame selection |
CN111553212A (en) * | 2020-04-16 | 2020-08-18 | 中国科学院深圳先进技术研究院 | Remote sensing image target detection method based on smooth frame regression function |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110211097B (en) * | 2019-05-14 | 2021-06-08 | 河海大学 | Crack image detection method based on fast R-CNN parameter migration |
-
2020
- 2020-04-16 CN CN202010302996.7A patent/CN111553212B/en active Active
- 2020-12-28 WO PCT/CN2020/140022 patent/WO2021208502A1/en active Application Filing
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020012451A1 (en) * | 2000-06-13 | 2002-01-31 | Ching-Fang Lin | Method for target detection and identification by using proximity pixel information |
CN108052940A (en) * | 2017-12-17 | 2018-05-18 | 南京理工大学 | SAR remote sensing images waterborne target detection methods based on deep learning |
CN108564109A (en) * | 2018-03-21 | 2018-09-21 | 天津大学 | A kind of Remote Sensing Target detection method based on deep learning |
CN109800755A (en) * | 2018-12-14 | 2019-05-24 | 中国科学院深圳先进技术研究院 | A kind of remote sensing image small target detecting method based on Analysis On Multi-scale Features |
CN110288017A (en) * | 2019-06-21 | 2019-09-27 | 河北数云堂智能科技有限公司 | High-precision cascade object detection method and device based on dynamic structure optimization |
CN110956157A (en) * | 2019-12-14 | 2020-04-03 | 深圳先进技术研究院 | Deep learning remote sensing image target detection method and device based on candidate frame selection |
CN111553212A (en) * | 2020-04-16 | 2020-08-18 | 中国科学院深圳先进技术研究院 | Remote sensing image target detection method based on smooth frame regression function |
Non-Patent Citations (3)
Title |
---|
CAI ZHAOWEI; VASCONCELOS NUNO: "Cascade R-CNN: Delving Into High Quality Object Detection", 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, IEEE, 18 June 2018 (2018-06-18), pages 6154 - 6162, XP033473531, DOI: 10.1109/CVPR.2018.00644 * |
SHENG YUAN: "Research on Object Detection Algorithm of Remote Sensing Images Based on Deep Learning", CHINESE MASTER'S THESES FULL-TEXT DATABASE, TIANJIN POLYTECHNIC UNIVERSITY, CN, 15 July 2020 (2020-07-15), CN , XP055857596, ISSN: 1674-0246 * |
WANG GUOWEN: "Pedestrian and Vehicle Detection Using Improved YOLOv3 Network with Multiscale Feature Fusion", CHINESE MASTER'S THESES FULL-TEXT DATABASE, TIANJIN POLYTECHNIC UNIVERSITY, CN, 15 February 2020 (2020-02-15), CN , XP055857603, ISSN: 1674-0246 * |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113920375A (en) * | 2021-11-01 | 2022-01-11 | 国网新疆电力有限公司营销服务中心(资金集约中心、计量中心) | Fusion characteristic typical load recognition method and system based on combination of Faster R-CNN and SVM |
CN114707532A (en) * | 2022-01-11 | 2022-07-05 | 中铁隧道局集团有限公司 | Ground penetrating radar tunnel disease target detection method based on improved Cascade R-CNN |
CN114707532B (en) * | 2022-01-11 | 2023-05-19 | 中铁隧道局集团有限公司 | Improved Cascade R-CNN-based ground penetrating radar tunnel disease target detection method |
CN114792300B (en) * | 2022-01-27 | 2024-02-20 | 河南大学 | X-ray broken needle detection method based on multi-scale attention |
CN114792300A (en) * | 2022-01-27 | 2022-07-26 | 河南大学 | Multi-scale attention X-ray broken needle detection method |
CN114529552A (en) * | 2022-03-03 | 2022-05-24 | 北京航空航天大学 | Remote sensing image building segmentation method based on geometric contour vertex prediction |
CN114925387A (en) * | 2022-04-02 | 2022-08-19 | 北方工业大学 | Sorting system and method based on end edge cloud architecture and readable storage medium |
CN114925387B (en) * | 2022-04-02 | 2024-06-07 | 北方工业大学 | Sorting system, method and readable storage medium based on end-edge cloud architecture |
CN114757970A (en) * | 2022-04-15 | 2022-07-15 | 合肥工业大学 | Multi-level regression target tracking method and system based on sample balance |
CN114757970B (en) * | 2022-04-15 | 2024-03-08 | 合肥工业大学 | Sample balance-based multi-level regression target tracking method and tracking system |
CN115170883A (en) * | 2022-07-19 | 2022-10-11 | 哈尔滨市科佳通用机电股份有限公司 | Method for detecting loss fault of brake cylinder piston push rod open pin |
CN115170883B (en) * | 2022-07-19 | 2023-03-14 | 哈尔滨市科佳通用机电股份有限公司 | Brake cylinder piston push rod opening pin loss fault detection method |
CN116645523B (en) * | 2023-07-24 | 2023-12-01 | 江西蓝瑞存储科技有限公司 | Rapid target detection method based on improved RetinaNet |
CN116645523A (en) * | 2023-07-24 | 2023-08-25 | 济南大学 | Rapid target detection method based on improved RetinaNet |
Also Published As
Publication number | Publication date |
---|---|
CN111553212A (en) | 2020-08-18 |
CN111553212B (en) | 2022-02-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021208502A1 (en) | Remote-sensing image target detection method based on smooth bounding box regression function | |
CN110059554B (en) | Multi-branch target detection method based on traffic scene | |
Yang et al. | Real-time face detection based on YOLO | |
CN109117876B (en) | Dense small target detection model construction method, dense small target detection model and dense small target detection method | |
CN110070074B (en) | Method for constructing pedestrian detection model | |
CN110796186A (en) | Dry and wet garbage identification and classification method based on improved YOLOv3 network | |
CN110033473B (en) | Moving target tracking method based on template matching and depth classification network | |
JP5227888B2 (en) | Person tracking method, person tracking apparatus, and person tracking program | |
CN111723798B (en) | Multi-instance natural scene text detection method based on relevance hierarchy residual errors | |
CN110930387A (en) | Fabric defect detection method based on depth separable convolutional neural network | |
CN112767357A (en) | Yolov 4-based concrete structure disease detection method | |
CN107844785A (en) | A kind of method for detecting human face based on size estimation | |
CN107909027A (en) | It is a kind of that there is the quick human body target detection method for blocking processing | |
CN109284779A (en) | Object detecting method based on the full convolutional network of depth | |
CN113435282B (en) | Unmanned aerial vehicle image ear recognition method based on deep learning | |
CN109087261A (en) | Face antidote based on untethered acquisition scene | |
CN111860587A (en) | Method for detecting small target of picture | |
WO2023160666A1 (en) | Target detection method and apparatus, and target detection model training method and apparatus | |
CN117495735B (en) | Automatic building elevation texture repairing method and system based on structure guidance | |
CN114529552A (en) | Remote sensing image building segmentation method based on geometric contour vertex prediction | |
CN113850761A (en) | Remote sensing image target detection method based on multi-angle detection frame | |
CN113496480A (en) | Method for detecting weld image defects | |
CN113627302B (en) | Ascending construction compliance detection method and system | |
CN110276358A (en) | High similarity wooden unit cross section detection method under intensive stacking | |
CN112199984B (en) | Target rapid detection method for large-scale remote sensing image |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20930942 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20930942 Country of ref document: EP Kind code of ref document: A1 |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20930942 Country of ref document: EP Kind code of ref document: A1 |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 04.07.2023) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20930942 Country of ref document: EP Kind code of ref document: A1 |