CN111127506A - Sequence image-based marine moving target comprehensive detection method - Google Patents
Sequence image-based marine moving target comprehensive detection method Download PDFInfo
- Publication number
- CN111127506A CN111127506A CN201911137190.0A CN201911137190A CN111127506A CN 111127506 A CN111127506 A CN 111127506A CN 201911137190 A CN201911137190 A CN 201911137190A CN 111127506 A CN111127506 A CN 111127506A
- Authority
- CN
- China
- Prior art keywords
- target
- delta
- cloud
- trail
- white point
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/207—Analysis of motion for motion estimation over a hierarchy of resolutions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a sequence image-based marine moving target comprehensive detection method, belonging to the field of remote sensing satellite image processing and application; step one, shooting the sea surface; judging whether the single-frame image has a cloud layer or not; step two, setting a cloud layer gradient detection function delta (delta); when delta (delta) is 1, entering a step three; when delta (delta) is 0, entering a step four; step three, sequentially carrying out cloud removal, hole filling and target enhancement processing on the image; entering the step five; step four, performing multi-frame continuous image shooting, determining a target white point by adopting a clustering method, and performing cloud removal and target enhancement processing on other interference target points; step five, when the target white point and the trail exist simultaneously, the target ship detection and the determination of the target ship motion direction are completed, and the speed of the target ship is calculated; the invention judges the motion direction and the motion state of the target through multi-frame detection, solves the influence of most marine clouds on the false alarm of target detection, and improves the detection probability.
Description
Technical Field
The invention belongs to the field of remote sensing satellite image processing and application, and relates to a sequence image-based marine moving target comprehensive detection method.
Background
CN201810513672.0 is a moving ship detecting and tracking method based on satellite sequence images. The method provided by the invention does not provide a solution to cloud layer interference, various cloud layer interferences are common in the optical image of the sea surface, the probability of no cloud is less, and the applicability of the method is restricted.
A method for rapidly detecting a ship moving on the sea surface by a stationary orbit remote sensing satellite in the No. 8 of volume 37 of No. 8 of month 8 in 2015. This document proposes a moving ship detection algorithm using sequence images, but this method does not mention a false alarm removal method for cloud states.
CN201310256096.3 optical remote sensing image ship detection method with cloud layer interference. The method is suitable for the image with medium resolution (about 10 m) by taking geometric characteristics as a main judgment basis, but is restricted by losing the geometric characteristics of the target in the image of the high-orbit optical satellite with 50m resolution.
A marine ship target detection method capable of resisting the interference of broken clouds is disclosed in No. 12 of volume 32 of 2010, computer engineering and science. The method has the core that the ship trail is detected through radon transformation to eliminate the false alarm of broken clouds, but the ship trail is difficult to embody for a high-orbit optical satellite with low resolution, and the method is restricted.
In 2007, 43 rd volume 14 th of volume 43, a novel real-time detection method for a marine moving target is provided, a method for detecting a target on an imaging sequence in a visible light range is provided, and rapid anti-interference target detection is realized by using a deformed time difference method.
In the No. 48 No. 1 of the No. 2008 telecommunication technology, a ship detection method based on wavelet direction filtering and provided with cloud layer remote sensing images is provided. The method is used for eliminating cloud layer interference by means of fusion of wavelet decomposition and directional filtering of the detection direction of the image, and finally achieving target detection in a remote sensing image with cloud layer interference, but is not suitable for eliminating the cloud breaking false alarm.
The northeast Master university newspaper: natural science edition 2009, vol 41, 6, 2, weak target detection algorithm research under cloud layer background based on OTSU segmentation. The maximum between-class variance OTSU segmentation algorithm is used for removing floating cloud interference in the background, and the calculation is simple and convenient. But this method is not applicable to broken cloud false alarm culling.
Disclosure of Invention
The technical problem solved by the invention is as follows: the method overcomes the defects of the prior art, provides a marine moving target comprehensive detection method based on sequence images, judges the moving direction and the moving state of the target through multi-frame detection, solves the influence of most marine cloud layers on target detection false alarm, and improves the detection probability.
The technical scheme of the invention is as follows:
a marine moving target comprehensive detection method based on sequence images comprises the following steps:
step one, shooting the sea surface through a high-orbit optical remote sensing satellite; judging whether the single-frame image has a cloud layer or not; entering a second step when the cloud layer exists; entering a fifth step when no cloud layer exists;
step two, setting a cloud layer gradient detection function delta (delta); judging the cloud layer condition according to the value of the cloud layer gradient detection function delta (delta); when the cloud layer gradient detection function delta (delta) is 1, entering a third step; when the cloud layer gradient detection function delta (delta) is 0, entering a step four;
step three, sequentially carrying out cloud removal, hole filling and target enhancement processing on the image; cloud layer weakening is realized; entering the step five;
step four, shooting multi-frame continuous images, and judging the motion directions of all target points according to the multi-frame images by adopting a clustering method; determining a target white point, and carrying out cloud removal and target enhancement processing on other interference target points; entering the step five;
judging whether a target white point and a trail exist or not; when the target white point and the trail exist simultaneously, the target ship detection and the determination of the target ship motion direction are completed, and the speed of the target ship is calculated; otherwise, returning to the step one.
In the above method for comprehensively detecting a moving object at sea based on a sequence image, in the second step, the cloud layer gradient detection function Δ (δ) is:
Δ(δ)＝Δ(X+)·Δ(X-)·Δ(Y+)·Δ(Y-)
wherein, X is the X-direction coordinate of the detected pixel in the image;
y is the Y-direction coordinate of the detected pixel in the image;
delta (X +) and delta (X-) are image gray gradient values of two adjacent positions of the pixel in the X direction;
delta (Y +) and delta (Y-) are image gray gradient values of two adjacent positions of the pixel in the Y direction;
the cloud layer gradient detection function delta (delta) is calculated by the following method:
setting a threshold value a according to experience; when the cloud layer gradient detection function delta (delta) is larger than a, enabling the delta (delta) to be 1; otherwise Δ (δ) is 0.
In the above method for comprehensively detecting a moving object at sea based on a sequence image, in the second step, when a cloud layer gradient detection function Δ (δ) is 1, cloud layers are continuously distributed, and interference terms to a white point and a trail of the object do not exist in the cloud layers; when the cloud layer gradient detection function delta (delta) is 0, the cloud layer is distributed in a broken cloud mode, and the broken cloud is an interference target point of a target white point and a target trail.
In the above method for comprehensively detecting a marine moving target based on a sequence image, in the fourth step, a specific method for determining a target white point is as follows:
judging the motion directions of all target points according to the multi-frame images; when the moving direction of one target point is inconsistent with that of other target points; the target point is the target white point; other targets are interference targets formed by the debris clouds.
In the above method for comprehensively detecting a moving object on the sea based on a sequence image, in the fifth step; the method for judging the trail comprises the following steps:
s1, when a target white point and a trail in a sharp wave shape exist and a trail tip points to the target white point; the target white point is the target ship; the pointed direction is the movement direction of the target ship;
s2, when a target white point and a linear-shaped trail exist and one end of the linear trail points to the target white point, the target white point is the target ship; the direction of the linear wake pointing to the target white point is the motion direction of the target ship.
In the above method for comprehensively detecting a moving object on the sea based on a sequence image, in S1, when the trail is in the shape of a sharp wave, the included angle of the sharp wave is 32 ° -39 °, and the track is determined to be valid.
In the above method for comprehensively detecting a moving object at sea based on a sequence image, in S2, when the trail is in a linear shape and the length of the trail is 3 times or more of the length of the target white point, it is determined that the trail is valid.
In the above method for comprehensively detecting a moving target on the sea based on a sequence image, the method for calculating the speed of the target ship comprises the following steps: and (4) carrying out progressive association calculation according to the continuous multi-frame images to obtain the speed of the target ship.
Compared with the prior art, the invention has the beneficial effects that:
(1) the invention adopts a brand-new processing flow to meet the requirement of detecting the high-orbit optical satellite sequence image ship target. The sequence image of the high orbit optical satellite is not a video image, the frame frequency is as low as 3-5 minutes/frame, in order to rapidly obtain the motion state of the target, generally only 5-10 frames are continuously obtained, a large number of samples cannot be provided, and the traditional video image moving target detection means cannot be effectively used. The high time resolution of the high orbit optical satellite is beneficial to realizing the continuous tracking and monitoring of the moving target on the sea surface. The detection of the moving target on the sea surface can be realized by effectively processing the sequence images in the same area;
(2) the invention improves the detection rate of the ship target and reduces the false alarm rate caused by interference of broken clouds and the like. Due to the fact that the distance from the earth is far, the resolution ratio of the high orbit satellite is poor, the state of the sea surface moving target is similar to broken clouds and reefs, and the false alarm rate of a common detection algorithm is high. The static and dynamic combined comprehensive processing flow effectively reduces the occurrence of false alarms;
(3) the invention integrates various detection means such as single-frame image ship trail detection, target detection under cloud interference reduction of sequence images, sequence image moving target detection and the like. The trail detection effectively confirms the moving ship target, the influence of cloud layers and broken clouds can be effectively reduced by a sequence image gradient change detection and clustering method, and the state of the moving target can be estimated and predicted by the sequence image moving target detection;
(4) the method is used for processing the high orbit satellite sequence image, can be used for ship target detection in important areas, and provides important reference data for industries such as national defense construction, shipping management, fishery management and the like.
Drawings
FIG. 1 is a flow chart of the comprehensive detection of the marine moving target of the invention;
FIG. 2 is a schematic view of the linear trail of the present invention showing the target form of the moving ship;
fig. 3 is a schematic diagram of the target form of the kelvin trail of the sports vessel of the present invention.
Detailed Description
The invention is further illustrated by the following examples.
The invention provides a comprehensive detection method for a marine moving target facing a high-orbit optical satellite sequence image. The method considers the data characteristics of high orbit optical satellite sequence images, combines a relatively mature static image ship detection means and an image processing technology, adopts a static-dynamic combination mode to improve the detection probability of sea surface moving objects, carries out classification processing on cloud areas when processing sea surface cloud layer interference, and reduces the false alarm rate. The method is used for the sequence images which are preprocessed, and the preprocessing content comprises the following steps: geometric correction and radiation correction of each frame image, and pixel-level registration, sea-land segmentation and sea-island segmentation among sequence images. Wherein, the radiation correction needs to consider the dynamic range adjustment problem under the ocean background besides correcting the system error; the pixel level registration mainly considers the elimination of imaging position errors caused by orbit perturbation and attitude jitter in the imaging process.
As shown in fig. 1, the method for comprehensively detecting a moving object on the sea based on a sequence image mainly includes the following steps:
step one, shooting the sea surface through a high-orbit optical remote sensing satellite; judging whether the single-frame image has a cloud layer or not; entering a second step when the cloud layer exists; entering a fifth step when no cloud layer exists; in the high-orbit optical remote sensing satellite, other types of trails are not obvious, and the motion direction of the moving target can be directly locked only by using a single-frame image through trail detection, and then the searching is carried out in the sequence image along the motion direction of the target, so that the detection and motion state estimation of the moving target can be rapidly completed.
And step two, sea surface moving object detection for eliminating cloud layer interference. For the areas covered by the cloud layers, the detection cannot be directly carried out, and the cloud layers need to be classified firstly and then processed respectively according to the characteristics of the cloud layers and the target. The specific process is as follows: firstly, cloud cover characteristic classification is carried out, the area which is continuously covered by thick cloud and has no target bulge is continuously subjected to gradient change in the cloud range and is undoubtedly similar to a target area, cloud removal and hole filling processing are directly adopted for the area, and target detection operation is not needed; continuously changing gradient and forming a suspected target area in a continuous thick cloud area in which a target is raised, and performing target enhancement and cloud layer inhibition treatment on the suspected target area; for a plurality of fragments of cloud areas, judging the overall movement direction of the fragments of cloud by using a multi-frame image and adopting a clustering method, and selecting a target point which is inconsistent with the overall movement direction of the cloud as a suspected target; for a single-chip clouding (or independent suspected moving ship target) area, a multi-frame image is used for detecting whether the form and the gray scale of the single-chip clouding (or independent suspected moving ship target) area are changed or not, so that suspected possibility is eliminated. Setting a cloud layer gradient detection function delta (delta); judging the cloud layer condition according to the value of the cloud layer gradient detection function delta (delta); when the cloud layer gradient detection function delta (delta) is 1, entering a third step; when the cloud layer gradient detection function delta (delta) is 0, entering a step four; the cloud gradient detection function Δ (δ) is:
Δ(δ)＝Δ(X+)·Δ(X-)·Δ(Y+)·Δ(Y-)
wherein, X is the X-direction coordinate of the detected pixel in the image;
y is the Y-direction coordinate of the detected pixel in the image;
delta (X +) and delta (X-) are image gray gradient values of two adjacent positions of the pixel in the X direction;
delta (Y +) and delta (Y-) are image gray gradient values of two adjacent positions of the pixel in the Y direction;
the cloud layer gradient detection function delta (delta) is calculated by the following method:
the detection threshold of Δ (δ) may be determined by calculation or machine learning, or the like. If the image gray gradient matrix is calculated, determining a threshold value by using a certain numerical calculation method, wherein the threshold value is defined as the 4 th power of the mean value of the gray gradient matrix of the image in the selected area; if a machine learning method is adopted, a support vector machine model can be learned based on labeled training samples with violent change/gentle change: in the testing stage, the gradient characteristics of the model and the current sample are utilized to determine the type with violent/gentle change, and the violent change is higher than a threshold value; the gradual change is lower than the threshold value. Setting a threshold value a; when the cloud layer gradient detection function delta (delta) is larger than a, enabling the delta (delta) to be 1; otherwise Δ (δ) is 0. When the cloud layer gradient detection function delta (delta) is 1, the cloud layers are continuously distributed, and interference terms to the target white point and the tail trace do not exist in the cloud layers; when the cloud layer gradient detection function delta (delta) is 0, the cloud layer is distributed in a broken cloud mode, and the broken cloud is an interference target point of a target white point and a target trail.
Step three, sequentially carrying out cloud removal, hole filling and target enhancement processing on the image; cloud layer weakening is realized; entering the step five;
step four, shooting multi-frame continuous images, and judging the motion directions of all target points according to the multi-frame images by adopting a clustering method; the specific method for determining the target white point comprises the following steps: judging the motion directions of all target points according to the multi-frame images; when the moving direction of one target point is inconsistent with that of other target points; the target point is the target white point; if the moving direction of the target in the multi-frame image accords with the general ship moving characteristics (the moving direction between adjacent image frames is stable, the moving track has no break angle larger than 90 degrees) and the brightness of the target in the image has no obvious change, the suspected target can be confirmed to be a moving ship target, and the track is marked. Other targets are interference targets formed by the debris clouds. Carrying out cloud removal and target enhancement processing on other interference target points; entering the step five;
judging whether a target white point and a trail exist or not; the method for judging the trail comprises the following steps:
s1, when a target white point and a trail in a sharp wave shape exist and a trail tip points to the target white point; the target white point is the target ship; the pointed direction is the movement direction of the target ship; when the trail is in the shape of a sharp wave, the included angle of the sharp wave is 32-39 degrees, and the trail is judged to be effective, as shown in fig. 3.
S2, when a target white point and a linear-shaped trail exist and one end of the linear trail points to the target white point, the target white point is the target ship; the direction of the linear wake pointing to the target white point is the motion direction of the target ship. When the trail is linear, the trail is judged to be valid when the trail length is more than 3 times of the target white point length, as shown in fig. 2. When the target white point and the trail exist simultaneously, the target ship detection and the determination of the target ship motion direction are completed, and the speed of the target ship is calculated; the calculation method of the target ship speed comprises the following steps: and (4) carrying out progressive association calculation according to the continuous multi-frame images to obtain the speed of the target ship. Otherwise, returning to the step one.
Although the present invention has been described with reference to the preferred embodiments, it is not intended to limit the present invention, and those skilled in the art can make variations and modifications of the present invention without departing from the spirit and scope of the present invention by using the methods and technical contents disclosed above.
Claims (8)
1. A marine moving target comprehensive detection method based on sequence images is characterized by comprising the following steps: the method comprises the following steps:
step one, shooting the sea surface through a high-orbit optical remote sensing satellite; judging whether the single-frame image has a cloud layer or not; entering a second step when the cloud layer exists; entering a fifth step when no cloud layer exists;
step two, setting a cloud layer gradient detection function delta (delta); judging the cloud layer condition according to the value of the cloud layer gradient detection function delta (delta); when the cloud layer gradient detection function delta (delta) is 1, entering a third step; when the cloud layer gradient detection function delta (delta) is 0, entering a step four;
step three, sequentially carrying out cloud removal, hole filling and target enhancement processing on the image; cloud layer weakening is realized; entering the step five;
step four, shooting multi-frame continuous images, and judging the motion directions of all target points according to the multi-frame images by adopting a clustering method; determining a target white point, and carrying out cloud removal and target enhancement processing on other interference target points; entering the step five;
judging whether a target white point and a trail exist or not; when the target white point and the trail exist simultaneously, the target ship detection and the determination of the target ship motion direction are completed, and the speed of the target ship is calculated; otherwise, returning to the step one.
2. The marine moving object comprehensive detection method based on the sequence image as claimed in claim 1, characterized in that: in the second step, the cloud layer gradient detection function Δ (δ) is:
Δ(δ)＝Δ(X+)·Δ(X-)·Δ(Y+)·Δ(Y-)
wherein, X is the X-direction coordinate of the detected pixel in the image;
y is the Y-direction coordinate of the detected pixel in the image;
delta (X +) and delta (X-) are image gray gradient values of two adjacent positions of the pixel in the X direction;
delta (Y +) and delta (Y-) are image gray gradient values of two adjacent positions of the pixel in the Y direction;
the cloud layer gradient detection function delta (delta) is calculated by the following method:
setting a threshold value a according to experience; when the cloud layer gradient detection function delta (delta) is larger than a, enabling the delta (delta) to be 1; otherwise Δ (δ) is 0.
3. The marine moving object comprehensive detection method based on the sequence image as claimed in claim 2, characterized in that: in the second step, when the cloud layer gradient detection function delta (delta) is 1, the cloud layers are continuously distributed, and interference terms to the target white point and the tail trace do not exist in the cloud layers; when the cloud layer gradient detection function delta (delta) is 0, the cloud layer is distributed in a broken cloud mode, and the broken cloud is an interference target point of a target white point and a target trail.
4. The marine moving object comprehensive detection method based on the sequence image as claimed in claim 3, characterized in that: in the fourth step, a specific method for determining the target white point is as follows:
judging the motion directions of all target points according to the multi-frame images; when the moving direction of one target point is inconsistent with that of other target points; the target point is the target white point; other targets are interference targets formed by the debris clouds.
5. The marine moving object comprehensive detection method based on the sequence image as claimed in claim 4, characterized in that: in the fifth step; the method for judging the trail comprises the following steps:
s1, when a target white point and a trail in a sharp wave shape exist and a trail tip points to the target white point; the target white point is the target ship; the pointed direction is the movement direction of the target ship;
s2, when a target white point and a linear-shaped trail exist and one end of the linear trail points to the target white point, the target white point is the target ship; the direction of the linear wake pointing to the target white point is the motion direction of the target ship.
6. The marine moving object comprehensive detection method based on the sequence image as claimed in claim 5, characterized in that: in the step S1, when the trail is in the shape of a sharp wave, the included angle of the sharp wave is 32 ° -39 °, and the trail is determined to be valid.
7. The marine moving object comprehensive detection method based on the sequence image as claimed in claim 6, characterized in that: in S2, when the trail is linear, the trail is determined to be valid when the trail length is 3 times or more the target white point length.
8. The marine moving object comprehensive detection method based on the sequence image as claimed in claim 7, characterized in that: the calculation method of the target ship speed comprises the following steps: and (4) carrying out progressive association calculation according to the continuous multi-frame images to obtain the speed of the target ship.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911137190.0A CN111127506B (en) | 2019-11-19 | 2019-11-19 | Marine moving target comprehensive detection method based on sequence image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911137190.0A CN111127506B (en) | 2019-11-19 | 2019-11-19 | Marine moving target comprehensive detection method based on sequence image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111127506A true CN111127506A (en) | 2020-05-08 |
| CN111127506B CN111127506B (en) | 2023-06-06 |
Family
ID=70495800
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911137190.0A Active CN111127506B (en) | 2019-11-19 | 2019-11-19 | Marine moving target comprehensive detection method based on sequence image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111127506B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113393571A (en) * | 2021-06-15 | 2021-09-14 | 北京市遥感信息研究所 | Cloud-free satellite image generation method and device |
| CN113393497A (en) * | 2021-07-07 | 2021-09-14 | 中国人民解放军海军航空大学 | Ship target tracking method, device and equipment of sequence remote sensing image under condition of broken clouds |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101246545A (en) * | 2008-02-22 | 2008-08-20 | 华南师范大学 | Possion method for removing cloud from optical remote sensing image |
| WO2016101279A1 (en) * | 2014-12-26 | 2016-06-30 | 中国海洋大学 | Quick detecting method for synthetic aperture radar image of ship target |
| CN109815871A (en) * | 2019-01-16 | 2019-05-28 | 中国科学院电子学研究所 | The detection of target naval vessel and tracking based on remote sensing image |
-
2019
- 2019-11-19 CN CN201911137190.0A patent/CN111127506B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101246545A (en) * | 2008-02-22 | 2008-08-20 | 华南师范大学 | Possion method for removing cloud from optical remote sensing image |
| WO2016101279A1 (en) * | 2014-12-26 | 2016-06-30 | 中国海洋大学 | Quick detecting method for synthetic aperture radar image of ship target |
| CN109815871A (en) * | 2019-01-16 | 2019-05-28 | 中国科学院电子学研究所 | The detection of target naval vessel and tracking based on remote sensing image |
Non-Patent Citations (2)
| Title |
|---|
| 莫金花等: "全局-局部联合滤波的红外小目标背景抑制方法", 《中国体视学与图像分析》 * |
| 陈海亮等: "一种抗碎云干扰的海上舰船目标检测方法", 《计算机工程与科学》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113393571A (en) * | 2021-06-15 | 2021-09-14 | 北京市遥感信息研究所 | Cloud-free satellite image generation method and device |
| CN113393571B (en) * | 2021-06-15 | 2023-06-27 | 北京市遥感信息研究所 | Cloud-free satellite image generation method and device |
| CN113393497A (en) * | 2021-07-07 | 2021-09-14 | 中国人民解放军海军航空大学 | Ship target tracking method, device and equipment of sequence remote sensing image under condition of broken clouds |
| CN113393497B (en) * | 2021-07-07 | 2022-08-09 | 中国人民解放军海军航空大学 | Ship target tracking method, device and equipment of sequence remote sensing image under condition of broken clouds |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111127506B (en) | 2023-06-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110084210B (en) | SAR image multi-scale ship detection method based on attention pyramid network | |
| CN110232350B (en) | Real-time water surface multi-moving-object detection and tracking method based on online learning | |
| CN101214851B (en) | Intelligent all-weather actively safety early warning system and early warning method thereof for ship running | |
| CN111738112B (en) | Remote sensing ship image target detection method based on deep neural network and self-attention mechanism | |
| Li et al. | Infrared maritime dim small target detection based on spatiotemporal cues and directional morphological filtering | |
| CN102279973B (en) | Sea-sky-line detection method based on high gradient key points | |
| CN112560671B (en) | Ship detection method based on rotary convolution neural network | |
| CN111476159A (en) | Method and device for training and detecting detection model based on double-angle regression | |
| CN112487912B (en) | Arbitrary direction ship detection method based on improved YOLOv3 | |
| CN113920436A (en) | Remote sensing image marine vessel recognition system and method based on improved YOLOv4 algorithm | |
| CN113657252B (en) | Efficient SAR image ship target detection method based on encoding and decoding device | |
| CN111127506A (en) | Sequence image-based marine moving target comprehensive detection method | |
| Kong et al. | Lightweight algorithm for multi-scale ship detection based on high-resolution SAR images | |
| Zhang et al. | Nearshore vessel detection based on Scene-mask R-CNN in remote sensing image | |
| CN116343113A (en) | Method and system for detecting oil spill based on polarized SAR characteristics and coding and decoding network | |
| Zhou et al. | Automatic ship detection in SAR Image based on Multi-scale Faster R-CNN | |
| CN117994666A (en) | Sea ice identification method combining residual error network and edge detection | |
| Xu et al. | Marine radar oil-spill monitoring through local adaptive thresholding | |
| CN112766286B (en) | Ship target detection method based on global-local features of SAR image | |
| Jia et al. | A fast progressive ship detection method for very large full-scene SAR images | |
| CN117456163A (en) | Ship target detection method, system and storage medium | |
| Li et al. | Overview of deep convolutional neural network approaches for satellite remote sensing ship monitoring technology | |
| CN108876807A (en) | A kind of real-time piggyback satellite image motion object detection tracking | |
| Jiang et al. | YOLOv7-Ship: A Lightweight Algorithm for Ship Object Detection in Complex Marine Environments | |
| Fan et al. | A coarse-to-fine vehicle detection in large SAR scenes based on GL-CFAR and PRID R-CNN |
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 |