WO2019132131A1 - 사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템 및 그 분석 방법 - Google Patents
사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템 및 그 분석 방법 Download PDFInfo
- Publication number
- WO2019132131A1 WO2019132131A1 PCT/KR2018/005628 KR2018005628W WO2019132131A1 WO 2019132131 A1 WO2019132131 A1 WO 2019132131A1 KR 2018005628 W KR2018005628 W KR 2018005628W WO 2019132131 A1 WO2019132131 A1 WO 2019132131A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- wavelength
- ship
- unit
- module
- Prior art date
Links
- 238000010191 image analysis Methods 0.000 title claims abstract description 66
- 238000012545 processing Methods 0.000 claims abstract description 57
- 238000003860 storage Methods 0.000 claims abstract description 10
- 238000005286 illumination Methods 0.000 claims abstract description 3
- 238000001514 detection method Methods 0.000 claims description 94
- 238000012800 visualization Methods 0.000 claims description 46
- 238000000034 method Methods 0.000 claims description 43
- 238000004458 analytical method Methods 0.000 claims description 26
- 230000003287 optical effect Effects 0.000 claims description 14
- 239000000428 dust Substances 0.000 claims description 11
- 230000000877 morphologic effect Effects 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 10
- 239000000779 smoke Substances 0.000 claims description 10
- 238000003709 image segmentation Methods 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 6
- 239000002245 particle Substances 0.000 claims description 5
- 238000007476 Maximum Likelihood Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 2
- 230000007613 environmental effect Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 7
- 230000003595 spectral effect Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000012790 confirmation Methods 0.000 description 2
- 230000007123 defense Effects 0.000 description 2
- 230000008676 import Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 238000004611 spectroscopical analysis Methods 0.000 description 2
- 238000002834 transmittance Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241001474374 Blennius Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 230000009429 distress Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000003703 image analysis method Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000003595 mist Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004297 night vision Effects 0.000 description 1
- 230000010287 polarization Effects 0.000 description 1
- 239000013535 sea water Substances 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012360 testing 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
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2323—Non-hierarchical techniques based on graph theory, e.g. minimum spanning trees [MST] or graph cuts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/143—Segmentation; Edge detection involving probabilistic approaches, e.g. Markov random field [MRF] modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
- G06V10/7635—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks based on graphs, e.g. graph cuts or spectral clustering
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/10—Cameras or camera modules comprising electronic image sensors; Control thereof for generating image signals from different wavelengths
- H04N23/11—Cameras or camera modules comprising electronic image sensors; Control thereof for generating image signals from different wavelengths for generating image signals from visible and infrared light wavelengths
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/20—Cameras or camera modules comprising electronic image sensors; Control thereof for generating image signals from infrared radiation only
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/30—Transforming light or analogous information into electric information
- H04N5/33—Transforming infrared radiation
-
- 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
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/194—Terrestrial scenes using hyperspectral data, i.e. more or other wavelengths than RGB
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N2209/00—Details of colour television systems
- H04N2209/04—Picture signal generators
- H04N2209/041—Picture signal generators using solid-state devices
- H04N2209/042—Picture signal generators using solid-state devices having a single pick-up sensor
- H04N2209/047—Picture signal generators using solid-state devices having a single pick-up sensor using multispectral pick-up elements
Definitions
- the present invention relates to a multi-wavelength image analysis electro-optical system and an analysis method thereof. More particularly, the present invention relates to a multi-wavelength image analysis electro-optical system and an analysis method thereof, And more particularly, to a multi-wavelength image analysis-based detection system and method for visualizing a search object using image information of a selective wavelength band according to conditions or physical conditions of a detection object.
- the search for missing persons and accident vessels carried out by the domestic search agencies is conducted using a search platform (ship, airplane) with visual search / visible camera (daytime) and an infrared camera .
- the electro-optic equipment used in the search of marine accidents in Korea is limited to the color image in the daytime and to the function of obtaining the thermal image in the nighttime, and the functions such as fog, fine dust, In marine environmental conditions, which are difficult to detect, there is a disadvantage in that the detection probability is low because the utilization of the equipment is limited.
- the visibility camera which is a daytime image camera
- the infrared camera which is a night vision camera
- the infrared camera is integrated and developed by introducing products from abroad.
- electrooptical system using spectral image analysis which is a specialized method with high detection degree according to search object and search environment conditions, is utilized as search support equipment.
- optimized search images can be obtained, enabling quick search and rescue compared with existing search devices (radar, daytime camera, night camera, etc.).
- the US infrared-range electro-optical sensor is an item subject to import and export control regulations, and imports are limited for private development except for the public or research. Therefore, The international competitiveness of domestic companies in the development market is currently very low.
- a search platform such as an aircraft or a ship is mobilized.
- the detection resolution resolution
- an active sensor such as a radar
- An electro-optic sensor having a relatively high level is mainly used.
- the currently used electro-optical sensors have a limitation in utilization in dark conditions without natural light or misty or rainy conditions, and when the size and color of the object to be detected do not differ from the surrounding environment, they are separated from each other.
- U.S. Patent No. 8300108 relates to a multi-channel imaging device that uses a single focal plane array (FPA) to provide improved object identification methods and methods for identifying and identifying high resolution infrared images with polarization information, broadband fan color intensity levels, and multi- Lt; / RTI >
- FPA focal plane array
- certain embodiments increase the size of the filters used to filter image content and reduce complexity, thereby reducing manufacturing and production costs.
- subpixel parallax is used to generate a high resolution image, to provide a range estimate of the target, and to distinguish moving objects from background disturbances.
- a conventional technique such as US 8300108 must overcome the following two conditions.
- the first is a detectable marine environmental condition.
- conventional electro-optical sensors which are designed for daytime environments with good weather conditions and sufficient light intensity
- nighttime environments with limited light intensity by using multi-wavelength band images acquired through ultra-low-light visible wide-band image sensors and additional infrared band sensors
- the second is the separation of the detected object.
- the detection is performed using only the difference between the observed values of the target object (ship, submerger) and the background (sea water) at the time of the sea detection, If the absolute value characteristics within the range are similar, detection is not performed or false detection is made.
- the detection rate largely degrades because it is impossible to acquire most observation values in the image or the difference of the image observation values is not clear.
- multi-wavelength image including observation values of the selected wavelength band using the ultra-low light intensity sensor and filter for converting and amplifying the limited optical signal, and additional three infrared bands (long wavelength, medium wave and short wavelength infrared) , It is necessary to be able to detect the target object which is optimized in a limited marine accident environment condition.
- the present invention provides a multi-wavelength image analysis electro-optical system for detecting a ship and a dehydrator capable of improving the detection rate of an accident vessel and a deceased person, and an analysis method thereof.
- a multi-wavelength image analysis electro-optical system for detecting a ship and a dehydrator, the multi-wavelength image analyzing electronic optical system for detecting a ship and a dehydrator,
- An input unit having a medium-wave infrared image sensor and a long-wavelength infrared image sensor;
- a signal processing unit for receiving and processing data of the input unit;
- a display unit for receiving and displaying data of the signal processing unit;
- a storage unit for storing data of the signal processing unit and the display unit;
- a control unit having a camera control board and a drive control board and controlling the input unit, the signal processing unit, the display unit, and the storage unit.
- the camera control board may include an EMCCD module, a VIS filter control module, and an EMCCD zoom lens module.
- the camera control board may include an LWIR module, an MWIR module, and an SWIR module.
- the drive control board may include a fan motor driver and a fan motor encoder.
- the drive control board may include a tilt motor driver and a tilt motor encoder.
- the camera control board and the drive control board may receive a control signal from the signal processing board.
- the signal processing board can receive a control signal from a user UI.
- the input unit may include an image receiving unit, and the image receiving unit may further include a visible light image receiving module, an infrared image receiving module, and an image conformity checking module.
- the signal processing unit may include an image analysis unit, and the image analysis unit may further include a multispectral library module, a multispectral mixture analysis module, and a process result integration module.
- the display unit may include an image visualization unit, and the image visualization unit may further include a multi-wavelength image visualization module, an infrared image visualization module, and an integrated image visualization module.
- a method for analyzing a multi-wavelength image analyzing electronic optical system for detecting a ship and a dehydrator Receiving an airborne multi-wavelength image in which the image receiving unit observes; (b) generating an original image for each of the signal processing and wavelength by the image analysis unit; And (c) applying a marine object detection algorithm for image feature-based feature detection and optimal threshold-based detection; And (d) visualizing the detection object image by the image visualization unit 300; . ≪ / RTI >
- the step (a) may include: (a-1) using a short-wave infrared sensor having a wavelength of 1 to 2.5 .mu.m, which is longer than particles of mist, fine dust, and smoke; And (a-2) using a long-wave infrared (LWIR) sensor with a wavelength of 8 to 14 um, which is longer than a short-wave infrared (SWIR) sensor, in a low illumination environment; As shown in FIG.
- the step (c) includes the steps of: (c-1) detecting the feature detection based on the multi-wavelength image based on the feature detection based on the feature vector of each pixel for image segmentation,
- the method may further include estimating parameters for determining the probability model using a statistical method, or performing a segmentation using a cluster algorithm based on the similarity between the feature vectors, assuming a probability model.
- the algorithm for detecting a feature based feature based on the multi-wavelength image (c-1) detects the maximum likelihood for an unknown parameter in incomplete data, To obtain a maximum value of the maximum value.
- the algorithm for detecting an object of optimal threshold-based detection based on the multi-wavelength image is performed by mixing histograms of a Gaussian function and an original image formed around all level values of an image And an optimized image segmentation technique that sets a threshold value through a new histogram of the image can be used.
- the step (d) includes the steps of (d-1) displaying and storing the aviation visible light image inputted in a visible light image visualization module by selecting a specific band (for example, RGB) in an image form; And (d-2) displaying and storing an aerial infrared image in an image form in an infrared image visualization module; As shown in FIG.
- the integrated visualization module may further include a step of visualizing the position of the detection object by visualizing the position of the detection object, have.
- the aerial observation multi-wavelength image that has undergone the preprocessing process in the image reception unit and the object to be detected in the corresponding area are displayed as images in time, Displaying them together in a text form; As shown in FIG.
- the integrated image visualization module divides the detection result according to classification, and displays and stores the detection result in a tabular form together with detailed information such as type, material, As shown in FIG.
- a computer readable recording medium storing a program for implementing an analysis method of a multi-wavelength image analysis electro optical system for detecting a ship and a dehydrator.
- the present invention by using the multi-wavelength band image acquired through the ultra-low-illuminance visible-light-range image sensor and the additional infrared-ray sensor, it is possible to reduce the amount of smoke due to fog, It is possible to operate under the conditions that occur.
- multi-wavelength images including observation values of the selected wavelength band using the ultra-low light intensity sensor and filter for converting and amplifying the limited optical signal, and additional three infrared bands (long wavelength, medium wave and short wavelength infrared) , It is possible to detect an object to be optimized in a limited marine accident environment condition.
- FIG. 1 (a) to 1 (c) illustrate a method of acquiring an airborne multi-wavelength image, a method of analyzing a video image of an airborne multi-wavelength image, Fig.
- Fig. 2 is a photograph showing images taken by selecting sensors having high fog (a), fine dust (b), smoke (c), and high transmittance according to environmental conditions.
- 3 is a graph showing SWIR, MWIR, and LWIR regions of multiple wavelengths.
- Fig. 4 is a schematic diagram in which a search area of the sea is set according to the size (small, medium, large) of the ship and the flooded state of the missing person (state 1, state 2, state 3).
- FIG. 5 is a photograph of a multi-wavelength image analysis electro-optical system for detecting a ship and a dehydrator according to the present invention.
- FIG. 6 is a block diagram illustrating a multi-wavelength image analysis electro-optical system for detecting a ship and a dehydrator according to the present invention.
- FIG. 7 is a circuit diagram showing the connection of circuits of a multi-wavelength image analysis electro-optical system for detecting a ship and a dehydrator according to the present invention shown in FIG.
- FIG. 8 is a block diagram illustrating a signal processing unit of a multi-wavelength image analysis electro-optical system for detecting a ship and a dehydrator according to the present invention shown in FIG.
- FIG. 9 is a flowchart illustrating an analysis method of a multi-wavelength image analysis electro-optical system for detecting a ship and a dehydrator according to the present invention shown in FIG.
- FIG. 10 is a view of an embodiment of the result of the accident vessel and dehydrator detection displayed through the image visualization unit 300 of the multi-wavelength image analysis electro-optical system for detecting a ship and a dehydrator according to the present invention.
- the component may be directly connected or in contact with another component.
- the terms "part”, “unit”, “module”, “apparatus” and the like mean units capable of handling one or more functions or operations, if used.
- FIG. 1 (a) to 1 (c) illustrate a method of acquiring an airborne multi-wavelength image, a method of analyzing a video image of an airborne multi-wavelength image, Fig.
- Fig. 2 is a photograph showing images taken by selecting sensors having high fog (a), fine dust (b), smoke (c), and high transmittance according to environmental conditions.
- 3 is a graph showing SWIR, MWIR, and LWIR regions of multiple wavelengths.
- Fig. 4 is a schematic diagram in which a search area of the sea is set according to the size (small, medium, large) of the ship and the flooded state of the missing person (state 1, state 2, state 3).
- FIG. 5 is a photograph of a multi-wavelength image analysis electro-optical system for detecting a ship and a dehydrator according to the present invention.
- FIG. 6 is a block diagram illustrating a multi-wavelength image analysis electro-optical system for detecting a ship and a dehydrator according to the present invention.
- FIG. 7 is a circuit diagram showing the connection of circuits of a multi-wavelength image analysis electro-optical system for detecting a ship and a dehydrator according to the present invention shown in FIG.
- FIG. 8 is a block diagram illustrating a signal processing unit of a multi-wavelength image analysis electro-optical system for detecting a ship and a dehydrator according to the present invention shown in FIG.
- FIG. 9 is a flowchart illustrating an analysis method of a multi-wavelength image analysis electro-optical system for detecting a ship and a dehydrator according to the present invention shown in FIG.
- FIG. 10 is a view of an embodiment of the result of the accident vessel and dehydrator detection displayed through the image visualization unit 300 of the multi-wavelength image analysis electro-optical system for detecting a ship and a dehydrator according to the present invention.
- the multi-wavelength image analyzing electro-optical system for detecting a ship and a dehydrator of the present invention is a multi-wavelength image analyzing electro-optical system for detecting a ship and a dehydrator, comprising an ultra low light camera (3)
- An input unit 10 having a medium wavelength infrared image sensor 7 and a long wavelength infrared image sensor 9;
- a signal processing unit 20 for receiving and processing data of the input unit 10;
- a display unit (30) for receiving and displaying data of the signal processing unit (30);
- a storage unit 40 for storing data of the signal processing unit 20 and the display unit 30;
- a control unit 90 having a camera control board 50 and a drive control board 60 and controlling the input unit 10, the signal processing unit 20, the display unit 30, and the storage unit 40; .
- the input unit 10 of the multi-wavelength image analysis electro-optical system 1 for detecting a ship and a dehydrator of the present invention includes an ultra low light camera 3, a short wavelength infrared image sensor 5, A long infrared ray image sensor 7, and a long wavelength infrared ray image sensor 9.
- the multi-wavelength image analysis electro-optical system 1 for detecting a ship and a dehydrator of the present invention is a multi-wavelength image analysis electro-optical system for detecting a ship and a dehydrator
- An input unit 10 having a short wavelength infrared image sensor 5, a medium wavelength infrared image sensor 7, and a long wavelength infrared image sensor 9;
- a signal processing unit 20 for receiving and processing data of the input unit 10;
- a display unit (30) for receiving and displaying data of the signal processing unit (30);
- a control unit 90 having a camera control board 50 and a drive control board 60 and controlling the input unit 10, the signal processing unit 20, the display unit 30, and the storage unit 40; .
- the input unit 10 includes an image receiving unit 100 and the image receiving unit 100 includes a visible light image receiving module 110, an infrared image receiving module 120, and an image conformity checking module 130.
- the signal processing unit 20 includes an image analysis unit 200 and the image analysis unit 200 includes a visible light image processing module 210, a multi-wavelength mixture analysis module 220, and a processing result integration module 230 .
- the display unit 30 includes an image visualization unit 300 and the image visualization unit 300 includes a multi-wavelength image visualization module 310, an infrared image visualization module 320, and an integrated image visualization module 330.
- the camera control board 50 includes an EMCCD module 51, a VIS filter control module 52 and an EMCCD zoom lens module 53 and includes an LWIR module 55, an MWIR module 56, and an SWIR module 57 do.
- the drive control board 60 includes a fan motor driver 61 and a fan motor encoder 63 and the drive control board 60 includes a tilt motor driver 65 and a tilt motor encoder 67.
- the camera control board 50 and the drive control board 60 receive a control signal from the signal processing board 70.
- the signal processing board 70 receives a control signal from the user UI 80.
- the multi-wavelength image analysis electro-optical system 1 for detecting a ship and a dehydrator includes an image receiving unit 100, an image analyzing unit 200, and an image visualizing unit 300 .
- the image receiving unit 100 includes a visible light image receiving module 110, an infrared image receiving module 120 and an image conformity checking module 130.
- the image analyzing unit 200 includes a visible light image processing module 210, Processing module 220 and a processing result integration module 230.
- the image visualizer 300 includes a visible light image visualization module 310, an infrared image visualization module 320, and an integrated image visualization module 330 .
- FIG. 9 a schematic operation of a multi-wavelength image analysis electro-optical system for detecting a ship and a dehydrator according to the present invention will be described.
- the image receiving unit 100 receives the visible wideband and infrared band of the observed multi-wavelength signal and confirms that the image is suitable for detection analysis (S100).
- the visible light image receiving module 110 receives the observed aerial visible light image (S110).
- the infrared ray image receiving module 120 receives the observed infrared ray image (S120).
- the image suitability confirmation module 130 receives the received aerial visible light image and the infrared image, and confirms whether the observation information and the image observation value are suitable for detection and analysis (S130).
- the image analysis unit 200 processes the received visible light image and the infrared image, and generates a signal processing and a source image for each wavelength (S200).
- the visible light image processing module 210 processes the received visible light image (S210).
- the infrared image processing module 220 processes the received aerial infrared image (S220).
- the processing result integration module 230 integrates the signal-processed images in the visible light image processing module 110 and the infrared image processing module 220 to generate a raw image for each wavelength (S230).
- morphological feature based detection and optimal threshold based detection are applied to the object detection algorithm (S300).
- the algorithm of the object detection based on the optimum threshold based detection based on the multi-wavelength image is applied (S320).
- the image visualization unit 300 visualizes the received visible light image and the infrared image in an image form, displays and stores the detected visible light image and infrared image, and displays detailed information of the detected position and detection result of the accident ship and the deceased person (S400).
- the visible light image visualization module 310 visualizes the aerial visible light image in the form of an image, displays it, and stores it (S410).
- the infrared image visualization module 320 visualizes and displays the aerial infrared image in an image form and stores it (S420).
- the integrated image visualization module 330 visualizes the position of the detection object in the form of an integrated image by classifying the detected ship and the dehydrator, and displays and displays the combined image in operation S430.
- FIG. 1 The operation of the multi-wavelength image analyzing electro-optical system for detecting a ship and a dehydrator according to the present invention will be described in detail with reference to FIGS. 1 to 10.
- FIG. 1 The operation of the multi-wavelength image analyzing electro-optical system for detecting a ship and a dehydrator according to the present invention will be described in detail with reference to FIGS. 1 to 10.
- FIG. 1 The operation of the multi-wavelength image analyzing electro-optical system for detecting a ship and a dehydrator according to the present invention will be described in detail with reference to FIGS. 1 to 10.
- the present invention provides an optical system capable of multi-wavelength image analysis, Acquires images of wavelengths, and detects objects to be searched through image analysis by wavelength.
- detection conditions include a daytime environment such as fog, fine dust, and rain, and a nighttime environment.
- the detection targets include a marine drift vessel and a marine disappearance person.
- the wavelengths of the visible light region and the near infrared region which are the optimal wavelength bands of the multi-wavelength detection sensor, are derived in consideration of the search object and the search environment conditions. That is, in a marine environment having a particle diameter of 1 ⁇ m or less, such as fog, fine dust, smoke, etc., the wavelength of visible light is smaller than the particle size, so that light is scattered and does not reach visible visual equipment or the naked eye.
- a short-wave infrared (SWIR) sensor having a wavelength of 1 to 2.5 .mu.m, which is longer than particles such as fog, fine dust, and smoke, is used in the present invention.
- a long-wave infrared (LWIR) sensor with a wavelength of 8 to 14 ⁇ m, which is longer than a short-wave infrared (SWIR) sensor, is used.
- the search object conditions in the search area of the sea are set as the size of the ship ), And the flooded state of the missing person (state 1, state 2, state 3).
- a system requirement specification is derived for an optimal image acquisition according to search environment conditions.
- the spectroscopic method are derived, and the optimum wavelength of the two wavelengths of the infrared band electronic optical sensor is selected.
- spectral filter specifications for spectroscopic image spectroscopy with three wavelengths are selected and images are acquired to design the exhibition module.
- the first prototype mechanical part of the integrated electronic optical sensor (visible light + spectral filter, infrared sensor) of the multi-wavelength image analysis system is modeled and the image is acquired to design the exhibition module in detail.
- basic design of detection and analysis algorithm for each wavelength band image, individual image analysis for each wavelength band, and search object detection algorithm are used.
- the image receiving unit 100 of the present invention receives a visible wide-band and infrared band of an observed airborne multi-wavelength signal and confirms whether it is suitable for detection analysis (S100).
- the visible light image receiving module 110 receives the observed aerial visible light image (S110).
- the infrared ray image receiving module 120 receives the observed infrared ray image (S120).
- the image suitability confirmation module 130 receives the received aerial visible light image and the infrared image, and confirms whether the observation information and the image observation value are suitable for detection and analysis (S130).
- the image analysis unit 200 processes the received visible light image and the infrared image, and generates a signal processing and a source image for each wavelength (S200).
- the visible light image processing module 210 processes the received visible light image (S210).
- the infrared image processing module 220 processes the received aerial infrared image (S220).
- the processing result integration module 230 integrates the signal-processed images in the visible light image processing module 110 and the infrared image processing module 220 to generate a raw image for each wavelength (S230).
- morphological feature based detection and optimal threshold based detection are applied to the object detection algorithm (S300).
- the algorithm of the object detection based on the optimum threshold based detection based on the multi-wavelength image is applied (S320).
- the image visualization unit 300 visualizes the received visible light image and the infrared image in an image form, displays and stores the detected visible light image and infrared image, and displays detailed information of the detected position and detection result of the accident ship and the deceased person (S400).
- the visible light image visualization module 310 visualizes the aerial visible light image in the form of an image, displays it, and stores it (S410).
- the infrared image visualization module 320 visualizes and displays the aerial infrared image in an image form and stores it (S420).
- the integrated image visualization module 330 visualizes the position of the detection object in the form of an integrated image by classifying the detected ship and the dehydrator, and displays and displays the combined image in operation S430.
- the present invention applies morphological feature based detection based on a multi-wavelength image and a marine object detection algorithm for optimal threshold based detection (S300). This is different from conventional multi-wavelength image-based marine target detection technology in which detection range is largely limited depending on spatial resolution and target size when multiple substances in a pixel are mixed by using simple reflectance or morphological characteristic, have.
- a feature detection based on feature detection based on a multi-wavelength image is represented by a feature vector observed in each pixel for image segmentation, and an appropriate probability model is assumed for the feature detection.
- a marine object detection algorithm is an application of the problem of calculating the maximum likelihood for an unknown parameter in the incomplete data or obtaining the maximum value of the posterior probability distribution. Since the performance of the estimator depends on the starting point, Converges to the local maximum value (S310).
- the algorithm for detecting an optimal threshold based detection based on a multi-wavelength image mixes a histogram of an original image and a Gaussian function formed around all level values of an image, And uses an optimized image segmentation technique to set the threshold.
- the edge portion is clearly displayed and can be divided into detailed and accurate images to detect the marine object (S320).
- a morphological feature-based detection and a marginal object detection algorithm for optimal threshold-based detection are applied, and the result detected by the image receiving unit 100 is transmitted to the user via the image visualization unit 300 Is finally displayed in the form of a graphical user interface (GUI) (S400).
- GUI graphical user interface
- the image visualization unit 300 displays and stores the inputted aerial visible light image in the form of image in S410 and selects the specific band (for example, RGB) from the visible light image visualization module 310.
- the infrared visualization module 320 The infrared infrared image is displayed in an image form and stored (S420).
- the integrated image visualization module 330 visualizes and displays the position of the detection object in the form of an integrated image by classifying the detected accident vessel and the submerged person and classifies the information according to classification of the detection results, Size, and degree of detail, along with detailed information.
- the airborne multi-wavelength image that has undergone the preprocessing process in the image receiving unit 100 and the detectors to be detected in the corresponding area are displayed in an image form in real time and the detailed information is expressed together in text form (S430).
- the conventional search image equipment farnesoid, fine dust, As a result, it was confirmed that the peak signal-to-noise ratio (PSNR) of the image was improved by 10%.
- the target detection performance can be confirmed that the search object is detected with an accuracy level of 90% or more in Probability of Detection (POD) and less than 10% in False Alarm Rate (FAR).
- POD Probability of Detection
- FAR False Alarm Rate
- the multi-wavelength image analysis electro-optical system and its analysis method for detecting a ship and a dehydrator of the present invention overcome the marine target detection limit of the conventional technology by applying a multi-wavelength mixed analysis method for each pixel using multi- And provides more accurate and stable detection results immediately without further work.
- multi-wavelength image is used and it is possible to improve search speed of the accident ship and missing person due to marine accidents by analyzing the reflection spectrum analysis results of each object. have. Through this, it is possible to reduce the detection time of accident ship and missing person due to marine accidents, increase the detection probability, and support quick search operation.
- the detection probability can be improved to 90% or more and the accuracy of the false alarm rate of less than 10% can be realized.
- it will be used as a core technology in defense surveillance scout and illegal fishing vessel surveillance, which is rapidly increasing in demand in recent years, and will establish a base for domesticization and advancement of the whole marine search equipment industry which is continuously demanded.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Probability & Statistics with Applications (AREA)
- Computing Systems (AREA)
- Astronomy & Astrophysics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Databases & Information Systems (AREA)
- Remote Sensing (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Discrete Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Studio Devices (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
Description
Claims (20)
- 사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템에 있어서,초저조도 카메라(3)와, 단파장적외선 영상센서(5)와, 중파장적외선 영상센서(7)와, 장파장적외선 영상센서(9)를 구비한 입력부(10);상기 입력부(10)의 데이터를 수신하여 처리하는 신호처리부(20);상기 신호처리부(20)의 데이터를 수신하여 표시하는 표시부(30);상기 신호처리부(20) 및 표시부(30)의 데이터를 저장하는 저장부(40);카메라 제어보드(50)와 구동제어보드(60)를 구비하고 상기 입력부(10), 상기 신호처리부(20), 상기 표시부(30), 및 상기 저장부(40)를 제어하는 제어부(90);를 포함하여 구성되는,사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템.
- 제 1 항에 있어서,상기 카메라제어보드(50)는 EMCCD모듈(51), VIS필터제어모듈(52), EMCCD 줌렌즈모듈(53)을 포함하는,사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템.
- 제 2 항에 있어서,상기 카메라제어보드(50)는 LWIR 모듈(55), MWIR모듈(56), SWIR모듈(57)을 포함하는,사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템.
- 제 1 항에 있어서,상기 구동제어보드(60)는 팬모터 드라이버(61)와 팬모터 엔코더(63)를 포함하는,사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템.
- 제 4 항에 있어서,상기 구동제어보드(60)은 틸트모터 드라이버(65)와 틸트모터 엔코더(67)를 포함하는,사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템.
- 제 1 항에 있어서,상기 카메라제어보드(50) 및 구동제어보드(60)는 신호처리보드(70)로부터 제어신호를 인가받는,사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템.
- 제 6 항에 있어서,상기 신호처리보드(70)는 사용자 UI(80)로부터 제어신호를 인가받는,사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템.
- 제 1 항에 있어서,상기 입력부(10)는 영상수신부(100)를 구비하고,상기 영상수신부(100)는 가시광 영상 수신 모듈(110), 적외선 영상 수신 모듈(120), 영상 적합성 확인 모듈(130)을 더 포함하는,사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템.
- 제 1 항에 있어서,상기 신호처리부(20)는 영상분석부(200)를 구비하고,상기 영상분석부(200)는 다중파장 모듈(210), 적외선 영상 처리 모듈(220), 처리 결과 통합 모듈(230)을 더 포함하는,사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템.
- 제 1 항에 있어서,상기 표시부(30)는 영상가시화부(300)를 구비하고,상기 영상가시화부(300)는 가시광 영상 가시화 모듈(310), 적외선 영상 가시화 모듈(320), 통합 영상 가시화 모듈(330)을 더 포함하는,사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템.
- 사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템의 분석방법에 있어서,(a) 영상 수신부(100)가 관측된 항공 다중파장 영상을 수신하는 단계;(b) 영상 분석부(200)가 신호처리 및 파장별 원시영상을 생성하는 단계;(c) 상기 영상 분석부(200)가 형태적 특징 기반 탐지 및 최적임계값 기반 탐지의 해상물체탐지 알고리즘을 적용하는 단계; 및(d) 영상 가시화부(300)가 해상물체 탐지영상을 가시화하는 단계;를 포함하는,사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템의 분석방법.
- 제11항에 있어서,상기 (a) 단계는(a-1) 안개, 미세 먼지, 연기 등의 입자보다 더 긴 1 ~ 2.5 um 의 파장을 가지는 단파 적외선(short-wave infrared) 센서를 이용하는 단계; 및(a-2) 저조도 환경일 경우, 단파 적외선(short-wave infrared, SWIR) 센서보다 파장이 더 긴 8 ~ 14 um 파장의 장파 적외선(long-wave infrared, LWIR) 센서를 이용하는 단계; 를 더 포함하는,사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템의 분석방법.
- 제11항에 있어서,상기 (c) 단계는(c-1) 상기 다중파장 영상을 기반으로 한 형태적 특징 기반 탐지의 해상물체탐지 알고리즘은영상분할을 위해 각 화소에서 관측되는 특징벡터로 표현하며 이들에 대하여 적절한 확률모델을 가정하고,상기 확률모델을 결정하는 파라미터들을 통계적 방법으로 추정하여 이용하거나 각 특징 벡터간의 유사도를 기반으로 하는 군집 알고리즘을 사용하여 분할을 수행하는 단계를 더 포함하는,사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템의 분석방법.
- 제 13항에 있어서,상기 (c) 단계는(c-1) 상기 다중파장 영상을 기반으로 한 형태적 특징 기반 탐지의 해상물체탐지 알고리즘은불완전한 데이터에서 미지의 파라미터에 대한 최대 우도를 계산하는 경우나 사후 확률 분포의 최대값을 구하는 단계를 더 포함하는,사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템의 분석방법.
- 제 11항에 있어서,상기 (c) 단계는(c-2) 상기 다중파장 영상을 기반으로 한 최적임계값 기반 탐지의 해상물체탐지 알고리즘은영상의 모든 레벨값을 중심으로 형성된 가우시안 함수와 원 영상의 히스토그램을 혼합하여 영상의 새로운 히스토그램을 통해 임계값을 설정하는 최적화된 영상분할 기법을 이용하는 단계를 더 포함하는,사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템의 분석방법.
- 제 11항에 있어서,상기 (d) 단계는(d-1) 상기 영상 가시화부(300)는 가시광 영상 가시화 모듈(310)에서 특정 밴드(RGB)를 선택하여 입력된 항공 가시광 영상을 이미지 형태로 표출 및 저장하는 단계; 및(d-2) 상기 영상 가시화부(300)는 적외선 영상 가시화 모듈(320)에서 항공 적외선 영상을 이미지 형태로 표출 및 저장하는 단계; 를 더 포함하는,사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템의 분석방법.
- 제 11항에 있어서,상기 (d) 단계는(d-3) 상기 영상가시화부(300)는 통합 영상 가시화 모듈(330)에서 탐지된 사고 선박 및 익수자를 구분하여 탐지체의 위치를 통합영상 이미지 형태로 가시화하여 표출 및 저장하는 단계를 더 포함하는,사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템의 분석방법.
- 제 11항에 있어서,상기 (d) 단계는(d-4) 상기 영상가시화부(300)는 통합 영상 가시화 모듈(330)에서 상기 영상 수신부(100)의 전처리 과정을 거친 항공관측 다중파장 영상과 해당 영역 내 탐지되는 탐지체가 이미지 형태로 실시간으로 표출되며 상세 정보가 텍스트 형태로 함께 표출되는 단계; 를 더 포함하는,사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템의 분석방법.
- 제 11항에 있어서,상기 (d) 단계는(d-4) 상기 영상가시화부(300)는 통합 영상 가시화 모듈(330)에서 상기 탐지 결과를 분류에 따라 구분하여 종류, 크기, 위경도 등 상세 정보와 함께 표 형식으로 표출하고 저장하는 단계; 를 더 포함하는,사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템의 분석방법.
- 제11항 내지 제19항 중 어느 한 항에 기재된 방법을 구현하기 위한 프로그램이 저장된 컴퓨터 판독 가능한 기록 매체.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US16/470,531 US10803590B2 (en) | 2017-12-28 | 2018-05-16 | Multiple-wavelength images analysis electro optical system for detection of accident ship and submerged person and analysis method thereof |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR10-2017-0182494 | 2017-12-28 | ||
KR1020170182494A KR101852476B1 (ko) | 2017-12-28 | 2017-12-28 | 사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템 및 그 분석 방법 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2019132131A1 true WO2019132131A1 (ko) | 2019-07-04 |
Family
ID=62628239
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2018/005628 WO2019132131A1 (ko) | 2017-12-28 | 2018-05-16 | 사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템 및 그 분석 방법 |
Country Status (3)
Country | Link |
---|---|
US (1) | US10803590B2 (ko) |
KR (1) | KR101852476B1 (ko) |
WO (1) | WO2019132131A1 (ko) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111695633A (zh) * | 2020-06-12 | 2020-09-22 | 桂林电子科技大学 | 基于rpf-cam的低照度目标检测方法 |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111924117B (zh) * | 2020-08-14 | 2024-04-09 | 西安应用光学研究所 | 一种光电吊舱内置光学传感器波段自主切换方法 |
CN114257707A (zh) * | 2020-09-21 | 2022-03-29 | 安霸国际有限合伙企业 | 具有彩色夜间模式的智能ip摄像头 |
CN112198516A (zh) * | 2020-11-10 | 2021-01-08 | 广东智芯光电科技有限公司 | 一种水下图像采集的方法和系统 |
CN113450413B (zh) * | 2021-07-19 | 2022-09-27 | 哈尔滨工业大学 | 基于gf4单帧图像的舰船目标检测方法 |
EP4134644A1 (en) | 2021-08-11 | 2023-02-15 | Wooptix S.L. | System and method for extracting information on the spatial distribution of wavefronts |
CN116580313B (zh) * | 2023-03-31 | 2023-11-14 | 数字太空(北京)科技股份公司 | 一种基于数字孪生和遥感的异常船只识别方法及装置 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20110089892A (ko) * | 2010-02-02 | 2011-08-10 | 코스모스티이에스 (주) | 3파종 물체감지 및 영상체계 시스템 및 그 방법 |
KR20130121202A (ko) * | 2012-04-25 | 2013-11-06 | 한국전자통신연구원 | 영상에서의 객체 추적 방법, 장치 및 이를 컴퓨터 상에서 수행하는 프로그램이 기록된 기록 매체 |
KR20140043976A (ko) * | 2012-10-04 | 2014-04-14 | 엘지이노텍 주식회사 | 감시 장치 및 방법 |
KR20150011098A (ko) * | 2013-07-22 | 2015-01-30 | 현대모비스 주식회사 | 영상 처리 방법 및 이를 위한 위한 장치 |
KR20170087836A (ko) * | 2016-01-21 | 2017-07-31 | 강릉원주대학교산학협력단 | 해상에서 다중 채널 영상을 이용한 대기 에어로졸 탐지, 광학두께, 입자크기, 유효 고도 측정, 유효성 검사 시스템 및 방법 |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8300108B2 (en) | 2009-02-02 | 2012-10-30 | L-3 Communications Cincinnati Electronics Corporation | Multi-channel imaging devices comprising unit cells |
US20110164108A1 (en) * | 2009-12-30 | 2011-07-07 | Fivefocal Llc | System With Selective Narrow FOV and 360 Degree FOV, And Associated Methods |
CN103583037B (zh) * | 2011-04-11 | 2017-04-26 | 菲力尔系统公司 | 红外相机系统和方法 |
EP2866052A1 (en) * | 2013-10-23 | 2015-04-29 | Ladar Limited | A system for monitoring a maritime environment |
US10931934B2 (en) * | 2014-09-02 | 2021-02-23 | FLIR Belgium BVBA | Watercraft thermal monitoring systems and methods |
IL237717A (en) * | 2015-03-12 | 2017-04-30 | Elbit Systems Ltd | Identification, characterization and display of dangerous aerial phenomena |
US10055648B1 (en) * | 2015-04-16 | 2018-08-21 | Bae Systems Information And Electronic Systems Integration Inc. | Detection, classification, and tracking of surface contacts for maritime assets |
US9944366B2 (en) * | 2015-05-19 | 2018-04-17 | Rujing Tang | Unmanned aerial vehicle system and methods for use |
US10181249B2 (en) * | 2016-09-07 | 2019-01-15 | Seal Innovation, Inc. | Systems, methods and computer program products for detecting a presence of an object in a body of water |
-
2017
- 2017-12-28 KR KR1020170182494A patent/KR101852476B1/ko active IP Right Grant
-
2018
- 2018-05-16 US US16/470,531 patent/US10803590B2/en active Active
- 2018-05-16 WO PCT/KR2018/005628 patent/WO2019132131A1/ko active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20110089892A (ko) * | 2010-02-02 | 2011-08-10 | 코스모스티이에스 (주) | 3파종 물체감지 및 영상체계 시스템 및 그 방법 |
KR20130121202A (ko) * | 2012-04-25 | 2013-11-06 | 한국전자통신연구원 | 영상에서의 객체 추적 방법, 장치 및 이를 컴퓨터 상에서 수행하는 프로그램이 기록된 기록 매체 |
KR20140043976A (ko) * | 2012-10-04 | 2014-04-14 | 엘지이노텍 주식회사 | 감시 장치 및 방법 |
KR20150011098A (ko) * | 2013-07-22 | 2015-01-30 | 현대모비스 주식회사 | 영상 처리 방법 및 이를 위한 위한 장치 |
KR20170087836A (ko) * | 2016-01-21 | 2017-07-31 | 강릉원주대학교산학협력단 | 해상에서 다중 채널 영상을 이용한 대기 에어로졸 탐지, 광학두께, 입자크기, 유효 고도 측정, 유효성 검사 시스템 및 방법 |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111695633A (zh) * | 2020-06-12 | 2020-09-22 | 桂林电子科技大学 | 基于rpf-cam的低照度目标检测方法 |
Also Published As
Publication number | Publication date |
---|---|
US20200143543A1 (en) | 2020-05-07 |
KR101852476B1 (ko) | 2018-06-04 |
US10803590B2 (en) | 2020-10-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2019132131A1 (ko) | 사고 선박 및 익수자 탐지용 다중파장 영상 분석 전자 광학 시스템 및 그 분석 방법 | |
US7663507B2 (en) | Foreign object detection system and method | |
WO2022139110A1 (ko) | 해상객체 식별을 위한 초분광 데이터 처리방법 및 장치 | |
US9250135B2 (en) | MWIR sensor for flame detection | |
WO2019083109A1 (ko) | 항공 초분광 영상을 이용한 사고 선박 및 익수자 탐지 방법 | |
US20070116328A1 (en) | Nudity mask for use in displaying video camera images | |
CN111047568A (zh) | 一种漏汽缺陷检测识别方法及系统 | |
WO2012005387A1 (ko) | 다중 카메라와 물체 추적 알고리즘을 이용한 광범위한 지역에서의 물체 이동 감시 방법 및 그 시스템 | |
CN113486697B (zh) | 基于空基多模态图像融合的森林烟火监测方法 | |
WO2016036881A1 (en) | Wide-area real-time method for detecting foreign fluids on water surfaces | |
Sosnowski et al. | Thermovision system for flying objects detection | |
WO2020091337A1 (ko) | 영상 분석 장치 및 방법 | |
WO2018165027A1 (en) | Polarization-based detection and mapping method and system | |
Xie et al. | A UAV Forest Fire Detection Method Based on Dual-Light Vision Images | |
CN115947066B (zh) | 皮带撕裂检测方法、装置及系统 | |
WO2020116988A1 (ko) | 영상 분석 장치, 영상 분석 방법 및 기록 매체 | |
Silva et al. | UAV trials for multi-spectral imaging target detection and recognition in maritime environment | |
Markushin et al. | Image fusion in a dual-band scanning optoelectronic system for the search and detection of poaching activity | |
KR102015620B1 (ko) | 금속입자 검출 시스템 및 방법 | |
Ahmad et al. | Image Processing Techniques-based fire detection | |
Al-Lashi et al. | Toward omnidirectional and automated imaging system for measuring oceanic whitecap coverage | |
Waxman et al. | Sensor fused night vision: Assessing image quality in the lab and in the field | |
Tragulnuch et al. | High voltage transmission tower identification in an aerial video sequence using object-based image classification with geometry information | |
Sporrer et al. | NIR camera based person detection in the working range of industrial robots | |
RU2758881C1 (ru) | Тепловизионный способ обнаружения беспилотного летательного аппарата типа "мультикоптер" |
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: 18897017 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: 18897017 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 22/01/2021) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 18897017 Country of ref document: EP Kind code of ref document: A1 |