CN112616040A - Wild animal image transmission method and system based on distributed architecture - Google Patents
Wild animal image transmission method and system based on distributed architecture Download PDFInfo
- Publication number
- CN112616040A CN112616040A CN202011451128.1A CN202011451128A CN112616040A CN 112616040 A CN112616040 A CN 112616040A CN 202011451128 A CN202011451128 A CN 202011451128A CN 112616040 A CN112616040 A CN 112616040A
- Authority
- CN
- China
- Prior art keywords
- image
- transmission
- data
- distributed
- adopting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 158
- 241001465754 Metazoa Species 0.000 title claims abstract description 85
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000006835 compression Effects 0.000 claims abstract description 70
- 238000007906 compression Methods 0.000 claims abstract description 70
- 238000012544 monitoring process Methods 0.000 claims abstract description 35
- 238000011084 recovery Methods 0.000 claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000007781 pre-processing Methods 0.000 claims description 24
- 230000000750 progressive effect Effects 0.000 claims description 18
- 238000000605 extraction Methods 0.000 claims description 13
- 230000007246 mechanism Effects 0.000 claims description 12
- 238000011176 pooling Methods 0.000 claims description 10
- 238000006073 displacement reaction Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 7
- 230000008030 elimination Effects 0.000 claims description 7
- 238000003379 elimination reaction Methods 0.000 claims description 7
- 230000008447 perception Effects 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 241000854291 Dianthus carthusianorum Species 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 230000000873 masking effect Effects 0.000 description 2
- 208000032369 Primary transmission Diseases 0.000 description 1
- 208000032370 Secondary transmission Diseases 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/46—Embedding additional information in the video signal during the compression process
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/60—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using transform coding
- H04N19/63—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using transform coding using sub-band based transform, e.g. wavelets
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
The embodiment of the invention discloses a wild animal image transmission method and system based on a distributed architecture. The system is mainly applied to a wild animal monitoring system based on a wireless sensor network, a high-efficiency transmission channel is built for data monitoring nodes and a data center of the monitoring system through a distributed transmission model, the transmission channel mainly comprises an image acquisition processing module, an image compression coding module, an image data distributed transmission module and an image automatic recovery module, and through the organic combination of the four modules, the reliable transmission of data is guaranteed, and meanwhile, the high availability of an image sample and the low-power-consumption operation of the whole monitoring system can be guaranteed.
Description
Technical Field
The invention relates to the technical field of wild animal monitoring data transmission, in particular to a wild animal image transmission method and system based on a distributed architecture.
Background
The wild animal monitoring system is an important way for acquiring wild animal resource data. Based on the complexity of wild animal monitoring environment, how to efficiently and quickly transmit monitoring data to a data center is a main research content for improving the automation and intelligence level of a wild animal monitoring system. The wild animal monitoring data transmission system constructed based on the wireless sensor network can realize remote, real-time and fine monitoring and transmission of image data.
The wild animal monitoring image data has the characteristics of large data volume, complex data background and more data noise points, and a wild animal monitoring system formed based on a wireless sensor network has low processing capability, strong power consumption limitation and narrow transmission bandwidth. Therefore, on the premise of ensuring the data transmission quality, it is a technical problem that needs to be solved at present to fully consider the transmission efficiency and the balanced utilization of energy resources.
Disclosure of Invention
Aiming at the technical defects in the prior art, the embodiment of the invention aims to provide a wild animal image transmission method and system based on a distributed architecture.
In order to achieve the above object, in a first aspect, an embodiment of the present invention provides a wild animal image transmission method based on a distributed architecture, including:
image acquisition and preprocessing: acquiring real-time image data of wild animals, and preprocessing the real-time image data of the wild animals to obtain a first image; the first image comprises a salient object region and a background region;
and image compression encoding: based on the image progressive compression coding algorithm of the significance perception, carrying out layered progressive compression coding on the significance target area and the background area to obtain a second image so as to realize lossless compression on the significance target area and lossy compression on the background area;
image distributed transmission: transmitting the second image through a distributed transmission mechanism;
an image automatic recovery step: and recovering the second image based on an image automatic recovery algorithm of the improved self-encoder.
In some embodiments of the present application, the preprocessing the real-time wild animal image data specifically includes:
performing dirty data elimination and image target area extraction on the real-time image data of the wild animals; the dirty data includes false trigger images, low resolution images, and images of no practical value.
In some embodiments of the present application, the image compression encoding step specifically includes:
acquiring a wavelet coefficient of the first image;
mask marking the wavelet coefficients in the saliency target region;
calculating a wavelet coefficient mask image in the salient region by adopting a backtracking method;
adopting a maximum displacement plane lifting method to lift the marked wavelet coefficient bit plane, so that the transmission priority of the significant target area is higher than that of the background area;
carrying out lossless compression coding by adopting improved SPHIT aiming at a significant target region with higher transmission priority;
and performing lossy compression coding by adopting EZW aiming at the background area with lower transmission priority.
In some embodiments of the present application, the image distributed transmission step specifically includes:
establishing a distributed image transmission model based on an independent coding and joint decoding mode, and performing data distribution transmission on the salient target region and the background region by adopting the distributed image transmission model;
processing transmission data by adopting a distributed compressed sensing algorithm, wherein the transmission data refers to a second image comprising the saliency target area and a background area;
and aiming at the processed transmission data, a joint decoding algorithm model is established for decoding, and the received redundant information is removed by combining the correlation among the joint signals.
In some embodiments of the present application, the image automatic recovery step specifically includes:
on the basis of a self-encoder network structure, a jump layer short connection structure is adopted to add low-layer characteristics output by a network front end convolution layer and a pooling layer into deconvolution operation, and data after up-sampling and upper-layer convolution pooling are combined to recover a wild animal distorted image; the wildlife distorted image refers to the second image.
In a second aspect, the embodiments of the present invention provide a wild animal image transmission system based on a distributed architecture, including a processor, an input device, an output device, and a memory, where the processor, the input device, the output device, and the memory are connected to each other, where the memory is used to store a computer program, and the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method of the first aspect.
In a third aspect, an embodiment of the present invention provides another wild animal image transmission system based on a distributed architecture, including:
the system comprises an image acquisition and preprocessing module, a first image acquisition and preprocessing module and a second image acquisition and preprocessing module, wherein the image acquisition and preprocessing module is used for acquiring real-time image data of wild animals and preprocessing the real-time image data of the wild animals to obtain a first image; the first image comprises a salient object region and a background region;
the image compression coding module is used for carrying out layered progressive compression coding on the saliency target area and the background area based on a saliency-aware image progressive compression coding algorithm to obtain a second image so as to realize lossless compression on the saliency target area and lossy compression on the background area;
the image distributed transmission module is used for transmitting the second image through a distributed transmission mechanism;
and the image automatic recovery module is used for recovering the second image based on the image automatic recovery algorithm of the improved self-encoder.
In a fourth aspect, embodiments of the present invention provide a wild animal remote monitoring system, including:
the data monitoring node is used for automatically acquiring image data of wild animal activities in a monitoring area, and performing dirty data elimination, target area extraction and compression coding on the image data to obtain transmission data; the transmission data comprises a salient target area with higher transmission priority and a background area with lower transmission priority;
a transmission module for transmitting the transmission data by a distributed mechanism;
and the data center is used for receiving the transmission data, recovering the transmission image based on an image automatic recovery algorithm of the improved self-encoder, and finishing the classified storage of the recovered wild animal image data.
The wild animal image transmission method and system based on the distributed architecture have the following beneficial effects that:
1. the wild animal image transmission system based on the distributed transmission mechanism can ensure real-time transmission of data, improve the transmission efficiency of the system, reduce the operation power consumption of the system and effectively prolong the service cycle of the system.
2. Based on the extraction of the saliency target region, the image progressive compression coding algorithm based on the saliency perception adopts bit plane lifting and mixed coding strategies to ensure the transmission priority of an important region in an image, realizes the lossless compression of the saliency target region and the lossy compression of a background region, and can ensure the reconstruction quality of the saliency target region while still ensuring the reconstruction quality of the whole image.
3. The wild animal distorted image automatic recovery method based on the self-coding neural network is used for training and testing databases established respectively aiming at images of a wild animal region and a background region, and overcomes the influence of the difference of texture information on the image recovery quality. The quality of the recovered image is effectively improved through the improved self-encoder network, and reliable data support can be provided for subsequent related researches of wild animals.
Drawings
In order to more clearly illustrate the detailed description of the invention or the technical solutions in the prior art, the drawings that are needed in the detailed description of the invention or the prior art will be briefly described below.
Fig. 1 is a schematic flow chart of a wild animal image transmission method based on a distributed architecture according to an embodiment of the present invention;
FIG. 2 is a flow chart of the image progressive compression encoding method of the present invention;
FIG. 3 is a technical block diagram of image hybrid encoding of the present invention;
FIG. 4 is a flow chart of a distributed transmission method of image data of the present invention;
FIG. 5 is a network architecture diagram for automatic image recovery of the present invention;
fig. 6 is an architecture diagram of a wild animal image transmission system based on a distributed architecture according to a first embodiment of the present invention;
fig. 7 is a block diagram of a wild animal image transmission system based on a distributed architecture according to a second embodiment of the present invention;
fig. 8 is a block diagram of a system for remote monitoring of wild animals according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a method for transmitting images of wild animals based on a distributed architecture according to an embodiment of the present invention includes:
s101, image acquisition and preprocessing: the method comprises the steps of obtaining real-time image data of wild animals, and preprocessing the real-time image data of the wild animals to obtain a first image.
Wherein the first image comprises a salient object region and a background region.
Specifically, the image preprocessing mainly includes dirty data elimination, image target area extraction and the like, and the dirty data mainly refers to false triggering images, low-resolution images and other image data without practical value. The image target region extraction refers to detection and extraction of an image salient target region, and the salient target region refers to a region where wild animals exist in an image.
S102, image compression coding: and carrying out layered progressive compression coding on the saliency target area and the background area based on a saliency-aware image progressive compression coding algorithm to obtain a second image so as to realize lossless compression on the saliency target area and lossy compression on the background area.
The image compression coding mainly refers to an image progressive compression coding algorithm based on significance perception, as shown in fig. 2. Based on the image data output in the image acquisition and processing step, the displacement plane lifting and mixed coding algorithm is adopted to carry out layered progressive compression coding on the wild animal monitoring image, so that lossless compression of a significant target area and lossy compression of a background area are realized. The specific implementation steps of image compression coding are as follows:
and S1-1, acquiring wavelet coefficients of the monitored images of the wild animals.
Specifically, the input wild animal monitoring image refers to data output in the image acquisition processing step. The wavelet coefficient specifically refers to the wavelet coefficient of the wild animal monitoring image obtained through decomposition in the row and column directions by adopting Mallat two-dimensional wavelet transform.
And S1-2, calculating a wavelet coefficient mask image in the saliency target area.
Specifically, the saliency target region refers to a result obtained by extracting the saliency target region in image preprocessing, and is marked by masking a wavelet coefficient in the saliency target region.
Specifically, wavelet coefficient mask images in the significant target region are respectively calculated by adopting a backtracking method.
And S1-3, lifting the marked wavelet coefficient bit plane by adopting a maximum displacement plane lifting method, and realizing the priority transmission of the significant target area.
Specifically, in order to realize the preferential transmission of the significant target region, the wavelet coefficient in the significant target region is boosted by adopting a maximum displacement plane boosting method to be higher than that of the background region, so that the wavelet coefficient of the significant target region is preferentially transmitted.
Specifically, the maximum value of the wavelet coefficient in the background region is first calculated, so that the bit plane s of the background region can be obtained.
s＝INT[log2|cmax|]
Wherein INT denotes rounding, cmaxRepresenting the maximum value of the wavelet coefficients in the background region.
Then all the coefficients in the saliency target region are multiplied by 2 according to the mask informationsOr the background area is entirely divided by 2sAll coefficients belonging to the saliency target region are made larger than the maximum of the background region.
Preferably, since the saliency object and the background are separated during information transmission, no mask coding information is needed at the decoding end to determine the wavelet coefficient of the saliency object, and only whether the coefficient is greater than 2 needs to be judgedsIf so, the coefficient belongs to the saliency target region, which is divided by 2 at the decoding endsAnd (4) performing a bit plane reduction operation, otherwise, the coefficient belongs to a background area, and reconstructing the original image without performing any operation on the coefficient.
And S1-4, realizing distributed coding of the image based on the hybrid coding algorithm.
Specifically, the distributed encoding is to implement lossless encoding of a saliency target region and lossy encoding of a background region by a hybrid encoding algorithm on the saliency target region and the background region in an image, and fig. 3 is a technical block diagram of image hybrid encoding.
Specifically, improved SPHIT is adopted for lossless compression coding aiming at a wild animal monitoring image significance target area with higher transmission priority; and aiming at the background area information, a lossy compression mode is adopted by EZW, pixels in the background image are sequenced, and the transmission process of the data can be finished at any time according to the specific compression requirement or the specified compressed data amount.
S103, image distributed transmission: transmitting the second image via a distributed transmission mechanism.
The image distributed transmission refers to distributed cooperative transmission aiming at a salient target area and a background area in an image, as shown in fig. 4. The significant target area is transmitted by adopting a primary transmission channel with high priority and high transmission efficiency to ensure the transmission efficiency of an important area in the image, and background area information with relatively large data volume is transmitted by a secondary transmission channel to maximize resource utilization. Specifically, the image distributed transmission includes:
s2-1, establishing a distributed image transmission model based on independent coding and joint decoding, and respectively performing data distribution transmission on a salient target region and a background region;
specifically, in the transmission process of image data, firstly, pixel points in an image are classified according to marks and unmarked, wherein all the marked pixel points are directly coded and transmitted through cluster head nodes, and the unmarked pixel points are divided according to the number of the cluster nodes and then transmitted through the cluster nodes. In the process, the cluster head node does not participate in the encoding task of the background area data, so that the significant target area is transmitted to the target node to the maximum extent.
S2-2, processing the transmission data by adopting a distributed compressed sensing algorithm;
s2-3, a joint decoding algorithm model is established to decode the data, and the received redundant information is removed by combining the correlation among the joint signals.
S104, an image automatic recovery step: and recovering the second image based on an image automatic recovery algorithm of the improved self-encoder.
In this embodiment, the wild animal region sample image and the background region sample image are trained and tested by using an unsupervised self-encoder neural network structure, respectively, and fig. 5 is a diagram of an image automatic recovery network structure.
Specifically, the image automatic recovery method is that on the basis of a self-encoder network structure, a jump layer short connection structure is adopted to add low-layer characteristics output by a network front-end convolution layer and a pooling layer into deconvolution operation, data after upsampling and upper-layer convolution pooling are combined to recover a wild animal distorted image, and a loss function adopts a mean square error function.
Compared with the prior art, the wild animal image transmission method based on the distributed architecture has the following beneficial effects:
1. the wild animal image transmission system based on the distributed transmission mechanism can ensure real-time transmission of data, improve the transmission efficiency of the system, reduce the operation power consumption of the system and effectively prolong the service cycle of the system.
2. Based on the extraction of the saliency target region, the image progressive compression coding algorithm based on the saliency perception adopts bit plane lifting and mixed coding strategies to ensure the transmission priority of an important region in an image, realizes the lossless compression of the saliency target region and the lossy compression of a background region, and can ensure the reconstruction quality of the saliency target region while still ensuring the reconstruction quality of the whole image.
3. The wild animal distorted image automatic recovery method based on the self-coding neural network is used for training and testing databases established respectively aiming at images of a wild animal region and a background region, and overcomes the influence of the difference of texture information on the image recovery quality. The quality of the recovered image is effectively improved through the improved self-encoder network, and reliable data support can be provided for subsequent related researches of wild animals.
Based on the same inventive concept, the embodiment of the invention provides a wild animal image transmission system based on a distributed architecture. As shown in fig. 6, the transmission system mainly includes: the image acquisition and processing module, the image compression and encoding module, the image data distributed transmission module and the image automatic recovery module.
The image acquisition and preprocessing module is mainly used for acquiring real-time image data of wild animals and preprocessing the real-time image data of the wild animals to obtain a first image; the first image includes a salient object region and a background region. The data source of the image acquisition and preprocessing module is a data monitoring node of the wild animal remote monitoring system.
The image compression coding module is used for carrying out layered progressive compression coding on the saliency target area and the background area based on a saliency-aware image progressive compression coding algorithm to obtain a second image so as to realize lossless compression on the saliency target area and lossy compression on the background area;
the image distributed transmission module is used for transmitting the second image through a distributed transmission mechanism;
and the image automatic recovery module is used for recovering the second image based on the image automatic recovery algorithm of the improved self-encoder.
Further, the image acquisition processing module is specifically configured to:
performing dirty data elimination and image target area extraction on the real-time image data of the wild animals; the dirty data includes false trigger images, low resolution images, and images of no practical value.
Further, the image compression encoding module is specifically configured to:
acquiring a wavelet coefficient of the first image;
mask marking the wavelet coefficients in the saliency target region;
calculating a wavelet coefficient mask image in the salient region by adopting a backtracking method;
adopting a maximum displacement plane lifting method to lift the marked wavelet coefficient bit plane, so that the transmission priority of the significant target area is higher than that of the background area;
carrying out lossless compression coding by adopting improved SPHIT aiming at a significant target region with higher transmission priority;
and performing lossy compression coding by adopting EZW aiming at the background area with lower transmission priority.
Further, the image data distributed transmission module is specifically configured to:
establishing a distributed image transmission model based on an independent coding and joint decoding mode, and performing data distribution transmission on the salient target region and the background region by adopting the distributed image transmission model;
processing transmission data by adopting a distributed compressed sensing algorithm, wherein the transmission data refers to a second image comprising the saliency target area and a background area;
and aiming at the processed transmission data, a joint decoding algorithm model is established for decoding, and the received redundant information is removed by combining the correlation among the joint signals.
Further, the image automatic recovery module is specifically configured to:
on the basis of a self-encoder network structure, a jump layer short connection structure is adopted to add low-layer characteristics output by a network front end convolution layer and a pooling layer into deconvolution operation, data after upsampling and upper-layer convolution pooling are combined to recover a wild animal distorted image, and a loss function adopts a mean square error function; the wildlife distorted image refers to the second image.
It should be noted that, for a specific workflow of the wild animal image transmission system, please refer to the foregoing method embodiment, which is not described herein again.
Optionally, the embodiment of the invention further provides another wild animal image transmission system based on a distributed architecture. As shown in fig. 7, may include: one or more processors 101, one or more input devices 102, one or more output devices 103, and memory 104, the processors 101, input devices 102, output devices 103, and memory 104 being interconnected via a bus 105. The memory 104 is used for storing a computer program comprising program instructions, and the processor 101 is configured to call the program instructions to execute the method of the above-mentioned embodiment part of the wild animal image transmission method based on the distributed architecture.
It should be understood that, in the embodiment of the present invention, the Processor 101 may be a Central Processing Unit (CPU), and the Processor may also be other general processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The input device 102 may include a keyboard or the like, and the output device 103 may include a display (LCD or the like), a speaker, or the like.
The memory 104 may include read-only memory and random access memory, and provides instructions and data to the processor 101. A portion of the memory 104 may also include non-volatile random access memory. For example, the memory 104 may also store device type information.
In a specific implementation, the processor 101, the input device 102, and the output device 103 described in this embodiment of the present invention may execute the implementation manner described in the embodiment of the wildlife image transmission method based on a distributed architecture provided in this embodiment of the present invention, which is not described herein again.
Referring to fig. 8 again, an embodiment of the present invention provides a system for remotely monitoring wild animals, including:
the data monitoring node is used for automatically acquiring image data of wild animal activities in a monitoring area, and performing dirty data elimination, target area extraction and compression coding on the image data to obtain transmission data; the transmission data comprises a salient target area with higher transmission priority and a background area with lower transmission priority;
a transmission module for transmitting the transmission data by a distributed mechanism;
and the data center is used for receiving the transmission data, recovering the transmission image based on an image automatic recovery algorithm of the improved self-encoder, and finishing the classified storage of the recovered wild animal image data.
In this embodiment, the specific steps of performing compression encoding on the image data are as follows:
1. and acquiring wavelet coefficients of the wild animal monitoring images.
Specifically, the input wild animal monitoring image is data obtained after dirty data removal and target area extraction. The wavelet coefficient specifically refers to the wavelet coefficient of the wild animal monitoring image obtained through decomposition in the row and column directions by adopting Mallat two-dimensional wavelet transform.
2. And calculating a wavelet coefficient mask image in the saliency target region.
Specifically, the saliency target region refers to a result obtained by extracting the saliency target region in image preprocessing, and is marked by masking a wavelet coefficient in the saliency target region.
3. And (3) lifting the marked wavelet coefficient bit plane by adopting a maximum displacement plane lifting method, and realizing the priority transmission of the significant target area.
Specifically, in order to realize the preferential transmission of the significant target region, the wavelet coefficient in the significant target region is boosted by adopting a maximum displacement plane boosting method to be higher than that of the background region, so that the wavelet coefficient of the significant target region is preferentially transmitted.
4. And realizing distributed coding of the image based on a hybrid coding algorithm.
Specifically, the distributed coding is to implement lossless coding of a saliency target area and lossy coding of a background area by a hybrid coding algorithm on the saliency target area and the background area in an image.
Specifically, improved SPHIT is adopted for lossless compression coding aiming at a wild animal monitoring image significance target area with higher transmission priority; and aiming at the background area information, a lossy compression mode is adopted by EZW, pixels in the background image are sequenced, and the transmission process of the data can be finished at any time according to the specific compression requirement or the specified compressed data amount.
In this embodiment, the image distributed transmission step specifically includes:
establishing a distributed image transmission model based on an independent coding and joint decoding mode, and performing data distribution transmission on the salient target region and the background region by adopting the distributed image transmission model;
processing transmission data by adopting a distributed compressed sensing algorithm, wherein the transmission data refers to a second image comprising the saliency target area and a background area;
and aiming at the processed transmission data, a joint decoding algorithm model is established for decoding, and the received redundant information is removed by combining the correlation among the joint signals.
In this embodiment, the image automatic recovery step specifically includes:
on the basis of a self-encoder network structure, a jump layer short connection structure is adopted to add low-layer characteristics output by a network front end convolution layer and a pooling layer into deconvolution operation, and data after upsampling and upper-layer convolution pooling are combined to recover a wild animal distorted image.
It should be noted that, for a more detailed description of the wild animal remote monitoring system according to the embodiment of the present invention, please refer to the foregoing embodiment, which is not described herein again.
Compared with the prior art, the wild animal remote monitoring system has the following beneficial effects:
1. the wild animal image transmission system based on the distributed transmission mechanism can ensure real-time transmission of data, improve the transmission efficiency of the system, reduce the operation power consumption of the system and effectively prolong the service cycle of the system.
2. Based on the extraction of the saliency target region, the image progressive compression coding algorithm based on the saliency perception adopts bit plane lifting and mixed coding strategies to ensure the transmission priority of an important region in an image, realizes the lossless compression of the saliency target region and the lossy compression of a background region, and can ensure the reconstruction quality of the saliency target region while still ensuring the reconstruction quality of the whole image.
3. The wild animal distorted image automatic recovery method based on the self-coding neural network is used for training and testing databases established respectively aiming at images of a wild animal region and a background region, and overcomes the influence of the difference of texture information on the image recovery quality. The quality of the recovered image is effectively improved through the improved self-encoder network, and reliable data support can be provided for subsequent related researches of wild animals.
Further, an embodiment of the present invention also provides a readable storage medium, in which a computer program is stored, where the computer program includes program instructions, and the program instructions, when executed by a processor, implement: the wild animal image transmission method based on the distributed architecture is described.
The computer readable storage medium may be an internal storage unit of the electronic device described in the foregoing embodiment, for example, a hard disk or a memory of a system. The computer readable storage medium may also be an external storage device of the system, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) Card, Flash memory Card (Flash Card), etc. provided on the system. Further, the computer readable storage medium may also include both an internal storage unit and an external storage device of the system. The computer-readable storage medium is used for storing the computer program and other programs and data required by the system. The computer readable storage medium may also be used to temporarily store data that has been output or is to be output.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A wild animal image transmission method based on a distributed architecture is characterized by comprising the following steps:
image acquisition and preprocessing: acquiring real-time image data of wild animals, and preprocessing the real-time image data of the wild animals to obtain a first image; the first image comprises a salient object region and a background region;
and image compression encoding: based on the image progressive compression coding algorithm of the significance perception, carrying out layered progressive compression coding on the significance target area and the background area to obtain a second image so as to realize lossless compression on the significance target area and lossy compression on the background area;
image distributed transmission: transmitting the second image through a distributed transmission mechanism;
an image automatic recovery step: and recovering the second image based on an image automatic recovery algorithm of the improved self-encoder.
2. The method of claim 1, wherein preprocessing the live wildanimal image data specifically comprises:
performing dirty data elimination and image target area extraction on the real-time image data of the wild animals; the dirty data includes false trigger images, low resolution images, and images of no practical value.
3. The method according to claim 2, wherein the image compression encoding step comprises in particular:
acquiring a wavelet coefficient of the first image;
mask marking the wavelet coefficients in the saliency target region;
calculating a wavelet coefficient mask image in the salient region by adopting a backtracking method;
adopting a maximum displacement plane lifting method to lift the marked wavelet coefficient bit plane, so that the transmission priority of the significant target area is higher than that of the background area;
carrying out lossless compression coding by adopting improved SPHIT aiming at a significant target region with higher transmission priority;
and performing lossy compression coding by adopting EZW aiming at the background area with lower transmission priority.
4. The method according to claim 3, wherein the image distributed transmission step comprises in particular:
establishing a distributed image transmission model based on an independent coding and joint decoding mode, and performing data distribution transmission on the salient target region and the background region by adopting the distributed image transmission model;
processing transmission data by adopting a distributed compressed sensing algorithm, wherein the transmission data refers to a second image comprising the saliency target area and a background area;
and aiming at the processed transmission data, a joint decoding algorithm model is established for decoding, and the received redundant information is removed by combining the correlation among the joint signals.
5. The method according to claim 4, wherein the image automatic restoration step comprises in particular:
on the basis of a self-encoder network structure, a jump layer short connection structure is adopted to add low-layer characteristics output by a network front end convolution layer and a pooling layer into deconvolution operation, and data after up-sampling and upper-layer convolution pooling are combined to recover a wild animal distorted image; the wildlife distorted image refers to the second image.
6. A wildlife image transmission system based on a distributed architecture, comprising a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory being interconnected, wherein the memory is configured to store a computer program comprising program instructions, the processor being configured to invoke the program instructions to perform the method according to any one of claims 1-5.
7. A wildlife image transmission system based on a distributed architecture, comprising:
the system comprises an image acquisition and preprocessing module, a first image acquisition and preprocessing module and a second image acquisition and preprocessing module, wherein the image acquisition and preprocessing module is used for acquiring real-time image data of wild animals and preprocessing the real-time image data of the wild animals to obtain a first image; the first image comprises a salient object region and a background region;
the image compression coding module is used for carrying out layered progressive compression coding on the saliency target area and the background area based on a saliency-aware image progressive compression coding algorithm to obtain a second image so as to realize lossless compression on the saliency target area and lossy compression on the background area;
the image distributed transmission module is used for transmitting the second image through a distributed transmission mechanism;
and the image automatic recovery module is used for recovering the second image based on the image automatic recovery algorithm of the improved self-encoder.
8. The system of claim 7, wherein the image compression encoding module is specifically configured to:
acquiring a wavelet coefficient of the first image;
mask marking the wavelet coefficients in the saliency target region;
calculating a wavelet coefficient mask image in the salient region by adopting a backtracking method;
adopting a maximum displacement plane lifting method to lift the marked wavelet coefficient bit plane, so that the transmission priority of the significant target area is higher than that of the background area;
carrying out lossless compression coding by adopting improved SPHIT aiming at a significant target region with higher transmission priority;
performing lossy compression coding by adopting EZW aiming at a background area with lower transmission priority;
the image distributed transmission module is specifically configured to:
establishing a distributed image transmission model based on an independent coding and joint decoding mode, and performing data distribution transmission on the salient target region and the background region by adopting the distributed image transmission model;
processing transmission data by adopting a distributed compressed sensing algorithm, wherein the transmission data refers to a second image comprising the saliency target area and a background area;
and aiming at the processed transmission data, a joint decoding algorithm model is established for decoding, and the received redundant information is removed by combining the correlation among the joint signals.
9. A system for remote monitoring of wildlife, comprising:
the data monitoring node is used for automatically acquiring image data of wild animal activities in a monitoring area, and performing dirty data elimination, target area extraction and compression coding on the image data to obtain transmission data; the transmission data comprises a salient target area with higher transmission priority and a background area with lower transmission priority;
a transmission module for transmitting the transmission data by a distributed mechanism;
and the data center is used for receiving the transmission data, recovering the transmission image based on an image automatic recovery algorithm of the improved self-encoder, and finishing the classified storage of the recovered wild animal image data.
10. The system of claim 9, wherein the transmission module is specifically configured to:
establishing a distributed image transmission model based on an independent coding and joint decoding mode, and performing data distribution transmission on the salient target region and the background region by adopting the distributed image transmission model;
processing the transmission data by adopting a distributed compressed sensing algorithm;
and aiming at the processed transmission data, a joint decoding algorithm model is established for decoding, and the received redundant information is removed by combining the correlation among the joint signals.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011451128.1A CN112616040A (en) | 2020-12-11 | 2020-12-11 | Wild animal image transmission method and system based on distributed architecture |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011451128.1A CN112616040A (en) | 2020-12-11 | 2020-12-11 | Wild animal image transmission method and system based on distributed architecture |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112616040A true CN112616040A (en) | 2021-04-06 |
Family
ID=75233015
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011451128.1A Pending CN112616040A (en) | 2020-12-11 | 2020-12-11 | Wild animal image transmission method and system based on distributed architecture |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112616040A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102332162A (en) * | 2011-09-19 | 2012-01-25 | 西安百利信息科技有限公司 | Method for automatic recognition and stage compression of medical image regions of interest based on artificial neural network |
| CN102833536A (en) * | 2012-07-24 | 2012-12-19 | 南京邮电大学 | Distributed video encoding and decoding method facing to wireless sensor network |
| CN103561242A (en) * | 2013-11-14 | 2014-02-05 | 北京林业大学 | Wild animal monitoring system based on wireless image sensor network |
| CN104581167A (en) * | 2014-03-07 | 2015-04-29 | 华南理工大学 | Distributed image compression transmission method for wireless sensor network |
| CN105846960A (en) * | 2016-04-22 | 2016-08-10 | 中国矿业大学 | Data compression coding and reliable transmission method of distributed real-time monitoring information source |
| US20180054630A1 (en) * | 2016-08-19 | 2018-02-22 | Apple Inc. | Compression of image assets |
| CN108990130A (en) * | 2018-09-29 | 2018-12-11 | 南京工业大学 | Distributed compressed sensing QoS routing method based on cluster |
| CN109982085A (en) * | 2017-12-28 | 2019-07-05 | 新岸线(北京)科技集团有限公司 | A kind of method of high precision image mixing compression |
-
2020
- 2020-12-11 CN CN202011451128.1A patent/CN112616040A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102332162A (en) * | 2011-09-19 | 2012-01-25 | 西安百利信息科技有限公司 | Method for automatic recognition and stage compression of medical image regions of interest based on artificial neural network |
| CN102833536A (en) * | 2012-07-24 | 2012-12-19 | 南京邮电大学 | Distributed video encoding and decoding method facing to wireless sensor network |
| CN103561242A (en) * | 2013-11-14 | 2014-02-05 | 北京林业大学 | Wild animal monitoring system based on wireless image sensor network |
| CN104581167A (en) * | 2014-03-07 | 2015-04-29 | 华南理工大学 | Distributed image compression transmission method for wireless sensor network |
| CN105846960A (en) * | 2016-04-22 | 2016-08-10 | 中国矿业大学 | Data compression coding and reliable transmission method of distributed real-time monitoring information source |
| US20180054630A1 (en) * | 2016-08-19 | 2018-02-22 | Apple Inc. | Compression of image assets |
| CN109982085A (en) * | 2017-12-28 | 2019-07-05 | 新岸线(北京)科技集团有限公司 | A kind of method of high precision image mixing compression |
| CN108990130A (en) * | 2018-09-29 | 2018-12-11 | 南京工业大学 | Distributed compressed sensing QoS routing method based on cluster |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10834415B2 (en) | Devices for compression/decompression, system, chip, and electronic device | |
| CN110099280B (en) | Video service quality enhancement method under limitation of wireless self-organizing network bandwidth | |
| CN113379601A (en) | Real world image super-resolution method and system based on degradation variational self-encoder | |
| CN109903351B (en) | Image compression method based on combination of convolutional neural network and traditional coding | |
| CN114758203B (en) | Residual intensive visual transformation method and system for hyperspectral image classification | |
| CN112819082A (en) | Satellite spectrum sensing data reconstruction method based on deep learning | |
| CN115115540A (en) | Unsupervised low-light image enhancement method and unsupervised low-light image enhancement device based on illumination information guidance | |
| CN114936977A (en) | Image deblurring method based on channel attention and cross-scale feature fusion | |
| Liu et al. | An Efficient and Robust Underwater Image Compression Scheme Based on Autoencoder | |
| CN112616040A (en) | Wild animal image transmission method and system based on distributed architecture | |
| CN113256744B (en) | Image coding and decoding method and system | |
| CN116416216A (en) | Quality evaluation method based on self-supervision feature extraction, storage medium and terminal | |
| CN112637609B (en) | Image real-time transmission method, sending end and receiving end | |
| CN114330400B (en) | Two-dimensional code image processing method, system, device, electronic equipment and storage medium | |
| CN111553961B (en) | Method and device for acquiring line manuscript corresponding color map, storage medium and electronic device | |
| CN116366852A (en) | Video coding and decoding method, device, equipment and medium for machine vision task | |
| Bao et al. | Image Compression for Wireless Sensor Network: A Model Segmentation‐Based Compressive Autoencoder | |
| CN110633385A (en) | Retrieval and compression method of medical image | |
| CN116743999A (en) | Unmanned aerial vehicle overhead transmission line inspection image compression method and system | |
| US20240244256A1 (en) | Method for decoding, method for encoding, and method for training model | |
| CN117173263B (en) | Image compression method for generating countermeasure network based on enhanced multi-scale residual error | |
| CN117319815B (en) | Video stream identification method and device based on image sensor, equipment and medium | |
| CN116668702B (en) | Video coding method, device, terminal equipment and storage medium | |
| CN114025198B (en) | Video cartoon method, device, equipment and medium based on attention mechanism | |
| Jin et al. | Super-resolution of compressed image by deep residual network |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210406 |
|
| RJ01 | Rejection of invention patent application after publication |