WO2021159990A1 - 植物花期播报方法、系统及计算机可读存储介质 - Google Patents
植物花期播报方法、系统及计算机可读存储介质 Download PDFInfo
- Publication number
- WO2021159990A1 WO2021159990A1 PCT/CN2021/074752 CN2021074752W WO2021159990A1 WO 2021159990 A1 WO2021159990 A1 WO 2021159990A1 CN 2021074752 W CN2021074752 W CN 2021074752W WO 2021159990 A1 WO2021159990 A1 WO 2021159990A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- plant
- flowering
- flowering period
- species
- blooming
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 241000196324 Embryophyta Species 0.000 claims abstract description 280
- 241000894007 species Species 0.000 claims abstract description 74
- 230000017260 vegetative to reproductive phase transition of meristem Effects 0.000 claims description 149
- 238000012549 training Methods 0.000 claims description 48
- 238000012360 testing method Methods 0.000 claims description 27
- 230000004044 response Effects 0.000 claims description 7
- 238000003062 neural network model Methods 0.000 claims description 5
- 241000167854 Bourreria succulenta Species 0.000 description 35
- 235000019693 cherries Nutrition 0.000 description 35
- 238000013527 convolutional neural network Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 9
- 230000008569 process Effects 0.000 description 6
- 238000013507 mapping Methods 0.000 description 5
- 230000001360 synchronised effect Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- FGUUSXIOTUKUDN-IBGZPJMESA-N C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 Chemical compound C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 FGUUSXIOTUKUDN-IBGZPJMESA-N 0.000 description 1
- 235000006040 Prunus persica var persica Nutrition 0.000 description 1
- 240000006413 Prunus persica var. persica Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000027758 ovulation cycle Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/70—Labelling scene content, e.g. deriving syntactic or semantic representations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- 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
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
Definitions
- the present invention relates to the technical field of artificial intelligence, and in particular to a method, system and computer readable storage medium for broadcasting plant flowering period.
- the purpose of the present invention is to provide a method, system and computer readable storage medium for broadcasting plant flowering dates, which can display information such as specific species, viewing positions, and flowering dates of plants currently available for viewing to users.
- the specific technical solutions are as follows:
- the present invention provides a method for broadcasting the flowering period of plants, which includes:
- identifying the plant in the image to obtain the type of the plant includes:
- the species recognition model established by pre-training is used to recognize plants in the image to obtain the species of the plants, and the species recognition model is a neural network model.
- the step of training the species recognition model includes: obtaining a training sample set, each sample in the training sample set is labeled with the type of plant; obtaining a test sample set, each sample in the test sample set is also labeled There are types of plants, where the test sample set is different from the training sample set; the species recognition model is trained based on the training sample set; the species recognition model is tested based on the test sample set; When the test result indicates that the recognition accuracy rate of the species recognition model is less than the preset accuracy rate, increase the number of samples in the training sample set for re-training; and when the test result indicates that the species recognition model is recognized accurately When the rate is greater than or equal to the preset accuracy rate, the training is completed.
- the plant variety recognition model is a neural network model.
- the open state includes: unopened, initial blooming, blooming, and ending.
- the method for broadcasting the flowering period of the plant further includes:
- the viewing recommendation information of the plant is pushed to users in the area where the shooting position is located.
- the viewing recommendation information of the plant includes one or more of the following information: the specific species of the plant, the flowering period, and the geographic location of the viewing location.
- the method for broadcasting the flowering period of the plant further includes:
- the flowering period broadcast map is shared with other users in a specific area, where the specific area is an area within a preset distance from the shooting position of the picture.
- the method for broadcasting the flowering period of the plant further includes:
- the flowering period broadcast map corresponding to the selected geographic area is displayed to the user, or the flowering period broadcast map corresponding to all geographic areas is displayed to the user.
- the method for broadcasting the flowering period of the plant further includes:
- the specific species and/or scenic spot information of the plants at the selected viewing location are displayed on the blooming broadcast map.
- the method for broadcasting the flowering period of the plant further includes:
- the flowering period broadcast map Compare the flowering period broadcast map with the historically recorded previous flowering period broadcast map. If there is a viewing location that is not marked on the flowering period broadcast map in the previous flowering period broadcast map, the viewing will be marked on the flowering period broadcast map.
- Location, the current flowering period of the plant is estimated according to the time of the last flowering period of the plant at the viewing location, and the specific species and current flowering period of the plant at the viewing location are correspondingly displayed in the flowering period broadcast map.
- the method for broadcasting the flowering period of the plant further includes:
- a zoomed-out icon of a target picture is displayed at the viewing location on the blooming broadcast map, wherein the target picture is a picture taken at the viewing location with the best open state of the plant.
- the method for broadcasting the flowering period of the plant further includes:
- the collection of pictures is shown to the user.
- the present invention also provides a plant blooming date broadcast system.
- the system includes a processor and a memory.
- the memory stores instructions.
- the plant blooming date broadcast is implemented.
- the steps of the method include: receiving an image, identifying plants in the image to obtain the type of the plant; calling a plant variety recognition model corresponding to the type of the plant to identify the specific variety and open state of the plant Obtain the shooting time and shooting location of the picture, and determine the flowering period of the plant according to the shooting time and the open state; mark the shooting location as the viewing location of the plant on the flowering period broadcast map, and display it accordingly The specific species and flowering period of the plant.
- the present invention also provides a computer-readable storage medium with instructions stored on the computer-readable storage medium, and when the instructions are executed, the steps of the method for broadcasting plant flowering are realized, the method comprising : Receive an image, identify the plant in the image to obtain the type of the plant; call the plant variety recognition model corresponding to the type of the plant to identify the specific variety and open state of the plant; obtain the shooting time of the picture And the shooting location, determining the flowering period of the plant according to the shooting time and the open state; marking the shooting location as the viewing location of the plant on the flowering period broadcast map, and correspondingly displaying the specific species and the flowering period of the plant .
- the method, system and computer-readable storage medium for plant blooming provided by the present invention have the following advantages:
- the shooting time and shooting position of the picture, the flowering period of the plant is determined according to the shooting time and the open state, and finally the shooting position is marked as the viewing location of the plant on the flowering period broadcast map, and the corresponding display is displayed.
- the specific species and flowering period of the plant are described.
- the present invention can upload plant images by any user, and determine the specific species, flowering period, and shooting location of plants according to the plant images uploaded by the user, thereby updating the viewing locations, specific species and flowering dates of the displayed plants in the flowering period broadcast map, so that all
- the flowering period broadcast map displays relevant information about plants available for viewing in the current time period in time, so as to provide users with accurate reference information for viewing plants and improve the viewing experience of users.
- FIG. 1 is a schematic diagram of a network environment of a plant blooming date broadcast system provided by an embodiment of the present invention
- Fig. 2 is a schematic flow chart of a method for broadcasting plant flowering dates according to an embodiment of the present invention
- Fig. 3 is a schematic structural diagram of a plant blooming date broadcast system provided by an embodiment of the present invention.
- Fig. 1 shows a schematic diagram of a network environment 100 of a plant flowering period broadcast system according to an embodiment of the present invention.
- the network environment 100 of the plant blooming broadcast system may include a mobile device 102, a remote server 103, a training device 104, and a database 105, which are wired or wirelessly coupled to each other through the network 106.
- the network 106 may be embodied as a wide area network (such as a mobile phone network, a public switched telephone network, a satellite network, the Internet, etc.), a local area network (such as Wi-Fi, Wi-Max, ZigBeeTM, BluetoothTM, etc.) and/or other forms of networking functions.
- the mobile device 102 may include a mobile phone, a tablet computer, a laptop computer, a personal digital assistant, and/or other computing devices configured to capture, store, and/or transmit images such as digital photos. Therefore, the mobile device 102 may include an image capture device such as a digital camera and/or may be configured to receive images from other devices.
- the mobile device 102 may include a display.
- the display may be configured to provide one or more user interfaces to the user 101, the user interface may include multiple interface elements, the user 101 may interact with the interface elements, and so on. For example, the user 101 can use the mobile device 102 to photograph a certain plant and upload or store the image.
- the mobile device 102 can output detailed introductions about the plant's category, specific species, and flowering period to the user, or can display the flowering period broadcast map to the user, push the viewing recommendation information of the plant, and prompt the user to share the plant with other users or friends.
- the remote server 103 may be configured to analyze images and the like received from the mobile device 102 via the network 106 to determine the type of plant, and to identify the specific variety and open status of the plant and other detailed information.
- the remote server 103 may also be configured to create and train the plant variety recognition model and species recognition model of this embodiment. The specific training process of the plant variety recognition model and the species recognition model will be described below in conjunction with specific embodiments.
- the training device 104 may be coupled to the network 106 to facilitate the training of the plant variety recognition model and the species recognition model.
- the training device 104 may have multiple CPUs and/or GPUs to assist in training the plant species recognition model and the species recognition model.
- the database 105 may be coupled to the network 106 and provide data required by the remote server 103 for relevant calculations.
- the database 105 may include a sample library storing a large number of images of different types of plants, and a sample library of images of multiple varieties of plants under the same category.
- the sample library may include a large number of image samples of different varieties of cherry blossoms in different locations, different seasons, weather at different times, and different shooting angles.
- the selected plant photos taken by the user can also be stored in a sample library corresponding to the plant species.
- the location information, seasonal information, and time information of the plant can also be recorded in the database.
- the database can be implemented by various database technologies known in the art.
- the remote server 103 can access the database 105 to perform related operations as needed.
- the network environment 100 herein is only an example. Those skilled in the art can add more devices or delete some devices as needed, and can modify the functions and configurations of some devices. In the following, a description will be given taking the broadcast of the flowering period of the cherry blossoms as an example.
- the method for broadcasting the flowering period of a plant includes the following steps:
- Step S101 receiving an image, and identifying plants in the image to obtain the type of the plant.
- the received image may be previously stored by the user or captured by the user in real time.
- the image may be previously stored in the mobile device 102 by the user or captured in real time by the user using an external camera connected to the mobile device 102 or a built-in camera of the mobile device 102.
- the user can also obtain the image in real time via the network.
- a species recognition model established by pre-training may be used to recognize plants in the image to obtain the species of the plants.
- the training step of the species recognition model may include: step a, obtaining a training sample set, each sample in the training sample set is labeled with the type of plant; step b, obtaining a test sample set, each of the test sample sets This book is also marked with the types of plants, where the test sample set is different from the training sample set; step c, training the species recognition model based on the training sample set; step d, based on the test sample set Test the species recognition model; step e, when the test result indicates that the recognition accuracy of the species recognition model is less than a preset accuracy rate, increase the number of samples in the training sample set for retraining; and step f When the test result indicates that the recognition accuracy rate of the species recognition model is greater than or equal to the preset accuracy rate, the training is completed.
- a certain number of image samples labeled with corresponding information are acquired for each plant type, and the number of image samples prepared for each plant type may be equal or different.
- the corresponding information labeled for each image sample may include the plant species in the image sample (including scientific name, nickname, category name of botanical classification, etc.).
- the image samples obtained for each plant species can include as much as possible the different shooting angles, different lighting conditions, different weather (for example, the same plant may have different forms in sunny days and rainy days), different months or seasons (for example, the same The shape of plants may be different in different months or seasons), different times (for example, the shape of the same plant may be different in the morning and night of each day), different growth environments (for example, the shape of the same plant may be different indoors and outdoors), and different geographies An image of a location (for example, the same plant may grow differently in different geographic locations).
- the corresponding information labeled for each image sample may also include information such as the shooting angle, illumination, weather, season, time, growth environment, or geographic location of the image sample.
- the image samples that have undergone the above-mentioned annotation processing can be divided into a training sample set for training the species recognition model and a test sample set for testing the training result.
- the number of samples in the training sample set is significantly greater than the number of samples in the test sample set.
- the number of samples in the test sample set can account for 5% to 20% of the total number of image samples, and the corresponding training sample set The number of samples can account for 80% to 95% of the total number of image samples.
- the number of samples in the training sample set and the test sample set can be adjusted as needed.
- the training sample set can be used to train the species recognition model, and the test sample set can be used to test the recognition accuracy of the trained species recognition model. If the recognition accuracy does not meet the requirements, increase the number of image samples in the training sample set, and use the updated training sample set to retrain the species recognition model until the recognition accuracy of the trained species recognition model meets the requirements. If the recognition accuracy meets the requirements, the training ends. In one embodiment, it can be judged whether the training can end based on whether the recognition accuracy rate is less than the preset accuracy rate. In this way, a trained species recognition model whose output accuracy meets the requirements can be used to recognize plant species.
- the species recognition model is a neural network model, such as a deep convolutional neural network (CNN) or a deep residual network (Resnet).
- the deep convolutional neural network is a deep feedforward neural network, which uses the convolution kernel to scan the plant image, extracts the features to be recognized in the plant image, and then recognizes the features to be recognized in the plant.
- the original plant image can be directly input to the deep convolutional neural network model without preprocessing the plant image.
- the deep convolutional neural network model has higher recognition accuracy and recognition efficiency.
- the deep residual network model Compared with the deep convolutional neural network model, the deep residual network model adds an identity mapping layer, which can avoid the accuracy saturation or even saturation caused by the convolutional neural network as the network depth (the number of layers in the network) increases.
- the identity mapping function of the identity mapping layer in the residual network model needs to satisfy: the sum of the input of the identity mapping function and the residual network model is equal to the output of the residual network model.
- the residual network model changes the output more obviously, so it can greatly improve the recognition accuracy and recognition efficiency of plant physiological period recognition, and then improve the recognition accuracy and recognition efficiency of plants.
- Step S102 Invoking the plant variety recognition model corresponding to the type of plant to identify the specific variety and open state of the plant.
- the aforementioned species recognition model can only recognize the types of plants and cannot recognize the specific species of plants, in an embodiment of the present invention, corresponding plant species recognition models are pre-trained for different plant types. After the plant species is recognized in step S101, the plant species recognition model corresponding to the plant species is called to perform recognition again, so as to recognize the specific species of plants in the image, and at the same time, the open state of the plants can be recognized.
- step S101 recognizes that the plant is a cherry blossom
- a pre-trained cherry blossom variety recognition model is called to re-recognize the image, so as to identify the specific variety and open state of the cherry blossom.
- the open state of a plant can be divided according to the state of the flower bud and the degree of the whole plant blooming. For example, it can be divided into four states: unopened, early blooming, blooming and ending. For example, if the plant has no buds or only a few buds, then The open state is unopened. When the plant has more flower buds or a few flower buds open, the open state is the initial opening. If the proportion of the whole plant flowering exceeds a certain threshold (for example, 80%), the open state is in full bloom. If the proportion of withering exceeds a certain threshold (for example, 70%), the open state is closed.
- a certain threshold for example, 80%
- the open state is in full bloom.
- a certain threshold for example, 70%
- the training method of the plant variety recognition model corresponding to each plant species is basically the same. Taking the cherry blossom as an example, the training method of the cherry blossom variety recognition model is briefly introduced. There are many varieties of sakura, such as Hanhi Sakura, Kawazu Sakura, Rainy Weeping Sakura, Somei Yoshino Sakura, Oshima Sakura, Daisy Sakura, etc. Different varieties of cherry blossoms have their unique morphological characteristics. When training the cherry blossom species recognition model, obtain a certain number of image samples labeled with corresponding information for each cherry blossom species. The number of image samples prepared for each cherry blossom can be equal or unequal, and the labeled information should include image samples The varieties of cherry blossoms and their blooming state.
- the image samples obtained for each cherry blossom variety can include as much as possible the different shooting angles, different lighting conditions, different weather (for example, the same plant may have different forms on sunny days and rainy days), different months or seasons (for example, the same The shape of plants may be different in different months or seasons), different times (for example, the shape of the same plant may be different in the morning and night of each day), different growth environments (for example, the shape of the same plant may be different indoors and outdoors), and different geographies An image of a location (for example, the same plant may grow differently in different geographic locations).
- the corresponding information labeled for each image sample may also include information such as the shooting angle, illumination, weather, season, time, growth environment, or geographic location of the image sample.
- the cherry blossom species recognition model is also a neural network-based model, such as a deep convolutional neural network (CNN) or a deep residual network (Resnet). After the cherry blossom image samples are obtained, the cherry blossom species recognition model can be trained according to the above-mentioned training process of the species recognition model, which will not be repeated here.
- CNN deep convolutional neural network
- Resnet deep residual network
- the above-mentioned plant species identification model can simultaneously identify the specific species and the open state of plants.
- a separate plant variety recognition model and an open state recognition model can also be set at the same time.
- a separate plant variety recognition model is only used to identify specific species of plants, and the open state recognition model is used for Recognizing the open state of plants, it can be understood that by setting up separate plant variety recognition models and open state recognition models, the accuracy of variety recognition and open state recognition can be improved.
- the open state recognition model is used to recognize the open state of the plants in the image, it is also possible to combine the shooting position and shooting time information of the image to perform a second confirmation of the recognition result.
- the open state recognition model recognizes a certain When the open state of a plant in an image is in full bloom, combined with the shooting location and shooting time of the image, if it can be predicted that the open state of the same species of plants at this shooting location during the shooting time should be in full bloom, then it can be confirmed that The recognition result of the open state recognition model is accurate. Otherwise, it can be considered that the recognition result of the open state recognition model may be wrong. In this way, the open state of the plants in the image can be re-identified or directly manually recognized, or further The open state recognition model is retrained until the recognition accuracy of the open state recognition model meets the requirements. It can be seen that the accuracy of the recognition result of the open state recognition model can be guaranteed through the second confirmation of the shooting position and the shooting time.
- Step S103 Acquire the shooting time and shooting position of the image, and determine the flowering period of the plant according to the shooting time and the open state.
- the shooting time and shooting location of the image belong to the attribute information of the image. Therefore, the shooting time and shooting location of the image can be obtained from the attribute information of the image.
- the flowering period of the plant can be determined according to the shooting time and the open state.
- the flowering period of a plant may include the first blooming period and the blooming period.
- the image was taken on February 20, 2019, and the shooting location was location A.
- the cherry blossoms at location A can be predicted to bloom and bloom at location A based on the historically recorded flowering information For example, in the last flowering period, the cherry blossoms at this location A had their first blooming date on March 1, 2018 and their full blooming date was March 15, 2018, then it is predicted that the cherry blossoms at this location A will be in the current blooming period
- the first blooming date is March 1, 2019, and the blooming date is March 15, 2019;
- the shooting time can be used as the first blooming period of the cherry blossoms at the location A, and then The blooming period of the cherry blossoms at the location A is predicted based on the initial blooming period; if the open state is in full bloom, the shooting time is taken as the blooming period of the cherry blossoms at the location A.
- Step S104 Mark the shooting location as the viewing location of the plant on the flowering period broadcast map, and correspondingly display the specific species and flowering period of the plant.
- the display of the mobile device 102 provides the user with a user interface, and the flowering period broadcast map can be displayed on the user interface.
- the flowering period broadcast map can be used to display a specific plant species such as various viewing locations of cherry blossoms. It is also possible to display various viewing locations of multiple plant species such as cherry blossoms and peach blossoms at the same time, which is not limited in this embodiment.
- step S103 the shooting location of the image has been obtained, and the flowering period and specific species of the cherry blossoms in the image are also obtained, and then the flowering period broadcast map can be marked
- the shooting position is a viewing spot of cherry blossoms, and the specific varieties and flowering dates of cherry blossoms are correspondingly displayed at the same time.
- the shooting location is park A, and park A is marked with a specific sign in the flowering period broadcast map, and the specific species and flowering period of the cherry blossoms are displayed at the specific sign.
- the user can see from the flowering period broadcast map that the location corresponding to the shooting position has cherry blossoms available for viewing, and learn about the specific varieties and flowering dates of the cherry blossoms here.
- the method for broadcasting plant flowering period provided by the embodiment of the present invention can upload plant images by any user, and determine the specific species, flowering period, and shooting location of plants according to the plant images uploaded by the user, the viewing locations of the plants are updated in the flowering period broadcasting map.
- the flowering period broadcast map can timely display relevant information of plants available for viewing in the current time period, thereby providing users with accurate reference information for viewing plants and improving the viewing experience of users.
- the method for reporting the flowering period of the plant in this embodiment may further include: pushing the plant to users in the area where the shooting position is when the open state of the plant is early blooming or in full bloom.
- Recommended viewing information That is, if it is recognized that the open state of the plant is early blooming or in full bloom, it means that the plant is currently in the best viewing time period.
- the remote server 103 can report to other users in the area where the shooting location is located. Push the viewing recommendation information of the plant, prompting other users in the area where the shooting location is located to watch the plant at the shooting location. A user near the park A pushes the viewing recommendation information of the plant.
- the viewing recommendation information of the plant includes one or more of the following information: the specific species of the plant, the flowering period, the geographic location of the viewing location, etc. Of course, it may also include other information, which is not limited in this embodiment.
- the way of pushing the viewing recommendation information may be in the form of short message, in-app message, or other forms, which is not limited in this embodiment.
- the flowering period broadcast map can also be shared with other users in a specific area, where the specific area is within a preset distance from the shooting position of the picture Area. That is, the blooming broadcast map can be shared with other users or friends in a specific area (for example, within 5 kilometers from the shooting location).
- the user uploads a photographed plant picture, and the plant picture is marked on the blooming broadcast map.
- the user may choose to actively share the flowering period broadcast map with other users or friends, so as to invite other users or friends to this viewing location to view the plant.
- the blooming broadcast map can be shared with other users in the application, or can be shared with other users through other social platforms.
- the flowering period broadcast map may be processed and shared in the form of pictures, or the flowering period broadcast map may be processed into an H5 page for sharing, which is not limited in this embodiment.
- the user can click to view the recommended plant viewing locations in the current time period.
- the plant viewing locations are generally in parks, botanical gardens and other scenic spots.
- the mobile device 102 can In response to the user's operation of selecting the viewing location, the specific species and/or scenic spot information of the plants at the selected viewing location are displayed on the blooming broadcast map, such as scenic spot introduction, traffic information, traffic information, tickets, and others Charge information in order to provide users with more information about where to see plants.
- the user wishes to view the flowering status of the plant in a certain area or the entire area
- the mobile device 102 may respond to the user's operation to display the flowering period broadcast map corresponding to the selected geographic area to the user
- the flowering period broadcast map corresponding to all geographic regions is displayed to the user. For example, if the user chooses to view the flowering status of the plant in the Beijing area, the mobile device 102 will display the flowering period broadcast map of the Beijing area to the user.
- the user chooses to view the flowering status of the plant in all areas of China, it will include The flowering period broadcast map of all regions in China is shown to users.
- the method for broadcasting the flowering period of the plant in order to mark all the places available for viewing of the plant, and to provide users with comprehensive viewing information, the flowering period broadcasting map and the historical record of the previous flowering period can also be reported.
- the map is compared, and if there is a viewing location that is not marked on the flowering period reporting map in the previous flowering period broadcasting map, the viewing location is marked on the flowering period broadcasting map, and then the viewing location is based on the previous viewing location of the plant.
- the time of the flowering period predicts the current flowering period of the plant, and correspondingly displays the specific species and the current flowering period of the plant at the viewing location in the flowering period broadcast map.
- the current flowering period broadcast map has marked three viewing locations of the plants, namely locations A, B, and C, and the flowering period broadcast map of the previous flowering period has marked 4 locations for the plants.
- the viewing locations are locations A, B, C, and D.
- the plant (because no user has taken a plant picture at location D and uploaded it in the current flowering period, the location D cannot be marked on the flowering period broadcast map in the current flowering period), therefore, the location D is also marked in the flowering period broadcast map of the current flowering period
- the location D is also marked in the flowering period broadcast map of the current flowering period
- To view the location at the same time obtain the specific species of the plant at the location D of the last flowering period and the specific time of the flowering period, and estimate the time of the current flowering period based on the time of the last flowering period, so that the location D is correspondingly displayed on the broadcast map of the current flowering period.
- the specific species of the plant and the current flowering period can be used to update the viewing locations in the flowering period broadcast map of the current flowering period, so as to make up for the insufficiency of marking viewing locations by uploading plant images by the user.
- a zoomed-out icon of the target picture may be displayed at the viewing location on the blooming broadcast map, where the target picture is a picture taken at the viewing location with the best open state of the plant.
- the most recently taken picture (for example, within 24 hours) of the plant in the best open state may be used as the zoom-out icon at the corresponding viewing location.
- the picture with the best open state for example, you can choose the picture with more than 80% of the whole plant blooming, you can also choose the picture with the flowers occupying the most area of the picture, or the picture with the best open state identified by the above-mentioned open state recognition model picture.
- the received images of the plants taken at the same viewing location may also be combined into a picture set.
- the pictures in the picture set shown may be taken by the same user or may include those taken by other users.
- Each picture of can be sorted comprehensively according to the shooting time and open state.
- the user chooses to view the picture collection (for example, clicking the zoom-out icon described above)
- the picture collection is displayed to the user so that the user can view the flowering situation of the plant at the viewing location.
- the present invention also provides a plant blooming date broadcast system.
- the plant flowering date broadcast system 200 may include a processor 210 and a memory 220.
- the memory 220 stores instructions. When the instructions are executed by the processor 210, the steps in the plant flowering date broadcast method described above can be implemented. .
- the processor 210 may perform various actions and processing according to instructions stored in the memory 220.
- the processor 210 may be an integrated circuit chip with signal processing capability.
- the above-mentioned processor may be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, or discrete hardware components.
- DSP digital signal processor
- ASIC application specific integrated circuit
- FPGA off-the-shelf programmable gate array
- Various methods, steps, and logical block diagrams disclosed in the embodiments of the present invention can be implemented or executed.
- the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc., and may be an X86 architecture or an ARM architecture.
- the memory 220 stores executable instructions, and the instructions are executed by the processor 210 for the above-mentioned method for broadcasting the plant flowering period.
- the memory 220 may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory.
- the non-volatile memory may be read only memory (ROM), programmable read only memory (PROM), erasable programmable read only memory (EPROM), electrically erasable programmable read only memory (EEPROM), or flash memory.
- Volatile memory may be random access memory (RAM), which acts as an external cache.
- RAM synchronous dynamic random access memory
- SDRAM synchronous dynamic random access memory
- DDRSDRAM double data rate synchronous dynamic random access memory
- ESDRAM enhanced synchronous dynamic random access memory
- SLDRAM synchronous connection dynamic random access memory
- DR RAM direct memory bus random access memory
- the present invention also provides a computer-readable storage medium with instructions stored on the computer-readable storage medium.
- the instructions When executed, the steps in the above-described method for broadcasting plant flowering can be realized.
- the computer-readable storage medium in the embodiment of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory. It should be noted that the computer-readable storage media described herein are intended to include, but are not limited to, these and any other suitable types of memory.
- each block in the flowchart or block diagram may represent a module, program segment, or part of code, and the module, program segment, or part of code contains one or more logic for implementing the specified Executable instructions for the function.
- the functions marked in the block may also occur in a different order from the order marked in the drawings. For example, two blocks shown one after another can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved.
- each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart can be implemented by a dedicated hardware-based system that performs the specified functions or operations Or it can be realized by a combination of dedicated hardware and computer instructions.
- the various exemplary embodiments of the present invention may be implemented in hardware or special purpose circuits, software, firmware, logic, or any combination thereof. Certain aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device.
- firmware or software that may be executed by a controller, microprocessor, or other computing device.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Animal Husbandry (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Agronomy & Crop Science (AREA)
- General Business, Economics & Management (AREA)
- Mining & Mineral Resources (AREA)
- Marine Sciences & Fisheries (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Automation & Control Theory (AREA)
- Image Processing (AREA)
Abstract
Description
Claims (15)
- 一种植物花期播报方法,其特征在于,包括:接收一植物的图像,识别所述图像中的植物以得到所述植物的种类;调用所述植物的种类对应的植物品种识别模型,识别所述植物的具体品种以及开放状态;获取所述图片的拍摄时间和拍摄位置,根据所述图片的拍摄时间和所述植物的开放状态确定所述植物的花期;在一花期播报地图上标记所述图片的拍摄位置为所述植物的观赏地点,并对应显示所述植物的具体品种以及花期。
- 如权利要求1所述的植物花期播报方法,其特征在于,识别所述图像中的植物以得到所述植物的种类,包括:利用预先训练建立的物种识别模型识别所述图像中的植物以得到所述植物的种类,所述物种识别模型为神经网络模型。
- 如权利要求2所述的植物花期播报方法,其特征在于,所述物种识别模型的训练步骤包括:获取训练样本集,所述训练样本集中的每一样本标注有植物的种类;获取测试样本集,所述测试样本集中的每一样本也标注有植物的种类,其中,所述测试样本集不同于所述训练样本集;基于所述训练样本集对所述物种识别模型进行训练;基于所述测试样本集对所述物种识别模型进行测试;在所述测试结果指示所述物种识别模型的识别准确率小于预设准确率时,增加所述训练样本集中的样本数量进行再次训练;以及在所述测试结果指示所述物种识别模型的识别准确率大于或等于所述预设准确率时,完成训练。
- 如权利要求1所述的植物花期播报方法,其特征在于,所述植物品种识别模型为神经网络模型。
- 如权利要求1所述的植物花期播报方法,其特征在于,所述植物的开放状态包括:未开、初开、盛开和完结。
- 如权利要求5所述的植物花期播报方法,其特征在于,还包括:当所述植物的开放状态为初开或盛开时,向所述拍摄位置所在区域内的用户推送所述植物的观赏推荐信息。
- 如权利要求6所述的植物花期播报方法,其特征在于,所述植物的观赏推荐信息包括以下信息中的一个或多个:所述植物的具体品种、花期、观赏地点的地理位置。
- 如权利要求5所述的植物花期播报方法,其特征在于,还包括:当所述植物的开放状态为盛开时,将所述花期播报地图分享给特定区域内的其它用户,其中所述特定区域为与所述图片的拍摄位置在预设距离内的区域。
- 如权利要求1所述的植物花期播报方法,其特征在于,还包括:响应于用户操作,将选定地理区域对应的所述花期播报地图展示给用户,或者,将所有地理区域对应的所述花期播报地图展示给用户。
- 如权利要求1所述的植物花期播报方法,其特征在于,还包括:响应于用户选择一观赏地点的操作,在所述花期播报地图中显示选定的观赏地点处的所述植物的具体品种和/或景点信息。
- 如权利要求1所述的植物花期播报方法,其特征在于,还包括:将所述花期播报地图与历史记录的上一花期播报地图进行比对,若上一花期播报地图中存在所述花期播报地图未标注的观赏地点,则在所述花期播报地图中标注出该观赏地点,再根据该观赏地点处所述植物的上一花期的时间预估所述植物的当前花期,并在所述花期播报地图中对应显示该观赏地点处所述植物的具体品种以及当前花期。
- 如权利要求1所述的植物花期播报方法,其特征在于,还包括:在所述花期播报地图上的观赏地点处显示目标图片的缩小图标,其中所述目标图片为在所述观赏地点处拍摄的所述植物的开放状态最好的图片。
- 如权利要求1所述的植物花期播报方法,其特征在于,还包括:将接收到的在所述观赏地点处拍摄的所述植物的图像组成图片集,其中各个图片按照拍摄时间和开放状态进行排序;响应于用户操作,将所述图片集展示给用户。
- 一种植物花期播报系统,其特征在于,所述系统包括处理器和存储器,所述存储器上存储有指令,当所述指令被所述处理器执行时,实现如权利要求1至13中任一项所述的方法的步骤。
- 一种计算机可读存储介质,其特征在于,所述计算机可读存储介质上存储有指令,当所述指令被执行时,实现如权利要求1至13中任一项所述的方法的步骤。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US17/629,413 US12026964B2 (en) | 2020-02-14 | 2021-02-02 | Plant blooming period broadcast method and system, and computer-readable storage medium |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010093209.2 | 2020-02-14 | ||
CN202010093209.2A CN111291689B (zh) | 2020-02-14 | 2020-02-14 | 植物花期播报方法、系统及计算机可读存储介质 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021159990A1 true WO2021159990A1 (zh) | 2021-08-19 |
Family
ID=71029241
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2021/074752 WO2021159990A1 (zh) | 2020-02-14 | 2021-02-02 | 植物花期播报方法、系统及计算机可读存储介质 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN111291689B (zh) |
WO (1) | WO2021159990A1 (zh) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111291689B (zh) * | 2020-02-14 | 2024-02-27 | 杭州睿琪软件有限公司 | 植物花期播报方法、系统及计算机可读存储介质 |
CN113837707B (zh) * | 2020-06-08 | 2024-04-09 | 杭州睿琪软件有限公司 | 辅助用户进行植物养护的方法和计算机系统 |
CN111931070B (zh) * | 2020-09-29 | 2021-01-01 | 江西省气象信息中心(江西省气象培训中心、江西省农村经济信息中心) | 旅游目的地推荐方法、装置、可读存储介质及计算机设备 |
CN113556473B (zh) * | 2021-09-23 | 2022-02-08 | 深圳市天和荣科技有限公司 | 花朵开花过程的拍摄方法、装置、电子设备及存储介质 |
CN113886620A (zh) * | 2021-11-01 | 2022-01-04 | 杭州睿胜软件有限公司 | 植物推荐方法、可读存储介质和电子设备 |
CN114707585A (zh) * | 2022-03-22 | 2022-07-05 | 杭州睿胜软件有限公司 | 过敏物种播报方法、系统及可读存储介质 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108647652A (zh) * | 2018-05-14 | 2018-10-12 | 北京工业大学 | 一种基于图像分类和目标检测的棉花发育期自动识别方法 |
CN110363146A (zh) * | 2019-07-16 | 2019-10-22 | 杭州睿琪软件有限公司 | 一种物体识别方法、装置、电子设备和存储介质 |
CN110378303A (zh) * | 2019-07-25 | 2019-10-25 | 杭州睿琪软件有限公司 | 用于对象识别的方法及系统 |
CN111291689A (zh) * | 2020-02-14 | 2020-06-16 | 杭州睿琪软件有限公司 | 植物花期播报方法、系统及计算机可读存储介质 |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008070557A (ja) * | 2006-09-13 | 2008-03-27 | Clarion Co Ltd | ランドマーク表示方法、ナビゲーション装置、車載装置及びナビゲーションシステム |
CN102997907A (zh) * | 2011-09-08 | 2013-03-27 | 昆达电脑科技(昆山)有限公司 | 主动显示大自然讯息的方法及个人导航装置 |
CN104318240B (zh) * | 2014-07-18 | 2017-11-07 | 天津理工大学 | 一种基于计算机视觉的花蕾判别方法 |
CN105022789A (zh) * | 2015-06-23 | 2015-11-04 | 中国科学院昆明植物研究所 | 一种基于地理位置和特征图像的植物物种鉴定方法及系统 |
US20180012167A1 (en) * | 2016-07-05 | 2018-01-11 | Sostena, Inc. | System and Method for Crop Management |
US10088816B1 (en) * | 2017-06-26 | 2018-10-02 | International Business Machines Corporation | Cognitive plant clinic |
WO2019237200A1 (en) * | 2018-06-12 | 2019-12-19 | Paige Growth Technologies Inc. | Precision agriculture system and related methods |
CN109146703A (zh) * | 2018-08-09 | 2019-01-04 | 成都天地量子科技有限公司 | 一种农田作物种类实时标记系统 |
CN109544505A (zh) * | 2018-10-16 | 2019-03-29 | 江苏省无线电科学研究所有限公司 | 咖啡开花期的检测方法、装置及电子设备 |
CN109447150B (zh) * | 2018-10-26 | 2020-12-18 | 杭州睿琪软件有限公司 | 一种植物观赏方法、装置、电子设备和存储介质 |
CN109815846B (zh) * | 2018-12-29 | 2021-08-27 | 腾讯科技(深圳)有限公司 | 图像处理方法、装置、存储介质和电子装置 |
CN110555416B (zh) * | 2019-09-06 | 2021-09-03 | 杭州睿琪软件有限公司 | 一种植物识别方法及装置 |
-
2020
- 2020-02-14 CN CN202010093209.2A patent/CN111291689B/zh active Active
-
2021
- 2021-02-02 WO PCT/CN2021/074752 patent/WO2021159990A1/zh active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108647652A (zh) * | 2018-05-14 | 2018-10-12 | 北京工业大学 | 一种基于图像分类和目标检测的棉花发育期自动识别方法 |
CN110363146A (zh) * | 2019-07-16 | 2019-10-22 | 杭州睿琪软件有限公司 | 一种物体识别方法、装置、电子设备和存储介质 |
CN110378303A (zh) * | 2019-07-25 | 2019-10-25 | 杭州睿琪软件有限公司 | 用于对象识别的方法及系统 |
CN111291689A (zh) * | 2020-02-14 | 2020-06-16 | 杭州睿琪软件有限公司 | 植物花期播报方法、系统及计算机可读存储介质 |
Also Published As
Publication number | Publication date |
---|---|
CN111291689B (zh) | 2024-02-27 |
CN111291689A (zh) | 2020-06-16 |
US20220358772A1 (en) | 2022-11-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021159990A1 (zh) | 植物花期播报方法、系统及计算机可读存储介质 | |
CN110555416B (zh) | 一种植物识别方法及装置 | |
CN110378303B (zh) | 用于对象识别的方法及系统 | |
CN109068056B (zh) | 一种电子设备及其拍摄图像的滤镜处理方法、存储介质 | |
WO2021223607A1 (zh) | 植物状态评估方法、系统及计算机可读存储介质 | |
CN105472553B (zh) | 基于移动终端的植物识别方法 | |
WO2023098463A1 (zh) | 植物识别方法、植物识别设备和植物识别系统 | |
WO2021135828A1 (zh) | 对象识别方法、装置及设备 | |
CN110493517A (zh) | 图像捕获装置的辅助拍摄方法和图像捕获装置 | |
CN109447150A (zh) | 一种植物观赏方法、装置、电子设备和存储介质 | |
ES2377303A1 (es) | Método y sistema para recomendar fotografías. | |
US20180025215A1 (en) | Anonymous live image search | |
US20140258297A1 (en) | Automatic grouping of photos into folders and naming the photo folders | |
WO2022262585A1 (zh) | 植物图片识别方法、可读存储介质及电子设备 | |
WO2024027476A1 (zh) | 用于植物图像的识别处理方法、系统和存储介质 | |
CN102194215A (zh) | 图像处理设备、方法以及程序 | |
CN103823678B (zh) | 图像处理方法和图像处理装置 | |
WO2021088657A1 (zh) | 获取物种识别名称的方法及装置 | |
JP2003274320A (ja) | 画像撮像装置、画像情報処理装置及び画像情報処理方法 | |
WO2024120288A1 (zh) | 植物养护方法、系统及可读存储介质 | |
WO2023179317A1 (zh) | 过敏物种播报方法、系统及可读存储介质 | |
US12026964B2 (en) | Plant blooming period broadcast method and system, and computer-readable storage medium | |
JP6863159B2 (ja) | データベース構築方法、およびデータベース構築プログラム | |
WO2023093480A1 (zh) | 物种游览方法、游览系统及可读存储介质 | |
Baskauf et al. | Digital plant images as specimens: toward standards for photographing living plants |
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: 21754653 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: 21754653 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 1205 DATED 28.03.2023) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21754653 Country of ref document: EP Kind code of ref document: A1 |