CN115147716A - Forest area felling detection method and device, electronic equipment and storage medium - Google Patents
Forest area felling detection method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115147716A CN115147716A CN202210528348.2A CN202210528348A CN115147716A CN 115147716 A CN115147716 A CN 115147716A CN 202210528348 A CN202210528348 A CN 202210528348A CN 115147716 A CN115147716 A CN 115147716A
- Authority
- CN
- China
- Prior art keywords
- forest
- characteristic
- image
- forest region
- detection
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
- Y02A40/22—Improving land use; Improving water use or availability; Controlling erosion
Abstract
The embodiment of the application provides a forest region felling detection method and device, electronic equipment and a storage medium, relates to the technical field of artificial intelligence and aims to solve the problems of poor real-time performance and high detection cost of forest region felling detection. The forest area felling detection method comprises the following steps: under the condition that a first characteristic of a first forest region image is detected, detecting whether a second characteristic of a second forest region image exists or not, wherein the first forest region image is acquired through detection equipment arranged on an outdoor tower body, the second forest region image comprises all characteristics or partial characteristics of the first forest region image, the second forest region image comprises the first characteristic, the first characteristic is a characteristic matched with the characteristic of cutting equipment, and the second characteristic is a characteristic matched with the characteristic of cutting trees; and under the condition that the second characteristic exists in the second forest region image, determining that the forest region corresponding to the second forest region image has a cutting behavior.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a forest region felling detection method and device, electronic equipment and a storage medium.
Background
At present, forest region felling detection methods mainly comprise the following two main types: firstly, change information of vegetation coverage conditions in forest regions is obtained through remote sensing satellite images, and the mode is likely to be detected only by large-scale felling and has poor real-time performance; secondly, the tree state is detected by arranging the sensors in the forest area, and the sensors are required to be arranged at all positions of the forest area in the mode, so that the detection cost is high. Therefore, the problems of poor real-time performance and high detection cost exist in the existing forest region felling detection method.
Disclosure of Invention
The embodiment of the application provides a forest region felling detection method and device, electronic equipment and a storage medium, and aims to solve the problems of poor real-time performance and high detection cost of an existing forest region felling detection method.
The embodiment of the application is realized as follows:
in a first aspect, an embodiment of the present application provides a forest region felling detection method, including:
under the condition that a first characteristic of a first forest region image is detected, detecting whether a second characteristic of a second forest region image exists or not, wherein the first forest region image is acquired through detection equipment arranged on an outdoor tower body, the second forest region image comprises all characteristics or partial characteristics of the first forest region image, the second forest region image comprises the first characteristic, the first characteristic is a characteristic matched with the characteristic of cutting equipment, and the second characteristic is a characteristic matched with the characteristic of cutting trees;
and under the condition that the second characteristic exists in the second forest region image, determining that the forest region corresponding to the second forest region image has a cutting behavior.
In a second aspect, an embodiment of the present application provides a forest region felling detection device, including:
the detection device comprises a first detection module, a second detection module and a control module, wherein the first detection module is used for detecting whether a second forest region image has a second characteristic or not under the condition that a first forest region image has the first characteristic, the first forest region image is acquired through detection equipment arranged on an outdoor tower body, the second forest region image comprises all characteristics or partial characteristics of the first forest region image, the second forest region image comprises the first characteristic, the first characteristic is a characteristic matched with the characteristic of felling equipment, and the second characteristic is a characteristic matched with the characteristic of felling trees;
and the determining module is used for determining that the forest region corresponding to the second forest region image has the cutting behavior under the condition that the second characteristic exists in the second forest region image.
In a third aspect, an embodiment of the present application further provides an electronic device, which includes a processor, a memory, and a computer program stored on the memory and executable on the processor, where the computer program, when executed by the processor, implements the steps of the forest area felling detection method according to the first aspect.
In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the forest area felling detection method according to the first aspect are implemented.
In this application embodiment, utilize the detection equipment of installing in outdoor tower body to gather the forest zone image, under the condition that detects forest zone image and have and fell equipment characteristic assorted characteristic, further detect whether forest zone image has and trees fell characteristic assorted characteristic to this can confirm whether the forest zone that forest zone image corresponds has the action of felling. In the embodiment of the application, because outdoor tower body generally sets up in the higher forestry district of relief, consequently, install in the detection equipment of outdoor tower body can survey the region in place from top to bottom, can cover great detection area to can realize that forest zone on a large scale surveys, it is lower to survey the cost. And, through carrying out characteristic detection to the forest zone image, can detect the emergence of cutting down the action in relatively in time, improve the real-time of cutting down the detection.
Drawings
FIG. 1 is a flow chart of a forest region felling detection method provided by an embodiment of the application;
FIG. 2 is a flowchart of forest region felling detection based on a deep learning algorithm according to an embodiment of the present application;
FIG. 3 is a block diagram of a forest region felling detection device provided by an embodiment of the present application;
fig. 4 is a block diagram of an electronic device provided in an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, of the embodiments of the present application. 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 application.
Referring to fig. 1, fig. 1 is a flowchart of a forest region felling detection method provided in an embodiment of the present application. As shown in fig. 1, the present embodiment provides a forest region felling detection method, which includes the following steps:
step 101: under the condition that a first characteristic of a first forest region image is detected, detecting whether a second characteristic of a second forest region image exists or not, wherein the first forest region image is acquired through detection equipment arranged on an outdoor tower body, the second forest region image comprises all characteristics or partial characteristics of the first forest region image, the second forest region image comprises the first characteristic, the first characteristic is a characteristic matched with the characteristic of cutting equipment, and the second characteristic is a characteristic matched with the characteristic of cutting trees;
step 102: and under the condition that the second characteristic exists in the second forest region image, determining that the forest region corresponding to the second forest region image has a cutting behavior.
For convenience of understanding and explanation, the forest region felling detection method according to the embodiment of the present application will be described below with the forest region felling detection apparatus as an execution subject.
Before step 101, the forest region felling detection apparatus may acquire a first forest region image acquired by the detection device, and detect whether the first forest region image has a first characteristic. The detection equipment can be a high power camera and can be arranged on outdoor tower bodies such as a signal tower and wind power generation equipment. The first feature is the felling device feature, which is understood to be the device that is required for felling trees, such as a feller, truck, electric feller saw, etc. Accordingly, the felling device features may be feller car features, truck features, felling saw features, and the like.
If the first characteristic of the first forest region image is detected, the fact that the felling equipment possibly enters a forest region corresponding to the first forest region image is indicated, and felling behaviors possibly exist in the forest region. At this time, the forest region felling detection apparatus cannot determine whether the forest region felling behavior occurred. For ease of understanding, detecting the first characteristic in the first forest region image may be interpreted as a suspicious object entering the forest region, and at this time, may be interpreted as a suspected felling behavior in the forest region.
If a forest area is felled, objects such as toppled trunks, sawn tree cuts, scattered branches and the like are usually present on the ground. Based on this, in step 101, in the case that the first characteristic is detected in the first forest region image, the forest region felling detection apparatus may further detect whether a second characteristic is present in the second forest region image, so as to determine whether a forest region corresponding to the second forest region image has a felling behavior. The second feature, a tree felling feature, may be, for example, a trunk dump feature, a tree cut feature, a branch spill feature, or the like.
And if the second characteristic of the second forest region image is detected, the forest region is subjected to the cutting behavior. Based on this, in step 102, in the case that it is detected that the second characteristic exists in the second forest region image, the forest region felling detection apparatus may determine that the forest region corresponding to the second forest region image has a felling behavior.
It should be noted that the first forest zone image and the second forest zone image may be images acquired by the detection device at the same time, or images acquired at different times. If the second forest zone image is an image acquired by the detection device at the same moment, the second forest zone image can be an image which is completely the same as the first forest zone image, and can also be an image obtained by amplifying the first forest zone image.
In the embodiment of the application, forest zone images are collected by utilizing detection equipment arranged on an outdoor tower body, and under the condition that the forest zone images have characteristics matched with characteristics of cutting equipment, whether the forest zone images have characteristics matched with the characteristics of cutting the trees is further detected, so that whether the cutting behaviors exist in the forest zones corresponding to the forest zone images can be determined. In the embodiment of the application, because outdoor tower body generally sets up in the higher forestry district of relief, consequently, install in the detection equipment of outdoor tower body can survey the region in top-down ground, can cover great detection area territory to can realize forest district on a large scale and survey, survey the cost lower. Moreover, by carrying out feature detection on the forest region image, the occurrence of the felling behavior can be detected in time, and the real-time property of felling detection is improved.
In some alternative embodiments, the first forest zone image is acquired by a detection device mounted on a signal tower.
At present, the signal tower spreads more and more extensively, and generally arranges high altitude area such as forest zone, and the height of signal tower is higher usually, through installing in the detection equipment of signal tower, can survey the forest zone in place region from top to bottom, has better detection field of vision, can cut down for forest zone and detect and provide better basic condition.
In the embodiment of the application, the forest region felling detection process can be realized based on a deep learning algorithm.
In some optional embodiments, before the step of detecting whether the second characteristic exists in the second forest zone image, the method further comprises:
and detecting whether the first characteristic exists in the first forest zone image or not based on an SSD algorithm.
The SSD (Single Shot multi box Detector) algorithm is a target detection algorithm. Each unit of the SSD algorithm is provided with prior boxes with different scales or aspect ratios, and predicted bounding boxes (bounding boxes) are based on the prior boxes, so that the training difficulty can be reduced to a certain extent. For example, each cell of the SSD algorithm may be provided with 4 a priori boxes, whose dimensions and aspect ratios differ, and the training may be performed using the a priori boxes that best fit their shapes.
In this embodiment, the detection of the suspicious target may be implemented by an SSD algorithm.
As an example, first, the forest region felling detection device may identify a forest region by using an SSD algorithm to obtain a specific forest region range (i.e., a forest region range corresponding to the first forest region image); secondly, the forest region felling detection device can perform target detection and semantic segmentation on the first forest region image through an SSD algorithm to detect whether suspicious target characteristics (namely first characteristics) exist in the first forest region image, and the process can be understood as performing suspicious target detection or suspected felling behavior detection on the forest region range.
In the above process, the SSD algorithm outputs a set of detection results (including a bounding box and a confidence) for each detection box of each cell. Further, the SSD algorithm may use the background as a special object class, and assuming that there are N suspicious object classes, the SSD algorithm may predict N +1 detection results, wherein one detection result (e.g., the first detection result) is used to indicate the background object. The embodiment can be applied to outdoor environment, and the target can occupy the whole detection image because the target size can not be estimated.
When the first forest region image has suspicious target characteristics, the forest region felling detection device can consider that the forest region may have suspected felling behaviors, and can further adopt a secondary detection algorithm to perform depth judgment. The depth judgment by adopting the secondary detection algorithm can be understood as depth detection of tree cuts, tree dumping, tree stacking and the like based on the deep learning algorithm.
In some optional embodiments, the detecting whether the second characteristic exists in the second forest zone image comprises:
detecting whether the second characteristic exists in the second forest region image based on a residual error neural network (ResNet) algorithm.
In the embodiment, the core idea based on the ResNet algorithm is to introduce an identical and fast connection structure model, the structure forms a residual error unit of ResNet, the network layer is mainly a convolutional layer, and for an input feature x, the output y of the residual error unit in ResNet is as follows:
y＝F(x)+x
taking the detection of the tree cut based on the ResNet algorithm as an example, when the target image is detected to be the tree cut, the tree is judged to be damaged. The ResNet algorithm has 5 convolution stages, in the first convolution stage, the convolution kernel size is 7 multiplied by 7, the number of channels of output features is 64, and the convolution kernel step size is 2. After the first stage of convolution, the size of the image features is reduced to 0.5 times the original size. Then in a second convolution stage, first through a maximization pooling layer with a pooling window size of 3 x 3 and a step size of 2. The pooling operation reduces the size of the image feature to 0.5 times the original size. In the following convolution operation, stacking of residual units will be performed, and the convolution kernel settings of the convolution layers in the residual units may be different for different numbers of layers of ResNet.
Further, the embodiment of the application can perform secondary detection based on the improved algorithm of the deep learning ResNet 101. For ResNet101 with 101 layers, a bottleneck (bottleeck) design is carried out on the convolution operation for reducing the parameter quantity and the calculation quantity, and a 1 x 1 convolution kernel is introduced for carrying out dimension reduction and dimension increase operation on the number of channels of the feature map. Thus, the network layer in each residual unit consists of three convolutional layers, with convolutional kernel sizes of 1 × 1, 3 × 3, and 1 × 1, respectively. Each of the above convolutional layers is connected by a ReLU active layer. The network performs downsampling operation on the features by setting the convolution kernel step size to be 2 at the conv3_1, conv4_1 and conv5_1 stages. The open-source ResNet101 algorithm model removes the average pooling and full connection layers for image classification in the ResNet network, and the detection speed can be effectively improved. In addition, for occlusion or blur in an image, feature extraction can be performed on input features using conv1, conv2_ x, conv3_ x, conv4_ x, and conv5_ x, so that the target detection rate can be increased, and false alarm due to occlusion or blur can be effectively avoided.
Referring to fig. 2, fig. 2 is a flowchart of forest region felling detection based on a deep learning algorithm according to an embodiment of the present application. As shown in fig. 2, the process of forest felling detection based on the deep learning algorithm may include the following steps:
step 201: inputting an image;
step 202: detecting a target; the target types can be predefined, the target types can comprise types such as trees, felling equipment and the like, the SSD algorithm can be used for carrying out initial detection on the image, and the information such as the number, the position, the pixel size and the like of various targets in the current image can be determined;
step 203: semantic segmentation; the SSD algorithm can be used for fitting the area and the range of the target, and semantic segmentation is carried out on the image;
step 204: judging suspected felling behaviors; judging whether the detected target is a suspicious target by using an SSD algorithm so as to judge whether the suspected felling behavior exists; if yes, go to step 205, otherwise go to step 206;
step 205: secondary detection; using a ResNet algorithm to carry out secondary detection on the image so as to determine whether the felling action exists;
step 206: and outputting a detection result.
The above provides a related implementation manner for realizing forest region felling detection based on a deep learning algorithm.
In the embodiment of the application, forest region cutting detection can be carried out in a self-adaptive mode, and particularly, forest region images can be subjected to cutting detection in a self-adaptive mode. A related embodiment of adaptively acquiring forest zone images is described below.
In some optional embodiments, before the step of detecting whether the second characteristic exists in the second forest zone image, the method further comprises:
acquiring an image in a detection range of the detection device through the detection device;
and detecting whether the first characteristic exists in the first forest zone image or not under the condition that the first forest zone image is identified to be acquired by the detection equipment.
In this embodiment, detecting equipment can be in its detection scope fixed point scanning regularly, and at the in-process of detecting equipment scanning, whether the image that forest zone fell detection device recognizable detection equipment gathered is forest zone image, and when the image of its collection was forest zone image discerned, forest zone fell detection device can carry out the detection of felling. And when the collected image is not identified to be a forest region image, the forest region felling detection device does not need to carry out felling detection. That is to say, but forest zone felling detection device self-adaptation ground is cut the detection to forest zone image, and need not to cut the detection to any image that detection equipment gathered, can improve detection efficiency like this, can save the resource that detects required consumption.
In addition, the detection device can also firstly acquire images in the detection range, then the forest region felling detection device performs image recognition on all the acquired images so as to determine forest region images, and then the felling detection process is performed. This is not explained in more detail since it is easier to understand.
In some optional embodiments, after the step of detecting whether the first characteristic exists in the first forest zone image and before the step of detecting whether the second characteristic exists in the second forest zone image, the method further comprises:
and acquiring a second forest zone image through zooming of the detection equipment under the condition that the first characteristic of the first forest zone image is detected, wherein the second forest zone image comprises a part of characteristics of the first forest zone image.
When the forest region felling detection device detects that the first forest region image has the first characteristic, whether a second characteristic exists in the forest region image needs to be further detected. In this embodiment, the detection accuracy of the second characteristic is higher than the detection accuracy of the first characteristic, and in order to improve the real-time performance of forest region cutting detection, the forest region cutting detection device is required to realize detection when the forest region cutting scale is small, so that the second forest region image can be acquired in a self-adaptive manner through zooming of the detection equipment on the basis of acquiring the first forest region image in a self-adaptive manner, and thus, the forest region image is amplified in a self-adaptive manner, so that the forest region cutting detection device can perform cutting detection more accurately.
In this embodiment, the detection device may be a high zoom camera.
In some optional embodiments, in a case that the second characteristic exists in the second forest region image, determining that a forest region corresponding to the second forest region image has a felling behavior includes:
under the condition that the second characteristic exists in the second forest region image, calculating the felling degree of the tree;
and determining that the forest region corresponding to the second forest region image has a cutting behavior under the condition that the tree cutting degree is greater than or equal to a preset threshold value.
In this embodiment, some factors are considered, the existence of toppling trees or tree cuts rarely does not indicate that the forest region has a cutting behavior, misdetection caused by accidental factors is avoided, the cutting detection accuracy is improved, the forest region cutting detection device can calculate the tree cutting degree under the condition that the second forest region image has the second characteristic, and the forest region corresponding to the second forest region image has the cutting behavior under the condition that the tree cutting degree is greater than or equal to the preset threshold value.
The tree felling degree can be calculated according to the number, coverage or accumulation degree and the like of the second features in the second forest zone image.
In summary, the beneficial effects of the present application at least include: forest zone images are collected through detection equipment installed on an outdoor tower body, characteristics of the forest zone images are detected, the occurrence of cutting behaviors can be detected timely, the instantaneity of cutting detection is improved, a large detection area can be covered, large-scale forest zone detection is achieved, and detection cost is low.
Referring to fig. 3, fig. 3 is a structural diagram of a forest region felling detection apparatus according to an embodiment of the present application, and as shown in fig. 3, a forest region felling detection apparatus 300 includes:
the first detection module 301 is configured to detect whether a second forest region image has a second feature or not under the condition that a first forest region image has the first feature, where the first forest region image is acquired by a detection device installed on an outdoor tower body, the second forest region image includes all or part of features of the first forest region image, the second forest region image includes the first feature, the first feature is a feature matched with a feature of a felling device, and the second feature is a feature matched with a feature of a tree felling;
a determining module 302, configured to determine that a forest region corresponding to the second forest region image has a felling behavior when the second characteristic exists in the second forest region image.
In some embodiments, the forest area felling detection apparatus 300 further comprises:
the first acquisition module is used for acquiring images in the detection range of the detection equipment through the detection equipment;
and the second detection module is used for detecting whether the first characteristic exists in the first forest zone image or not under the condition that the first forest zone image is identified to be acquired by the detection equipment.
In some embodiments, the forest area felling detection apparatus 300 further comprises:
and the second acquisition module is used for acquiring the second forest zone image through zooming of the detection equipment under the condition that the first forest zone image is detected to have the first characteristic, and the second forest zone image comprises a part of characteristic of the first forest zone image.
In some embodiments, the determining module 302 includes:
the calculating unit is used for calculating the tree felling degree under the condition that the second characteristic exists in the second forest region image;
and the determining unit is used for determining that the forest region corresponding to the second forest region image has the felling behavior under the condition that the tree felling degree is greater than or equal to a preset threshold value.
In some embodiments, the forest area felling detection apparatus 300 further comprises:
and the third detection module is used for detecting whether the first characteristic exists in the first forest zone image based on an SSD algorithm.
In some embodiments, the first detection module 301 is specifically configured to:
and detecting whether the second characteristic exists in the second forest region image or not based on a ResNet algorithm.
In some embodiments, the first forest zone image is acquired by a detection device mounted on a signal tower.
The forest region felling detection device 300 can implement the processes implemented by the method embodiments shown in fig. 1 to fig. 2 and achieve the same beneficial effects, and for avoiding repetition, the details are not described here again.
According to an embodiment of the present application, an electronic device and a readable storage medium are also provided.
As shown in fig. 4, is a block diagram of an electronic device according to an embodiment of the application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.
As shown in fig. 4, the electronic apparatus includes: one or more processors 401, memory 402, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input/output apparatus (such as a display device coupled to the interface). In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). One processor 401 is illustrated in fig. 4.
The memory 402 is a computer-readable storage medium provided herein. The storage stores instructions executable by at least one processor, so that the at least one processor executes the forest region felling detection method provided by the application. The computer-readable storage medium of the present application stores computer instructions for causing a computer to perform the forest area felling detection method provided by the present application.
The memory 402 may be used as a computer-readable storage medium for storing non-transitory software programs, non-transitory computer-executable programs, and modules, such as program instructions/modules (e.g., the first detection module 301 and the determination module 302 shown in fig. 3) corresponding to the forest area felling detection method in the embodiment of the present application. The processor 401 executes various functional applications of the server and data processing by running non-transitory software programs, instructions and modules stored in the memory 402, namely, implements the forest area felling detection method in the above method embodiment.
The memory 402 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created from use of an electronic device that implements the forest cutting detection method, and the like. Further, the memory 402 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, memory 402 optionally includes memory located remotely from processor 401, and such remote memory may be connected via a network to an electronic device implementing the forest cutting detection method. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic device for implementing the forest region felling detection method may further include: an input device 403 and an output device 404. The processor 401, the memory 402, the input device 403 and the output device 404 may be connected by a bus or other means, and fig. 4 illustrates an example of a connection by a bus.
The input device 403 may receive input numeric or character information and generate key signal inputs related to user settings and function controls of an electronic apparatus implementing the forest cutting detection method, such as a touch screen, keypad, mouse, track pad, touch pad, pointer stick, one or more mouse buttons, track ball, joystick, or other input device. The output devices 404 may include a display device, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibrating motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device can be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a component of' 8230; \8230;" does not exclude the presence of another like element in a process, method, article, or apparatus that comprises the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.
While the present embodiments have been described with reference to the accompanying drawings, it is to be understood that the invention is not limited to the precise embodiments described above, which are meant to be illustrative and not restrictive, and that various changes may be made therein by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A forest region felling detection method is characterized by comprising the following steps:
under the condition that a first characteristic of a first forest region image is detected, detecting whether a second characteristic of a second forest region image exists or not, wherein the first forest region image is acquired through detection equipment arranged on an outdoor tower body, the second forest region image comprises all characteristics or partial characteristics of the first forest region image, the second forest region image comprises the first characteristic, the first characteristic is a characteristic matched with the characteristic of cutting equipment, and the second characteristic is a characteristic matched with the characteristic of cutting trees;
and under the condition that the second characteristic exists in the second forest region image, determining that the forest region corresponding to the second forest region image has a cutting behavior.
2. The method of claim 1, wherein prior to the step of detecting whether the second forest zone image has the second feature, the method further comprises:
acquiring an image in a detection range of the detection device through the detection device;
and detecting whether the first characteristic exists in the first forest zone image or not under the condition that the first forest zone image is identified to be acquired by the detection equipment.
3. The method of claim 2, wherein after the step of detecting whether the first feature is present in the first forest area image and before the step of detecting whether the second feature is present in the second forest area image, the method further comprises:
and acquiring a second forest zone image through zooming of the detection equipment under the condition that the first characteristic exists in the first forest zone image, wherein the second forest zone image comprises a part of characteristic of the first forest zone image.
4. The method according to any one of claims 1 to 3, wherein determining that the forest region corresponding to the second forest region image has the felling behavior under the condition that the second feature exists in the second forest region image comprises:
under the condition that the second characteristic exists in the second forest region image, calculating the tree felling degree;
and determining that the forest region corresponding to the second forest region image has a cutting behavior under the condition that the tree cutting degree is greater than or equal to a preset threshold value.
5. The method according to any one of claims 1 to 3, wherein prior to the step of detecting whether a second feature is present in the second forest zone image, the method further comprises:
and detecting whether the first characteristic exists in the first forest zone image or not based on an SSD algorithm.
6. The method according to any one of claims 1 to 3, wherein the detecting whether the second forest area image has the second feature comprises:
and detecting whether the second characteristic exists in the second forest region image or not based on a ResNet algorithm.
7. The method according to any one of claims 1 to 3, wherein the first forest zone image is acquired by a detection device mounted to a signal tower.
8. A forest region felling detection device, comprising:
the detection device comprises a first detection module, a second detection module and a control module, wherein the first detection module is used for detecting whether a second forest region image has a second characteristic or not under the condition that a first forest region image has the first characteristic, the first forest region image is acquired through detection equipment arranged on an outdoor tower body, the second forest region image comprises all characteristics or partial characteristics of the first forest region image, the second forest region image comprises the first characteristic, the first characteristic is a characteristic matched with the characteristic of felling equipment, and the second characteristic is a characteristic matched with the characteristic of felling trees;
and the determining module is used for determining that the forest region corresponding to the second forest region image has the cutting behavior under the condition that the second characteristic exists in the second forest region image.
9. An electronic device, comprising a processor, a memory and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the forest area felling detection method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, carries out the steps of the forest area felling detection method according to any one of the claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210528348.2A CN115147716A (en) | 2022-05-16 | 2022-05-16 | Forest area felling detection method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210528348.2A CN115147716A (en) | 2022-05-16 | 2022-05-16 | Forest area felling detection method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115147716A true CN115147716A (en) | 2022-10-04 |
Family
ID=83407032
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210528348.2A Pending CN115147716A (en) | 2022-05-16 | 2022-05-16 | Forest area felling detection method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115147716A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117237824B (en) * | 2023-11-14 | 2024-02-02 | 吉林省林业科学研究院(吉林省林业生物防治中心站) | Forest region harvesting detection equipment based on remote sensing image technology |
-
2022
- 2022-05-16 CN CN202210528348.2A patent/CN115147716A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117237824B (en) * | 2023-11-14 | 2024-02-02 | 吉林省林业科学研究院(吉林省林业生物防治中心站) | Forest region harvesting detection equipment based on remote sensing image technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11423488B1 (en) | Systems and methods for hail damage verification on rooftops using computer vision and artificial intelligence | |
| CN107292886B (en) | Target object intrusion detection method and device based on grid division and neural network | |
| CN109241465B (en) | Interface display method, device, terminal and storage medium | |
| CN111289998A (en) | Obstacle detection method, obstacle detection device, storage medium, and vehicle | |
| CN111783878A (en) | Target detection method and device, electronic equipment and readable storage medium | |
| CN115147716A (en) | Forest area felling detection method and device, electronic equipment and storage medium | |
| CN110633594A (en) | Target detection method and device | |
| CN111539347B (en) | Method and device for detecting target | |
| CN110717496A (en) | Complex scene tree detection method based on neural network | |
| CN115018903B (en) | Method and system for calculating volume of stock pile in stock yard | |
| CN113569911A (en) | Vehicle identification method and device, electronic equipment and storage medium | |
| CN111337898B (en) | Laser point cloud processing method, device, equipment and storage medium | |
| CN112132015A (en) | Detection method, device, medium and electronic equipment for illegal driving posture | |
| CN114937027B (en) | Fan blade defect detection method and device, electronic equipment and storage medium | |
| CN114299475A (en) | Method for detecting corrosion of damper and related equipment | |
| CN115527187A (en) | Method and device for classifying obstacles | |
| CN111753960B (en) | Model training and image processing method and device, electronic equipment and storage medium | |
| CN116152702A (en) | Point cloud label acquisition method and device, electronic equipment and automatic driving vehicle | |
| CN115187831A (en) | Model training and smoke detection method and device, electronic equipment and storage medium | |
| CN115331048A (en) | Image classification method, device, equipment and storage medium | |
| CN113591567A (en) | Target detection method, training method of target detection model and device thereof | |
| CN113569912A (en) | Vehicle identification method and device, electronic equipment and storage medium | |
| CN114818777B (en) | Training method and device for active angle deception jamming recognition model | |
| CN115909020B (en) | Model robustness detection method, related device and storage medium | |
| JP7463463B2 (en) | Method and device for detecting work terrain, and construction equipment for detecting work terrain |
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 |