Methods, apparatuses, devices, and storage media for fire detection

Abstract

Embodiments of this disclosure provide methods, apparatus, devices, and storage media for fire detection. The method includes: determining a first identification result based on sensing data of at least one feature related to a fire event from at least one sensor, the first identification result indicating the probability of a fire event occurring in a space, wherein at least one sensor is deployed in the space; determining a second identification result based on at least one image related to the space, the second identification result indicating the presence of at least one object related to a fire event in the space; and determining a fire detection result for the space based on the first and second identification results, the fire detection result indicating whether a fire event has occurred in the space.

Description

Technical Field

[0001] The exemplary embodiments disclosed herein generally relate to the field of computers, and particularly to methods, apparatus, devices, computer-readable storage media, and computer program products for fire detection. Background Technology

[0002] Automated fire detection systems can detect fires early, enabling timely firefighting measures to prevent the fire from spreading and reduce losses. This is of great significance in various fields, including daily life, warehousing and logistics, and industrial production. However, traditional fire detection technologies still have shortcomings in terms of accuracy. Summary of the Invention

[0003] In a first aspect of this disclosure, a method for fire detection is provided. The method includes: determining a first identification result based on sensing data of at least one feature related to a fire event from at least one sensor, the first identification result indicating the probability of a fire event occurring in a space, wherein at least one sensor is deployed in the space; determining a second identification result based on at least one image related to the space, the second identification result indicating the presence of at least one object related to a fire event in the space; and determining a fire detection result for the space based on the first and second identification results, the fire detection result indicating whether a fire event has occurred in the space.

[0004] In a second aspect of this disclosure, an apparatus for fire detection is provided. The apparatus includes: a first identification module configured to determine a first identification result based on sensing data from at least one sensor of at least one feature related to a fire event, the first identification result indicating the likelihood of a fire event occurring in a space, the at least one sensor being deployed in the space; a second identification module configured to determine a second identification result based on at least one image related to the space, the second identification result indicating the presence of at least one object related to a fire event in the space; and a detection module configured to determine a fire detection result for the space based on the first and second identification results, the fire detection result indicating whether a fire event has occurred in the space.

[0005] In a third aspect of this disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the electronic device to perform the method of the first aspect.

[0006] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. A computer program is stored on the medium, which, when executed by a processor, implements the method of the first aspect.

[0007] In a fifth aspect of this disclosure, a computer program product is provided, comprising a computer program, wherein the computer program, when executed by a processor, implements the method of the first aspect.

[0008] It should be understood that the description in this section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0009] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0010] Figure 1 A schematic diagram of an example environment in which embodiments of the present disclosure can be implemented is shown;

[0011] Figure 2 A flowchart of a process for fire detection according to some embodiments of the present disclosure is shown;

[0012] Figure 3 A schematic diagram of an example architecture for fire detection according to some embodiments of the present disclosure is shown;

[0013] Figure 4 A schematic structural block diagram of an apparatus for fire detection according to some embodiments of the present disclosure is shown; and

[0014] Figure 5 A block diagram of an electronic device that can implement one or more embodiments of the present disclosure is shown. Detailed Implementation

[0015] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0016] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below.

[0017] In this document, unless explicitly stated otherwise, performing a step in response to A does not mean that the step is performed immediately after A, but may include one or more intermediate steps.

[0018] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition, use, storage or deletion of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0019] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, relevant users should be informed of the type, scope of use, and usage scenarios of the information involved in this disclosure through appropriate means in accordance with relevant laws and regulations, and authorization should be obtained from the relevant users. Among them, relevant users may include any type of rights holder, such as individuals, enterprises, and groups.

[0020] For example, in response to receiving an active request from a user, a prompt message is sent to the relevant user to clearly inform the user that the requested operation will require obtaining and using the user's information, thereby enabling the relevant user to choose whether to provide information to the software or hardware such as the electronic device, application, server, or storage medium that performs the operation of the technical solution disclosed herein based on the prompt message.

[0021] As an optional but non-restrictive implementation, in response to a user's active request, a prompt message can be sent to the user, such as a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide information to the electronic device.

[0022] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0023] As used in this paper, the term "model" refers to a model that learns the relationship between inputs and outputs from training data, enabling it to generate corresponding outputs for a given input after training. Model generation can be based on machine learning techniques. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs using multiple layers of processing units. A neural network model is an example of a deep learning-based model. In this paper, "model" may also be referred to as a "machine learning model," "learning model," "machine learning network," or "learning network," and these terms are used interchangeably.

[0024] A neural network is a machine learning network based on deep learning. A neural network processes input and provides a corresponding output, typically consisting of an input layer, an output layer, and one or more hidden layers between the input and output layers. Neural networks used in deep learning applications often include many hidden layers, thus increasing the network's depth. The layers of a neural network are connected sequentially, so that the output of the previous layer is provided as the input to the next layer. The input layer receives the input to the neural network, while the output layer's output serves as the final output. Each layer of a neural network includes one or more nodes (also called processing nodes or neurons), each node processing the input from the layer above.

[0025] Machine learning typically comprises three phases: training, testing, and application (also known as inference). In the training phase, a given model is trained using a large amount of training data, iteratively updating its parameter values ​​until the model can consistently generate inferences that meet the expected goals from the training data. Through training, the model can be considered to have learned the relationship between inputs and outputs (also known as the input-output mapping) from the training data. The parameter values ​​of the trained model are determined. In the testing phase, test inputs are applied to the trained model to test whether it can provide the correct output, thus determining the model's performance. In the application phase, the model can be used to process actual inputs based on the trained parameter values ​​to determine the corresponding output.

[0026] As mentioned earlier, fire detection enables timely firefighting measures by detecting fires early, preventing their spread and minimizing losses. It is of great significance in various fields, including daily life, warehousing and logistics, and industrial production. In particular, the rapidly developing electric vehicle sector has placed higher demands on fire detection in the production, warehousing, and logistics of electric vehicles. Traditional fire detection technologies primarily rely on sensors such as smoke and temperature sensors to detect fires in the environment. However, these sensors are susceptible to environmental factors, leading to limitations in the accuracy of traditional fire detection techniques.

[0027] In view of this, embodiments of the present disclosure provide an improved scheme for fire detection. In this scheme, at least one sensor is deployed in a space. The at least one sensor is used to sense at least one feature in the space related to a fire event, acquiring sensing data. Based on the sensing data, a first identification result indicating the probability of a fire event occurring in the space is determined. Based on at least one image related to the space, a second identification result is determined, indicating whether at least one object related to a fire event exists in the space. Subsequently, based on the first and second identification results, a fire detection result for the space is determined, indicating whether a fire event has occurred in the space.

[0028] According to embodiments of this disclosure, whether a fire event has occurred in a space is identified based on sensor data and image-based object detection, respectively. The fire detection result is then determined by combining the results of these two identifications. This allows for accurate detection of a fire event in a space by combining multiple pieces of information, thus improving the accuracy of fire detection.

[0029] Example Environment

[0030] Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. For example... Figure 1 As shown, environment 100 relates to space 120, which can be any environment space that needs to be subjected to fire detection, such as warehouses, parking lots, factories, offices, etc.

[0031] In some embodiments of this disclosure, one or more sensors 130 are deployed in space 120, such as sensor 130-1, sensor 130-2, ..., sensor 130-N, etc., where N is a positive integer. For ease of description, one or more sensors may be collectively referred to as sensor 130 herein. Sensor 130 can be used to sense at least one feature in space 120 that is related to a fire event. The at least one feature considered herein is correlated with a fire event. By sensing these features, the probability of a fire event occurring in space 120 can be determined.

[0032] In some embodiments, sensor 130 may include, but is not limited to, smoke sensors, temperature sensors, infrared flame detectors, ultraviolet flame detectors, gas detectors, etc. Of course, the sensor 130 described above is merely exemplary, and any other suitable sensor capable of sensing fire-related characteristics may also be used; the embodiments of this disclosure do not limit this.

[0033] In some embodiments of this disclosure, an image acquisition device 140 is also deployed in the space 120, through which images of the space 120 can be acquired. It should be noted that, although... Figure 1 Only one image acquisition device 140 is shown in the illustration, but in practical applications, one or more image acquisition devices 140 can be deployed in space 120 to enable the acquisition range of the image acquisition device 140 to cover different locations in space 120. In some examples, the image acquisition device 140 may include, but is not limited to, a camera or a webcam.

[0034] In some embodiments of this disclosure, environment 100 also relates to a fire detection platform 110. The fire detection platform 110 can be communicatively connected to a sensor 130 and an image acquisition device 120, respectively. The fire detection platform 110 can acquire sensing data from the sensor 130 and images acquired by the image acquisition device 120 based on the communication connection. Furthermore, the fire detection platform 110 can also detect whether a fire event has occurred in space 120 based on the sensing data and images.

[0035] In some embodiments, the fire detection platform 110 may utilize one or more machine learning models 150 to detect whether a fire event has occurred in the space 120. The machine learning model 150 may be of different types. In some examples, the machine learning model 150 may be built based on object detection and image segmentation models. Of course, the machine learning model 150 may also be built based on any other suitable model architecture, and the embodiments of this disclosure are not limited thereto.

[0036] In some embodiments, the fire detection platform 110 can be implemented on any computing system with computing capabilities, such as various computing devices / systems, terminal devices, servers, etc. The terminal device can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof.

[0037] Servers include, but are not limited to, mainframes, edge computing nodes, and computing devices in cloud environments. They can be standalone physical servers, server clusters or distributed systems composed of multiple physical servers, or cloud servers providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms. Servers may include, for example, computing systems / servers such as mainframes, edge computing nodes, and computing devices in cloud environments, etc.

[0038] It should be understood that the structure and function of the various elements in environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure.

[0039] Example process

[0040] Some exemplary embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0041] Figure 2 A flowchart of a process 200 for fire detection according to some embodiments of the present disclosure is shown. Process 200 can be implemented on a fire detection platform 110 or other remote device. For ease of discussion, the following will be combined with… Figure 1 Some embodiments of this disclosure are described in the context of environment 100 and from the perspective of fire detection platform 110, but these are merely exemplary.

[0042] In box 210, the fire detection platform 110 determines a first identification result based on sensing data from at least one sensor 130 regarding at least one feature related to a fire event. The first identification result indicates the likelihood of a fire event occurring in the space.

[0043] The at least one sensor is deployed in space 120 to sense the at least one feature in space 120 to obtain sensing data. The at least one feature may be a feature correlated with a fire event, and may indicate whether a fire event has occurred in space 120. In some embodiments, the at least one feature includes, but is not limited to, smoke concentration, temperature, light radiation intensity in a predetermined light region, or the concentration of a predetermined gas, etc. The light radiation intensity in the predetermined light region may include, but is not limited to, infrared (IR) radiation intensity, ultraviolet (UV) radiation intensity. The concentration of the predetermined gas may include, but is not limited to, the concentration of carbon monoxide, the concentration of carbon dioxide, etc.

[0044] In some embodiments, the fire detection platform 110 acquires at least one set of sensing data from the at least one sensor. A first identification result is then determined based on a comparison of the at least one set of sensing data with a corresponding threshold. In some examples, the at least one sensor 130 may include a smoke sensor to sense the smoke concentration in space 120. The fire detection platform 110 may compare the smoke concentration sensed by the smoke sensor with a preset smoke concentration threshold. If it is determined that the smoke concentration exceeds the smoke concentration threshold, the fire detection platform 110 generates a first identification result indicating that a fire event has occurred in space 120. If it is determined that the smoke concentration does not exceed the smoke concentration threshold, the fire detection platform 110 generates a first identification result indicating that no fire event has occurred in space 120.

[0045] Alternatively or additionally, the at least one sensor 130 may also include an infrared flame sensor, which can sense the intensity of infrared radiation in space 120. The fire detection platform 110 compares the sensed infrared radiation intensity with a pre-set infrared radiation intensity threshold. If the infrared radiation intensity exceeds the threshold, the fire detection platform 110 generates a first identification result indicating that a fire event has occurred in space 120. If the infrared radiation intensity does not exceed the threshold, the fire detection platform generates a first identification result indicating that no fire event has occurred in space 120.

[0046] Alternatively or additionally, the at least one sensor may also include a temperature sensor, an ultraviolet flame sensor, a carbon monoxide detector, a carbon dioxide detector, etc. Accordingly, the fire detection platform 110 can compare the temperature, ultraviolet radiation intensity, carbon monoxide concentration, and carbon dioxide concentration with corresponding thresholds to determine the probability of a fire event occurring in space 120 and generate a first identification result. It should be understood that the above features and sensors are merely exemplary, and other suitable types of sensors can also be used to sense other features in space 120 that are relevant to fire events; the embodiments of this disclosure are not limited in this regard.

[0047] In some embodiments, the fire detection platform 110 can communicate with the at least one sensor 130. For example, the at least one sensor 130 may be equipped with a communication module, such as a Wi-Fi communication module, a Bluetooth communication module, or a cellular communication module. The fire detection platform 110 can acquire sensing data from the at least one sensor 130 based on this communication connection.

[0048] Figure 3A schematic diagram of an example architecture 300 for fire detection according to some embodiments of the present disclosure is shown. In the example architecture 300, a fire detection platform 110 includes an object detection platform 310, a decision platform 320, and an alarm platform 330. The fire detection platform 110 can acquire sensing data from sensors using the decision platform 320. The decision platform 320 can then compare the acquired sensing data with corresponding thresholds to obtain a first identification result.

[0049] In some examples, the object detection platform 310 can be deployed near the edge of space 120, while the decision platform 320 and alarm platform 330 can be deployed on the server side away from space 120. In other examples, the object detection platform 310, decision platform 320, and alarm platform 330 can all be deployed on the server side away from space 120. Of course, the above deployment methods are merely exemplary, and in practical applications, any appropriate deployment method can be selected to deploy the object detection platform 310 according to actual needs. The embodiments of this disclosure do not limit this.

[0050] In the return process 200, at box 220, the fire detection platform 110 determines a second identification result based on at least one image associated with space 120. In some embodiments, one or more image acquisition devices 140 may be deployed in space 120, such as cameras or video cameras. These one or more image acquisition devices 140 are used to acquire still images, moving images, or video of space 120. The fire detection platform 110 can acquire images of space 120 from the image acquisition devices 140 and then determine the second identification result based on the acquired images.

[0051] The second identification result indicates whether at least one object related to a fire event exists in space 120. Identification of these objects can indicate whether a fire has occurred in space 120. In some embodiments, the at least one object related to a fire event is image-capable, and examples may include, but are not limited to, smoke or flames. After acquiring the at least one image, the fire detection platform 110 can perform object detection based on the at least one image to determine whether the at least one image contains objects related to a fire event, such as smoke or flames, and generate a corresponding second identification result.

[0052] In some embodiments, the fire detection platform 110 can acquire at least one image of the space 120. Then, object detection is performed on the at least one image using a trained machine learning model 150 to determine a second recognition result. As an example, combined with... Figure 3As shown, the object detection platform 310 can communicate with the image acquisition device 140 in the space 120, and receive images from the image acquisition device 140 based on this communication connection. The object detection platform 310 performs object detection on the received images, such as detecting whether the images contain smoke or flames, and generates a second recognition result. This second recognition result can indicate whether there is a flame or smoke in the space 120.

[0053] See back Figure 2 In frame 230, the fire detection platform 110 determines the fire detection result of the space based on the first identification result and the second identification result. The fire detection result indicates whether a fire event has occurred in the space.

[0054] In some embodiments, the fire detection platform 110 can determine whether a first identification result indicates a fire event has occurred in space 120, and the fire detection platform 110 can also determine whether a second identification result indicates the presence of at least one object, such as flame or smoke, in space 120. If the first identification result indicates a fire event has occurred in space 120, and the second identification result indicates the presence of at least one object in space 120, the fire detection platform 110 determines that a fire event has occurred in space 120 and generates a fire detection result indicating that a fire event has occurred in space 120. If the first identification result indicates a fire event has occurred in space 120, but the second identification result indicates that no object, such as flame or smoke, exists in space 120, the fire detection platform 110 can generate a fire detection result indicating that no fire event has occurred in space 120. If the second identification result indicates the presence of an object, such as flame or smoke, in space 120, but the first identification result does not indicate a fire event has occurred in space 120, the fire detection platform 110 can generate a fire detection result indicating that no fire event has occurred in space 120. In this way, the identification results of the sensors and the image can be combined to determine whether a fire has occurred in space 120, avoiding false detections due to a single detection method and improving the accuracy of fire detection results.

[0055] In some embodiments, if a first identification result indicates that a fire event has occurred in a space, the fire detection platform 110 may acquire one or more second identification results within a first time range. The fire detection platform 110 may determine whether the one or more second identification results indicate that the at least one object exists in the space 120. If it is determined that at least one of the one or more second identification results indicates that at least one object exists in the space 120, a fire detection result indicating that a fire event has occurred in the space 120 is generated. If it is determined that all of the one or more second identification results indicate that the at least one object does not exist in the space 120, the fire detection platform 110 may generate a fire detection result indicating that no fire event has occurred in the space 120. In some examples, the first time range may include a predetermined time range after the generation time of the first identification result. Of course, the first time range may also be other ranges, and the examples disclosed herein are not limited thereto.

[0056] As an example, a smoke sensor and an image acquisition device 140 can be deployed in space 120. The fire detection platform 110 can acquire sensing data from the smoke sensor in a first cycle to determine a first identification result. The fire detection platform 110 can also acquire images from the image acquisition device 140 in a second cycle to determine a second identification result. If the fire detection platform 110 determines that the first identification result generated in the first time indicates that the smoke concentration exceeds a predetermined smoke concentration threshold, it indicates that a fire event has occurred in space 120. However, due to viewing angle or the visibility of smoke or flames, the second identification result may indicate that no smoke or flames are detected in space 120. The fire detection platform 110 can acquire second identification results for one or more cycles within a first time range after the first time. If any of the second identification results in these one or more cycles indicates the presence of flames or smoke in space 120, the fire detection platform 110 determines that a fire has occurred in space 120 and generates a fire detection result indicating that a fire event has occurred in space 120. This avoids the detection error caused by the asynchronous nature of sensor-based and image-based identification results, and further improves the accuracy of fire detection results.

[0057] In some embodiments, if it is determined that a second identification result indicates the presence of at least one object (e.g., smoke or flame) in space 120, the fire detection platform 110 may acquire one or more first identification results within a second time range. The fire detection platform 110 may determine whether the one or more first identification results indicate a fire event in space 120. If it is determined that at least one of the one or more first identification results indicates a fire event in space 120, the fire detection platform 110 generates a fire detection result indicating that a fire event has occurred in space 120. If it is determined that all one or more first identification results indicate that no fire event has occurred in space 120, the fire detection platform 110 may generate a fire detection result indicating that no fire event has occurred in space 120. In some examples, the second time range may include a predetermined time range after the generation time of the second identification result. Of course, the second time range may also be other time ranges, and the embodiments of this disclosure are not limited thereto.

[0058] As an example, suppose the fire detection platform 110 determines that a second identification result generated at a second time indicates the presence of flame or smoke in space 120. The fire detection platform 110 can acquire one or more first identification results within a second time range after the second time. If the smoke concentration in space 120 indicated by the first identification results of these one or more periods exceeds a predetermined smoke concentration threshold, the fire detection platform 110 generates a fire detection result indicating that a fire event has occurred in space 120. In this way, the time difference in fire event detection caused by different fire detection methods can be eliminated to a certain extent, ensuring effective detection of fire events.

[0059] In some embodiments, if a first predetermined number of consecutive first identification results indicate that a fire has occurred in space 120, the fire detection platform 110 can generate a fire detection result indicating that a fire has occurred in space 120. Specifically, in practical applications, it is possible that consecutive first identification results indicate a fire has occurred in space 120. However, objects such as flames or smoke are not identified from the image. This situation may be due to the viewing angle, detection principle, or other reasons of the image acquisition device 140, resulting in the failure to detect objects such as flames or smoke in a timely manner. In this case, the probability of a fire in space 120 is high, and if a timely response to the fire is not taken, the optimal rescue time may be missed. Therefore, the fire detection platform 110 can determine that a fire has occurred in space 120 and generate a fire detection result indicating that a fire has occurred in space 120, so that rescue personnel can verify and carry out rescue operations in a timely manner.

[0060] In some embodiments, if a second predetermined number of consecutive second identification results indicate the presence of at least one object in space 120, the fire detection platform 110 can generate a fire detection result indicating a fire event has occurred in space 120. Specifically, in practical applications, it is possible that objects such as smoke or flames may be identified from an image, but due to limitations in the sensor's detection principle or other reasons, the sensor-based sensing data may not be able to detect the fire in a timely manner. To respond to a fire promptly, the fire detection platform 110 can generate a fire detection result indicating a fire event has occurred in space 120, thereby triggering a fire alarm or rescue response in a timely manner.

[0061] In some embodiments, the second identification result may also indicate whether a predetermined behavior exists in the space, whereby the predetermined behavior is defined as affecting the sensing of at least one sensor. That is, the predetermined behavior may interfere with the sensor's sensing results, causing the sensor to falsely detect. If the first identification result indicates that a fire event has occurred in space 120, and the second identification result indicates that a predetermined behavior exists in space 120, it is likely that the sensor is falsely detected due to interference from the predetermined behavior. The fire detection platform 110 generates a fire detection result indicating that no fire event has occurred in space 120, thereby improving the accuracy of the fire detection results.

[0062] In some examples, the predetermined behavior may include actions that generate dust or water mist. Actions that generate dust may include, but are not limited to, ground sweeping, earthwork operations, industrial processing activities, etc. Actions that generate water mist may include, but are not limited to, water spraying for dust suppression or cooling, actions that generate water vapor, etc. It is understood that the above predetermined behaviors are merely exemplary, and the behaviors that can interfere with the sensor's sensing results may differ depending on the type of sensor used. The embodiments of this disclosure do not limit the type of predetermined behavior.

[0063] In some embodiments, if the fire detection platform 110 determines that a fire event has occurred in space 120 based on fire detection results, it may trigger a fire alarm. For example, such as... Figure 3 As shown, the determination platform 320 can obtain a second identification result from the object detection platform 310. Based on its own generated first identification result and the obtained second identification result, the determination platform 320 can determine whether a fire has occurred in space 120. If a fire is determined to have occurred in space 120, the determination platform 320 can generate a fire detection result indicating a fire event in space 120. The alarm platform 330 can respond to the fire detection result indicating a fire event in space 120, triggering a fire alarm, such as sending alarm information to rescue personnel, triggering an emergency rescue system, etc.

[0064] It should be noted that the above method for determining fire detection results is merely exemplary. In practical applications, any other appropriate method can be selected to determine fire detection results according to actual needs. For example, feature extraction can be performed based on the first and second recognition results to obtain first and second features aligned in the feature space of the trained machine learning model 150. For instance, feature extraction can be performed on the comparison results of sensed data with corresponding thresholds and the segmentation results of images. The fire detection platform 110 can generate model input based on the first and second features. The machine learning model 150 generates fire detection results based on the first and second features. By aligning multimodal features in the feature space to achieve fire detection, the accuracy of fire detection results can be improved.

[0065] In summary, according to the embodiments of this disclosure, whether a fire event has occurred in a space is detected based on sensor data and images, respectively. Then, the fire detection result for the space is determined by combining the identification results of these two parts. This allows for accurate detection of whether a fire event has occurred in a space, which helps improve the accuracy of fire detection.

[0066] Example devices and equipment

[0067] Embodiments of this disclosure also provide corresponding apparatus for implementing the above methods or processes. Figure 4 A schematic structural block diagram of a fire detection apparatus 400 according to some embodiments of the present disclosure is shown. The apparatus 400 may be implemented in or included in a fire detection platform 110. Various modules / components in the apparatus 400 may be implemented by hardware, software, firmware, or any combination thereof.

[0068] like Figure 4 As shown, the device 400 includes: a first identification module 410 configured to determine a first identification result based on sensing data of at least one feature related to a fire event from at least one sensor, the first identification result indicating the likelihood of a fire event occurring in the space, the at least one sensor being deployed in the space; a second identification module 420 configured to determine a second identification result based on at least one image related to the space, the second identification result indicating whether at least one object related to a fire event exists in the space; and a detection module 430 configured to determine a fire detection result for the space based on the first and second identification results, the fire detection result indicating whether a fire event has occurred in the space.

[0069] In some embodiments, the detection module 430 is further configured to: generate a fire detection result indicating that a fire event has occurred in the space based on determining that a first identification result indicates that a fire event has occurred in the space and determining that a second identification result indicates that at least one object exists in the space.

[0070] In some embodiments, the detection module 430 is further configured to: in response to a first identification result indicating a fire event in the space, acquire a plurality of second identification results within a first time range; and generate a fire detection result indicating a fire event in the space based on determining that at least one of the plurality of second identification results indicates the presence of at least one object in the space.

[0071] In some embodiments, the detection module 430 is further configured to: in response to a second identification result indicating the presence of at least one object in the space, acquire a plurality of first identification results within a second time range; and generate a fire detection result indicating that a fire event has occurred in the space based on determining that at least one of the plurality of first identification results indicates that a fire event has occurred in the space.

[0072] In some embodiments, the detection module 430 is further configured to: generate a fire detection result indicating that a fire event has occurred in the space in response to a first predetermined number of consecutive first identification results indicating that a fire event has occurred in the space, or generate a fire detection result indicating that a fire event has occurred in the space in response to a second predetermined number of consecutive second identification results indicating that at least one object exists in the space.

[0073] In some embodiments, the second identification result also indicates whether a predetermined behavior exists in the space, the predetermined behavior being defined as affecting the sensing of at least one sensor, and the detection module 430 is further configured to: generate a fire detection result indicating that no fire event has occurred in the space based on determining that the first identification result indicates that a fire event has occurred in the space and determining that the second identification result indicates that a predetermined behavior exists in the space.

[0074] In some embodiments, the predetermined behavior includes at least one of the following: generating dust, or generating water mist.

[0075] In some embodiments, the first identification module 410 is further configured to: acquire at least one set of sensing data from at least one sensor; and determine a first identification result based on a comparison of the at least one set of sensing data with a corresponding threshold.

[0076] In some embodiments, the second recognition module 420 is further configured to: acquire at least one image of the space; and perform object detection on the at least one image using a trained machine learning model to determine a second recognition result.

[0077] In some embodiments, at least one feature includes at least one of the following: smoke concentration, temperature, light radiation intensity of a predetermined light field, or concentration of a predetermined gas, and / or at least one of the objects includes at least one of the following: smoke, or flame.

[0078] The units and / or modules included in device 400 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units and / or modules can be implemented using software and / or firmware, such as machine-executable instructions stored on a storage medium. In addition to or as an alternative to machine-executable instructions, some or all of the units and / or modules in device 400 can be implemented at least partially by one or more hardware logic components. By way of example and not limitation, exemplary types of hardware logic components that can be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chips (SoCs), complex programmable logic devices (CPLDs), and so on.

[0079] Figure 5 A block diagram of an electronic device 500 in which one or more embodiments of the present disclosure may be implemented is shown. It should be understood that... Figure 5 The electronic device 500 shown is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. Figure 5 The illustrated electronic device 500 may include or be implemented as Figure 1 Fire detection platform 110 or Figure 4 Device 400.

[0080] like Figure 5 As shown, electronic device 500 is in the form of a general-purpose electronic device. Components of electronic device 500 may include, but are not limited to, one or more processors or processing units 510, memory 520, storage device 530, one or more communication units 540, one or more input devices 550, and one or more output devices 560. Processing unit 510 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 520. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 500.

[0081] Electronic device 500 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 500, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 520 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 530 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data and can be accessed within electronic device 500.

[0082] Electronic device 500 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 5 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 520 may include computer program product 525 having one or more program modules configured to perform various methods or actions of various embodiments of this disclosure.

[0083] Communication unit 540 enables communication with other electronic devices via a communication medium. Additionally, the functionality of components of electronic device 500 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, electronic device 500 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0084] Input device 550 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 560 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 500 can also communicate with one or more external devices (not shown) via communication unit 540 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 500, or with any device that enables electronic device 500 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0085] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0086] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0087] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0088] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0089] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0090] Various implementations of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for fire detection, comprising: A first identification result is determined based on sensing data of at least one feature related to a fire event from at least one sensor, the first identification result indicating the likelihood of a fire event occurring in the space, wherein the at least one sensor is deployed in the space; A second identification result is determined based on at least one image associated with the space, the second identification result indicating whether there is at least one object in the space related to a fire event; as well as Based on the first identification result and the second identification result, a fire detection result for the space is determined, and the fire detection result indicates whether a fire event has occurred in the space.

2. The method according to claim 1, wherein determining the fire detection result includes: Based on determining that the first identification result indicates a fire event has occurred in the space, and determining that the second identification result indicates the presence of at least one object in the space, a fire detection result indicating that a fire event has occurred in the space is generated.

3. The method according to claim 1, wherein determining the fire detection result includes: In response to the first identification result indicating that a fire event has occurred in the space, multiple second identification results are acquired within a first time range; as well as Based on determining that at least one of the plurality of second identification results indicates the presence of at least one object in the space, a fire detection result indicating that a fire event has occurred in the space is generated.

4. The method according to claim 1, wherein determining the fire detection result includes: In response to the second identification result indicating the presence of at least one object in the space, a plurality of first identification results are acquired within a second time range; as well as Based on determining that at least one of the plurality of first identification results indicates that a fire event has occurred in the space, a fire detection result indicating that a fire event has occurred in the space is generated.

5. The method according to claim 1, wherein determining the fire detection result includes: In response to a first predetermined number of consecutive first identification results indicating a fire event in the space, a fire detection result indicating a fire event in the space is generated, or In response to a second predetermined number of consecutive second identification results indicating the presence of at least one object in the space, a fire detection result indicating a fire event has occurred in the space is generated.

6. The method of claim 1, wherein the second identification result further indicates whether a predetermined behavior exists in the space, the predetermined behavior being defined as affecting the sensing of the at least one sensor, and The determination of the fire detection results includes: Based on determining that the first identification result indicates that a fire event has occurred in the space, and determining that the second identification result indicates that the predetermined behavior exists in the space, a fire detection result indicating that no fire event has occurred in the space is generated.

7. The method of claim 6, wherein the predetermined action comprises at least one of the following: Actions that generate dust or water mist.

8. The method according to claim 1, wherein determining the first identification result includes: Acquire at least one set of sensing data from the at least one sensor; as well as The first identification result is determined by comparing the at least one set of sensing data with the corresponding threshold.

9. The method according to claim 1, wherein determining the second identification result includes: Acquire at least one image of the space; as well as The second recognition result is determined by performing object detection on the at least one image using a trained machine learning model.

10. The method of claim 1, wherein the at least one feature comprises at least one of the following: smoke concentration, temperature, light radiation intensity of a predetermined light field, or concentration of a predetermined gas, and / or The at least one of the objects mentioned includes at least one of the following: smoke or flame.

11. A device for fire detection, comprising: A first identification module is configured to determine a first identification result based on sensing data of at least one feature related to a fire event from at least one sensor, the first identification result indicating the likelihood of a fire event occurring in the space, wherein the at least one sensor is deployed in the space; The second identification module is configured to determine a second identification result based on at least one image associated with the space, the second identification result indicating whether at least one object associated with a fire event exists in the space; as well as The detection module is configured to determine a fire detection result for the space based on the first identification result and the second identification result, wherein the fire detection result indicates whether a fire event has occurred in the space.

12. An electronic device, comprising: At least one processing unit; as well as At least one memory, coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 10 when executed by the at least one processing unit.

13. A computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the method according to any one of claims 1 to 10.

14. A computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the method according to any one of claims 1 to 10.

Images