78 results about "Smoking behavior" patented technology

The application discloses a smoking behavior detection model construction method based on a double-main network. The model is composed of five parts: a ROI main network, a space constraint network, a cigarette main network, a cigarette neck network and a cigarette detection head. Through migration learning, the ROI main network is used to obtain smoking posture features of various scales; the space constraint network is used to face the smoking posture feature maps of various scales and extract smoking posture masks; the smoking posture masks of different scales are used to perform spatial filtering on the cigarette features of various scales obtained by the cigarette main network; and the filtered cigarette features are output to the neck network and the detection head to output the coordinates and confidence of the cigarette target. By adopting the method, posture detection, image segmentation and target detection are fused; through the spatial semantic constraint of the context, the false detection rate of similar cigarette objects in the image is effectively reduced, and the detection accuracy is improved.

The invention relates to the field of forensic medicine, and discloses a method and system for identifying smoking behaviors and application of the method and system. The construction method comprises the following steps: respectively obtaining saliva and excrement of a smoking object and a non-smoking object; performing metagenome sequencing to obtain original microbiome data; after processing the original microbiome data, extracting multi-omics feature information, including species information and gene function annotation information; based on a statistical analysis method, carrying out diversity analysis and screening microbial markers and functional genes significantly related to smoking behaviors; constructing a training set and a test set, and training a machine learning model and model evaluation by taking the microbial markers and / or the functional genes as input features; and performing smoking behavior identification on a target sample by using the model, and outputting a prediction result. The accuracy rate of model identification reaches 0.7966, the sensitivity is 0.8750, the specificity is 0.7037, and the method can be applied to health assessment and judicial expertise.

The invention relates to the technical field of smoke control area automatic identification, and discloses a smoke control area automatic identification system, which comprises a behavior data acquisition module, a behavior analysis module, a behavior risk judgment module, a response generation module, a co-processing unit and the like. The behavior data acquisition module acquires real-time sensing data streams and divides the real-time sensing data streams into far infrared thermal sensing and visible light picture data streams; the behavior analysis module generates abnormal feature maps respectively; the behavior risk judgment module fuses the feature map based on a preset strategy matrix and determines a risk level; the response generation module matches a response strategy; and the co-processing unit generates a processing instruction after cross validation. The system further comprises a network communication gateway, a security linkage module and the like, and the functions of data protocol adaptation, processing queue optimization, event archiving and the like can be achieved. According to the invention, through multi-source data fusion and intelligent analysis, the accuracy and response efficiency of smoke control monitoring are improved, and the method is suitable for automatic identification and management of smoking behaviors in public places.

The invention relates to the technical field of indoor behavior detection, and discloses an indoor smoking behavior detection method and system based on transient mutation characteristics. The system comprises a transient sensing module which captures multi-source sensing data streams such as temperature, humidity, air quality and images in a target space in real time and accurately captures environment changes related to smoking; the environment modeling module constructs a dynamic behavior response model based on multi-source data, converts smoking detection into an environment state evolution process, can adapt to a complex indoor environment, and avoids false detection and missing detection; the behavior decision-making module takes a transient feature analysis algorithm as an engine, generates a sudden change sensing agent, identifies a smoking behavior by analyzing a data trend and feature combination, and reduces a misjudgment rate; the execution verification module rapidly executes intervention instructions such as ventilation equipment starting and alarm triggering according to the judgment result, seamless joint of detection and intervention is achieved, the harm of smoking is reduced, and an efficient scheme is provided for indoor smoke control.

The invention relates to the technical field of robots, in particular to a robot inspection method and system for a dynamic scene. The method comprises the following steps: acquiring an infrared image of a target place, and taking an area of which the temperature is greater than a temperature threshold value in the infrared image as a candidate area; collecting a visible light image of the candidate area; inputting the infrared image into a first classifier to obtain a first confidence coefficient; inputting the visible light image into a second classifier or a neural network model to obtain a second confidence coefficient; fusing the first confidence coefficient and the second confidence coefficient based on a D-S evidence theory to obtain a smoking behavior confidence coefficient; responding to the condition that the smoking behavior confidence is greater than a first threshold value, and judging that the smoking behavior exists; and in response to the condition that the smoking behavior confidence is less than or equal to a first threshold value and greater than a second threshold value, performing smoking behavior modeling based on a Markov chain to determine whether a smoking behavior exists or not. The accuracy of smoking detection can be improved.

The invention provides a smoking behavior detection system based on an edge device, and belongs to the field of computer vision, the smoking behavior detection system is deployed on a Jetson Nano edge computing device, and the smoking behavior detection system is used for detecting the smoking behavior through video frame acquisition processing, a lightweight spatial-temporal feature extraction and recognition model and a high-speed reasoning module using a TensorRT reasoning engine. And the real-time detection of the smoking behavior in the monitoring video is realized. The system firstly preprocesses a video frame collected by a camera, and performs feature extraction on a target area and judges a smoking behavior by using a time-space behavior recognition network improved by pruning redundant Token of input data. When a smoking behavior is detected, the system may generate alarm information and alarm voice locally at the terminal. The system has the advantages of convenient deployment, high real-time performance, local reasoning and the like, and is suitable for firework safety management in various public scenes.

The invention relates to the technical field of electronic cigarettes, in particular to a safety control method and system for an electronic cigarette. The method comprises the steps of obtaining a pre-stored matching template and multi-modal data input during user verification; the multi-modal data comprises smoking behavior data, and the matching template comprises a smoking behavior template; performing identity verification on the user according to the multi-modal data and the matching template, and if the verification is passed, sending a starting instruction to the electronic cigarette; after the electronic cigarette is started, whether the current smoking behavior data are matched with the smoking behavior template or not is judged, and if the current smoking behavior data are not matched with the smoking behavior template, a locking instruction or an instruction for requiring a user to perform verification again is sent to the electronic cigarette. According to the method, the use safety of the electronic cigarette can be ensured in the whole process.

This invention relates to the field of indoor behavior detection technology, and discloses a method and system for detecting indoor smoking behavior based on transient change characteristics. The system includes a transient sensing module that captures multi-source sensor data streams such as temperature, humidity, air quality, and images in the target space in real time, accurately capturing smoking-related environmental changes; an environment modeling module that constructs a dynamic behavior response model based on multi-source data, transforming smoking detection into an environmental state evolution process, adaptable to complex indoor environments, and avoiding false positives and false negatives; a behavior decision module that uses a transient feature analysis algorithm as its engine to generate a change-sensing intelligent agent, identifying smoking behavior by analyzing data trends and feature combinations, reducing the false positive rate; and an execution verification module that, based on the judgment results, quickly executes intervention commands such as starting ventilation equipment and triggering alarms, achieving seamless integration of detection and intervention, reducing the harm of smoking, and providing an efficient solution for indoor smoking control.

The invention discloses a second-hand smoke monitoring and controlling device in a closed space. The device comprises a smoke source intelligent identification sub-module, and an infrared human body detection sub-module, a particulate matter concentration detection sub-module, a multimedia intervention sub-module, an air purification sub-module and an air quality announcement sub-module which are respectively in communication connection with the smoke source intelligent identification sub-module, the smoke source intelligent identification sub-module adopts an algorithm based on smoke source fingerprint identification, accurately distinguishes different sources of tobacco smoke and non-tobacco smoke by analyzing particle size distribution of particulate matters generated by different smoke sources or a change trend of chemical components along with time, and performs time-space fusion on smoke source data and infrared data to confirm a smoking behavior; and generating a co-processing instruction, and associating the co-processing instruction to the multimedia intervention sub-module, the air purification sub-module and the air quality announcement sub-module. The invention further discloses a method for monitoring and controlling the second-hand smoke in the closed space by using the device.

The invention discloses a smoking behavior recognition method based on multi-source perception and particle size fingerprint analysis, which comprises the following steps: arranging a particulate matter sensor module, continuously collecting a multi-channel particle size spectrum in a target space in a non-optical mode, and generating a high-resolution particle size distribution sequence according to time; an infrared sensor module is arranged to monitor entering and leaving states of personnel in real time; the short-term change of the concentration distribution of the particulate matters with different particle sizes is calculated through a parameterization formula, and the accurate judgment of the smoking event is realized in combination with the personnel state and the PM2.5 speed increase in the same period. According to the invention, the infrared sensing data stream and the particulate matter concentration data stream are deeply analyzed, and the on-site state of personnel and the specific fluctuation mode of cigarette smoke are accurately identified; through cross cooperation verification of multi-dimensional features, interference of water vapor, mosquito-repellent incense and non-artificial smoke sources can be effectively eliminated, and unification of high detection precision and low false alarm rate is achieved. According to the method, imaging equipment is completely abandoned, and the risk of privacy disclosure is avoided from the source.

The invention provides a bimodal-based pedestrian smoking state recognition system and method. The system comprises an image acquisition module, a data preprocessing module, a feature extraction and fusion module and a smoking detection module. According to the method, the high-precision detection and judgment of the smoking behavior are realized by fusing the complementary sensing characteristics of the visible light and the infrared image. According to the method, a double-flow collaborative deep neural network structure is adopted, semantic features of a visible light image and temperature features of an infrared image are extracted respectively, a cross-modal channel attention mechanism is introduced into a feature layer, and self-adaptive fusion and space focusing of multi-modal information are achieved. According to the method, accurate geometric calibration is not needed, and end-to-end smoking detection and identification can be realized only by ensuring collection time synchronization.

The invention discloses a smoking habit data acquisition device. The smoking habit data acquisition device comprises a smoking set body, and a honeycomb-shaped ceramic heating body, a heating control module, a main control module and a lithium battery which are arranged in the smoking set body, the heating control module comprises a voltage control module and a current detection module, and the voltage control module applies a constant voltage to the ceramic heating body to enable the ceramic heating body to reach heat balance at the set temperature of 50-80 DEG C; the current detection module periodically collects the working current of the ceramic heating body and sends the working current to the main control module; the master control module comprises a microprocessor, a storage unit and a wireless connection module and is used for data processing, data storage and communication with external equipment. By means of the device, a relation curve of working current and time of the ceramic heating body during smoking can be obtained, and quantitative data analysis is provided for smoking behavior analysis.

The present disclosure provides a triggering method of an intervention prompt on the basis of user smoking behavior records, comprising: receiving smoking behavior record data associated with a user, wherein the smoking behavior record data includes a plurality of smoking behavior records; analyzing the smoking behavior record data to determine smoking behavior location data associated with each of the plurality of smoking behavior records; calculating a distance between locations indicated by every two smoking behavior location data; recording a first number of smoking behavior records in which the distance is less than a first distance as a set of smoking behavior record data; in a case where the first number is greater than a first threshold, determining a prompt range on the basis of the smoking behavior location data associated with the set of smoking behavior record data, wherein the prompt range includes consecutive areas or spaces that are connected and further includes locations indicated by the respective smoking behavior location data associated with the set of smoking behavior record data; and triggering pushing of the intervention prompt if the user enters the prompt range from the outside.

The invention discloses a smoking behavior detection method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the following steps: acquiring a video stream; identifying a human body and a cigarette in each frame of video image, obtaining a preliminary classification result about whether the human body is a smoker, and determining the confidence of the human body and the confidence of the cigarette; performing association matching processing on the human body and the cigarette according to the spatial relationship between the human body and the cigarette; and according to the preliminary classification result, processing the confidence coefficient of the human body and the confidence coefficient of the cigarette associated and matched with the human body to obtain a final classification result about whether the human body is a smoker. According to the embodiment, association matching is carried out by analyzing the spatial relationship between the human body and the cigarette, and the final classification result is judged by adopting the proper smoking behavior judgment mode according to the preliminary classification result of whether the human body is the smoker, so that the false detection rate of smoking behavior detection is effectively reduced, the calculation complexity is reduced, and the accuracy and the real-time performance are improved.

The invention discloses a smoking behavior detection method and device, equipment and a storage medium, and relates to the field of image recognition, and the method comprises the steps: obtaining target video frames corresponding to a to-be-detected target event, extracting posture features based on each target video frame, and determining a target posture corresponding to each target video frame based on the posture features; performing time sequence mode matching on the target video frames based on the timestamps and the target postures corresponding to the target video frames to obtain corresponding mode matching results, and determining a target start frame and a target end frame when the mode matching results represent that the target event is a suspected smoking event; and determining a to-be-verified video frame and a corresponding dynamic region of interest based on the target attitude, and performing object detection on the dynamic region of interest by using a target object detection model to obtain a corresponding target detection result, so as to generate a smoking behavior detection result corresponding to the target event based on the target start frame, the target end frame and the target detection result. According to the invention, the misjudgment rate of smoking behaviors is reduced.

The application provides a smoking behavior recognition method and system, and relates to the technical field of computers.The method comprises the following steps: S1, acquiring a real-time video stream, calculating the video stream by using a deep learning target detection model efficientDet, and acquiring a region of interest of a person, wherein the region of interest comprises the position of a hand and the position of a mouth; S2, acquiring the position of a joint in the region of interest by using a hand joint model, and calculating joint position distribution information; and S3, comparing the joint position distribution information with existing standard hand-held cigarette palm joint distribution, judging whether the current palm action conforms to the palm joint position distribution when smoking, and if yes, recognizing the action as a smoking behavior; the region of interest of a person is acquired by using target detection, thereby reducing unnecessary detection, enabling better utilization of computing resources, and having stronger robustness and being suitable for various complex scenes.

The invention relates to the field of production safety management, in particular to a tipping paper production safety monitoring method and system, and the method comprises the steps: calculating the abnormal score of a person behavior in each frame of real-time image; and generating an abnormal behavior judgment result of the personnel according to the abnormal score, and for the personnel judged to be abnormal, obtaining identity information of the personnel so as to supervise safety behaviors of all personnel in the production place. The method and the device have the effect of improving the smoking behavior recognition accuracy in the production process of personnel.

The present invention discloses a smoking behavior detection method based on deep learning, belonging to the technical field of image data processing, and comprising the steps of: obtaining a dataset for semantic segmentation; constructing a semantic segmentation network, including a Segformer encoder, an MCA, and a DFF; training the semantic segmentation network with the dataset to obtain a human body and smoke segmentation model; and detecting and judging smoking behavior. The present invention improves the semantic segmentation model, enhances the key feature extraction ability for smoke and human body regions, and simultaneously suppresses the interference of background noise, can enhance the ability to capture smoke edge details and global semantic information, and improves the segmentation accuracy. By performing temporal analysis in combination with consecutive frames of a video stream, the occurrence and duration of smoking behavior are dynamically determined through the change of the smoke region and the overlapping situation of the human body region. This method improves the accuracy and robustness of detecting smoking behavior.

The smoking behavior monitoring and early warning method comprises the following steps: pulling a monitoring video stream, and inputting the monitoring video stream into a monitoring model of a cascade architecture including lightweight face detection and cigarette detection; face detection is carried out on the monitoring video stream by using a lightweight face detection model, and the lightweight face detection model takes RetinaFace as a reference and adopts MobileNetV1-0. 25 as a backbone network; the obtained face area is input into a cigarette detection model, and the cigarette detection model takes YOLOv5s as a benchmark; and if the cigarette detection model detects a target cigarette, generating early warning information. Through a cascade architecture, a detection range is reduced from a whole image to a human face surrounding area, and accurate judgment and positioning of smoking behaviors in a high-density crowd place are realized.

The present invention discloses a method for recognizing calling or smoking behaviors in special scenarios. The specific steps include: S1, collecting real-time monitoring images; S2, performing face detection to determine potential ROI regions; S3, correcting the images to generate images to be classified; S4, classifying the behaviors, and extracting the features of the images to be classified; S5, comparing the features and calculating the similarity; S6, comprehensively calculating the final result based on multi-frame comparison information and classification information; S7, outputting the result of whether calling or smoking according to the behavior corresponding to the final category. The present invention can greatly improve the algorithm accuracy under the condition of limited data volume, and further improve the algorithm accuracy by constructing a feature library for misclassified cases, and finally make a decision through the method of multi-frame target tracking and matching, reducing the false alarm rate.

The invention discloses a smoking target identification method based on context learning. The method comprises the following steps: S0, performing coarse screening by using skeleton extraction; the method comprises the following steps: S1, inputting an image into a pre-trained ResNet-101 network for feature extraction; s2, constructing a feature pyramid network, and fusing multi-scale features through a top-down path; s3, splicing to form a global feature map; s4, key features are enhanced through an scSE module; s5, candidate areas are generated and screened; s6, performing context alignment on the candidate areas; and S7, performing classification and regression. The false detection rate and the omission rate in a complex scene can be reduced, and high-precision real-time smoking behavior recognition can be realized as far as possible.

The invention relates to the technical field of civil engineering safety monitoring, and particularly discloses a civil engineering site fire risk intelligent assessment system and method. The system comprises an image module, a smoke module and an AI module, the image module comprises a first camera and a second camera which are used for collecting image information of a construction site from different angles, and the smoke module comprises a plurality of smoke sensors which are used for sensing smoke signals in a specific area of the construction site. And the AI module comprises a position identification sub-module, a behavior identification sub-module and a smoke feature analysis sub-module, and is used for performing multi-dimensional fusion processing on the acquired images and smoke signals, and performing intelligent identification and risk assessment on the smoking behavior of the construction personnel based on a set risk scoring algorithm. According to the method, sensing signal triggering, image behavior analysis and multi-source information matching are combined, a set of three-dimensional and real-time smoking recognition and early warning mechanism is constructed, and the intelligent management level of construction site fire safety can be effectively improved.

This application provides a method, system, device, and storage medium for identifying smoking behavior in industrial parks. The method includes: acquiring video stream data from park surveillance; decoding the video stream data to obtain image frames; performing human target detection on the image frames to determine the location of each human body within the image frames; cropping sub-images containing the human bodies from the image frames based on their locations; performing smoking behavior recognition on the sub-images to determine whether the human body in the sub-image is smoking; and outputting the smoking behavior recognition results for each human body in the image frames. This method, through a two-stage processing architecture of first human detection and then region cropping, transforms the problem of identifying small-target smoking behavior in a large-scale park surveillance scenario into a refined behavior discrimination problem at a normalized scale. This effectively alleviates the contradiction between sparse features of small targets and background interference, improving the balance between recognition accuracy and computational efficiency.

The present invention discloses a method and system for detecting light smoking, which includes: obtaining a number of smoking images showing smoking behavior and preprocessing the smoking images; labeling the smoking behavior in the smoking images, using the number of labeled smoking images as a training sample set, and training a preset smoking detection model; obtaining monitoring video frames in real time, and using the trained smoking detection model to determine whether smoking behavior exists in the video frames. The preset smoking detection model includes a residual network that integrates a deep separable convolutional network and CSPNet as a backbone feature extraction network and a network that integrates PANet and DW‑CSP‑Net as a multi-scale feature extraction network. By constructing a light smoking detection model, the present invention achieves lower computational complexity and parameter requirements for smoking detection, reduces hardware equipment loss, and realizes lightweight smoking detection.

The invention provides a smoking hypertension patient health monitoring and control method, device and equipment, a medium and a program product, and relates to the technical field of health data processing, the method is applied to an intelligent mobile terminal, and the method comprises the following steps: converting user complaint information into structured data including life time, symptoms and mood feeling; based on the structured data and physiological data including blood pressure data collected by the wearable device, integrated health data displayed by a time axis is generated; determining smoking habit data based on the time and the place corresponding to the structured data; inputting the smoking habit data and the integrated health data into a natural language generation model to generate a chief complaint record; and performing classification and grading health management strategies through an AI algorithm based on the physiological data. Smoking behavior analysis and hypertension health monitoring are fused, personalized and dynamic health management of smoking hypertension patients is achieved, the accuracy of health state monitoring results of the patients is improved, and effective medical assistance is achieved for chronic diseases.

The utility model discloses a wrist wearing type smoking cessation instrument, and relates to the technical field of smoking cessation instruments. A display screen, a setting button and an alarm are arranged on the front side wall of the smoking cessation instrument main body, a smoke detection sensor and a thermal infrared imager are arranged at the left side end of the smoking cessation instrument main body, a charging socket is formed in the right side end of the smoking cessation instrument main body, and a control module, a GPS positioning module and an equipment power supply are arranged on the inner side of the smoking cessation instrument main body. The smoke detection sensor can monitor the smoke concentration around the user in real time, and when smoke is detected, the user is reminded through the alarm, so that the user can timely realize the smoking behavior and correct the smoking behavior; and the thermal infrared imager can monitor the change of local temperature at the hand position of the user and assists in judging whether the user is smoking or not, so that the smoking cessation effect is further enhanced. The electrode slice on the rear side wall of the smoking cessation instrument body is matched with the conductive gel slice, the wrist of the user can be slightly electrically stimulated through the electrical stimulation module, and reminding and intervention are given when the user smokes.

The present application belongs to the technical field of smoking monitoring, and particularly relates to an indoor smoking management method based on infrared monitoring. The indoor smoking management method based on infrared monitoring comprises at least the following steps: a monitoring step of monitoring the ambient temperature in a monitoring range in real time; a smoking judgment step of regarding a smoking event as occurring when a high temperature point higher than a preset smoking temperature point is judged to exist; a judgment confirmation step of continuously performing the real-time monitoring step to obtain the motion trail of the high temperature point after the high temperature point occurs, and performing reconfirmation of the smoking behavior; and a notification step of performing alarm and recording the smoking event after the smoking event is judged and confirmed to occur. The indoor smoking management method based on infrared monitoring can accurately judge the occurrence of the smoking behavior through infrared heat detection, image analysis and behavior judgment, and timely perform alarm processing.

The application discloses a smoking behavior detection method and device, equipment and storage medium, and relates to the technical field of image recognition. The method comprises the following steps: acquiring a pedestrian area in a to-be-detected image; performing smoking detection on the pedestrian area by using a fusion model obtained by fusing multiple models; the fusion model comprises a pedestrian posture recognition submodel, a cigarette recognition submodel and a pedestrian gesture and mouth shape recognition submodel; and whether there is a smoking behavior in the to-be-detected image is judged according to the recognition result of the submodel in the fusion model. By using the detection mode of multiple model fusion, comprehensive judgment is performed on the image features of the cigarette, the posture and action of the person and the gesture and mouth shape of smoking. Compared with a single detection model, the accuracy of smoking detection is greatly improved, and the object of smoking detection is the pedestrian area in the to-be-detected image, that is, the cigarette detection is performed only in the area where the pedestrian is located, so that background interference is avoided, and the situation of missing report or false report is avoided.