504results about How to "Reduce false positives" patented technology

The invention discloses automatic detection and assembly production equipment for a PCB (Printed Circuit Board) and a use method of the automatic detection and assembly production equipment, and solves the problems that an existing device is not accurate in pause when detecting angle adjustment of a camera and image distortion is caused by blurred sight when detecting movement of the camera. The device comprises a device main body, an automatic feeding assembly, at least one group of combined detection mechanisms and an auxiliary detection assembly, and the device main body comprises a device base, a detection base and an assembly base; the combined detection mechanism is arranged, the combined detection part does not interfere with operation of the automatic feeding assembly, the detection efficiency is improved, the combined detection part is driven by the monitoring driving part and the detection linkage part, the detection range can be flexibly adjusted, automatic pause is achieved during detection, and therefore a camera is allowed to have more time for focusing, and the detection efficiency is improved. And each part is ensured to be in a clear focus state.

The invention relates to a composition for identifying bladder cancer based on urine sample detection and application thereof, and belongs to the technical field of molecular biology. According to the composition disclosed by the invention, the bladder cancer is identified by detecting the expression of one or more of hsa-miR-423-5p, hsa-miR-155-5p and hsa-miR-590-5p in a urine sample; the composition comprises a specific reverse transcription stem-loop primer, a specific detection forward primer, a specific detection probe and a universal reverse primer. According to the composition disclosed by the invention, the expression of hsa-miR-423-5p, hsa-miR-155-5p and hsa-miR-590-5p in a urine sample is detected, and a binomial logistic regression model is combined, so that auxiliary judgment is performed on the bladder cancer, the sensitivity and the specificity are relatively high, and the accuracy of identifying the bladder cancer can be improved. The invention further provides a kit containing the composition, the detection object of the kit is a urine sample, and the kit has the advantages of being small in sample dosage, noninvasive in sampling, convenient, rapid, small in risk and the like.

The invention discloses a transformer on-line monitoring and fault early warning system, and particularly relates to the technical field of power equipment monitoring, and the system comprises a signal collection module, a signal filtering module, a broadband focusing module, a signal complexity analysis module, a threshold self-tuning module, a fault early warning module and a fault positioning module. The signal acquisition module acquires operation data of a transformer in real time through a sensor network, the filtering module removes noise, and the broadband focusing module converts broadband signals into narrow-band signals, so that the resolution is improved; the signal complexity analysis module evaluates the signal complexity, and the threshold value self-tuning module dynamically adjusts the threshold value; the fault early warning module judges whether to trigger early warning based on the adjusted threshold value, and the fault positioning module determines the position of the partial discharge source through a cross positioning algorithm; according to the invention, the problem that the accuracy of early warning is affected due to the fact that a traditional fixed-threshold monitoring method is easy to generate false alarm or missing alarm can be solved, and operation and maintenance personnel can be helped to quickly determine the position of a fault source through cross positioning.

The invention, which relates to the technical field of building construction monitoring, discloses a tall template construction safety monitoring system comprising a template data acquisition module, a dynamic load analysis module, an interpolation module, a time window analysis module, an adjacent region comprehensive analysis module and an early warning module. The template data acquisition module collects stress data of a basic area in real time through a sensor network, the dynamic load analysis module dynamically adjusts division of the stress area according to the stress data, the interpolation module performs smoothing processing on the adjusted data, the time window analysis module calculates area stress fluctuation, and the time window analysis module analyzes the area stress fluctuation. The adjacent region comprehensive analysis module evaluates the stress influence of adjacent regions, the early warning module generates risk levels through fuzzy logic, and the construction report generation module is used for recording and generating a safety report; according to the invention, a local dangerous area can be better controlled and accurately positioned, and large-range blind troubleshooting is avoided, so that the safety management efficiency of a construction site is improved.

The invention provides a fire-fighting monitoring system for a ship. The fire-fighting monitoring system for the ship comprises a fire detection module and a fire-fighting monitoring module, wherein the fire detection module comprises fire monitoring and identifying cameras and sensor assemblies which are arranged at all corners of the ship; the fire monitoring module is used for constructing a fire recognition model based on the collected data of the ship and performing fire recognition warning; the fire hazard early warning module is used for constructing a fire hazard prediction model and performing prediction warning of fire hazard risks; the fire control module is used for realizing automatic fire extinguishing and comprises an automatic fire extinguishing control unit and a remote control unit; the intelligent decision-making module is used for providing escape guidance and comprises a fire source positioning unit and a route planning unit; the performance optimization module comprises fire source positioning optimization and escape route optimization. The system can comprehensively monitor the interior of the ship, accurately identify and predict the fire risk, can perform automatic fire extinguishing operation, position a fire source and plan an escape route at the first time when a fire occurs, guarantees the life and property safety of personnel, reduces the ship loss, and reduces the environmental pollution risk.

The invention relates to the technical field of vulnerability detection, in particular to an industrial asset fingerprint identification-based vulnerability stain detection system, which comprises a data acquisition module, a data analysis module, a fingerprint identification module, a vulnerability matching module, a stain analysis module and a verification module. The flow data of each industrial asset device in operation is collected in real time to generate fingerprint information of the industrial asset device, the data collected in real time is matched with a vulnerability library according to the fingerprint information, existing known vulnerabilities are identified, and possible taint propagation paths are deduced according to network topology and taint sources by constructing a network topological graph, so that the taint propagation efficiency is improved. The method comprises the following steps: identifying affected equipment, evaluating the flow change of the affected equipment, calculating the influence degree of a taint source on a network, identifying abnormal activities in a taint propagation process, evaluating the network security risk, and adjusting a monitoring strategy and a threshold value in time according to an evaluation result to ensure the accuracy and reliability of a monitoring system.

The invention provides an intelligent ultrasonic-assisted ToF water level monitoring device and method, and relates to the technical field of water level monitoring. Respectively carrying out power supply and support connection, and simultaneously carrying out auxiliary biological deposition removal treatment; signal emission distance measurement is carried out through a ToF sensor; performing data communication acquisition on the water level distance measurement monitoring signal flow according to a preset acquisition period; and calling the water level ranging data algorithm model library, performing matched data processing on the water level ranging periodic signal flow set, performing variation trend analysis, and generating a target water level monitoring report. The technical problem that in the prior art, due to the fact that a traditional water level sensor is prone to being affected by riverway weeds and the like, misinformation is caused, and the accuracy of water level monitoring data is low can be solved, by integrating the ToF sensor and the ultrasonic module, misinformation caused by the riverway weeds and other objects is reduced, and the accuracy of the water level monitoring data is improved. And the accuracy of water level monitoring data is improved.

The invention provides a home accompanying system based on scene intelligent analysis, and relates to the technical field of data processing, and the method comprises the steps: collecting behavior data and environment data of a user, carrying out the preprocessing, obtaining daily data, extracting features from the daily data, carrying out the calculation, obtaining the weights of behaviors and environments, and carrying out the calculation of the weights of the behaviors and the environments; performing time alignment on the behavior characteristic data and the environment characteristic data to obtain a matched data set, analyzing the relevance between behaviors and the environment according to the matched data set, generating behavior pattern data, predicting the behavior trend of the user under the real-time environment data through the behavior pattern data to obtain predicted behavior data, and outputting the predicted behavior data. The method comprises the steps of predicting behavior data of a user, comparing the predicted behavior data with real-time behavior data to obtain abnormal behavior data, judging whether the user has potential danger or not according to the abnormal behavior data, and if yes, generating early warning information and sending the early warning information to a guardian or a specified terminal. Whether the user is in danger or not can be judged by intelligently analyzing the scene.

The invention relates to the artificial intelligence technology, and discloses an abnormal transfer detection method and device based on IP address drifting, electronic equipment and a storage medium, and the method comprises the steps: generating an equipment ID of login equipment according to pre-collected Web information, and carrying out the change detection of the login equipment according to a pre-obtained IP address and equipment ID; generating information features of the login device according to a detection result of the change detection and pre-acquired transfer information, and generating an initial risk value of the login device by using a pre-trained risk assessment model and the information features; generating a device fingerprint of the login device according to the Web information, and generating a fingerprint similarity of the login device by using the device fingerprint; and carrying out overflow increasing processing on the initial risk value by utilizing the fingerprint similarity to obtain a final risk value of the login equipment, and carrying out abnormity judgment on the login equipment according to the final risk value and a preset risk threshold value. According to the invention, the accuracy of detecting the abnormal transfer account can be improved.

The invention discloses a host exogenous nucleic acid identification method based on a high-throughput sequencing technology. The method comprises the following steps: acquiring sequencing data of a to-be-detected sample; filtering the sequencing data twice by using a host reference genome database to remove a host sequence; species classification is performed on the sequencing data after host filtering, and interference of homologous species sequences is reduced; performing sequence comparison by utilizing an identified species reference genome to obtain an accurate species sequence; low-complexity sequence removal is carried out on the compared sequences, so that the influence of sequence preference is reduced; and carrying out secondary comparison on the species reference genome by using BLAST or comparing the species reference genome to an NT library. By applying the method, the exogenous nucleic acid sequences of different host samples can be accurately and specifically identified, and effective analysis of biomass samples of high-host background and low-exogenous species is realized.

The invention relates to the field of identity authentication, in particular to an identity authentication method and system based on palm veins. An identity authentication system based on palm veins comprises an identity information acquisition module, a palm vein image acquisition module, an environment data acquisition module, a feature extraction module, a matching value calculation module, an authentication threshold adjustment module and an identity authentication module. According to the method, the multi-angle fusion operation is executed in the palm vein feature extraction process, so that the image used for executing feature extraction can fit the registered palm vein image, the difference caused by user operation behaviors during identity authentication is avoided, and the false alarm rate during identity authentication is reduced; when the matching value is calculated, the direct distance between the palm vein feature vector of the user and the authenticated palm vein feature vector corresponding to the identity information of the user in the identity library is calculated, and the accumulated distance caused by the change of the operation behavior of the user is also considered, so that the influence of the change of the operation behavior is weakened, and the false alarm rate in actual use is reduced.

The invention discloses an industrial network fault intelligent diagnosis method and system based on multi-source data, and the method comprises the steps: synchronously collecting data from a plurality of data sources of an industrial network, and extracting a time sequence statistical feature, a flow entropy feature and a protocol conformity feature to form a multi-dimensional feature vector; establishing a dynamic baseline model by adopting a sliding window online learning method, and calculating a comprehensive anomaly score for anomaly detection; the fault suspicion degree is calculated based on the equipment incidence matrix and the fault propagation model to realize fault source positioning; carrying out fault type identification and root cause analysis by adopting Bayesian reasoning and a knowledge rule base; and outputting a structured diagnosis report containing the fault source, the type, the root cause and the disposal suggestion. According to the invention, early warning, accurate positioning and intelligent diagnosis of industrial network faults are realized, and the operation and maintenance efficiency, safety and reliability of the industrial control network are significantly improved.

The invention discloses a financial cloud data center encryption tunnel communication detection method and device, and belongs to the technical field of network security, and the method comprises the steps: S1, collecting the flow of a financial cloud data center, decoding an HTTP protocol, and obtaining HTTP protocol elements, the HTTP protocol elements comprising quintuple information, a request header, a request body, a response header and a response body; s2, disordered language elements in the HTTP elements are judged and recognized, the disordered language elements are recognized, and the disordered language elements are encrypted / coded character strings; and S3, analyzing the disordered language elements through a big data stream analysis mode, filtering false alarms, detecting threats and giving an alarm. According to the invention, the malicious encrypted traffic transmitted by using the HTTP tunnel technology can be effectively identified, and the problem that the traffic is difficult to detect in the prior art is solved.

The invention discloses a power grid fault diagnosis method, which belongs to the field of power grid diagnosis and combines a topological structure and equipment configuration of a power grid, constructs a dynamic fault tree model and dynamically adjusts node states and logic relations in the model so as to realize rapid detection and accurate positioning of faults. The method mainly comprises the following steps: data acquisition: collecting real-time operation data from each monitoring point of a power grid; data preprocessing: cleaning and standardizing the collected data; constructing a static fault tree: constructing a static fault tree model according to the topological structure and equipment configuration of the power grid; dynamically updating the fault tree: dynamically adjusting a fault tree model in combination with real-time operation data; fault mode identification: identifying a potential fault mode through logical operation by using the updated fault tree model; fault positioning and diagnosis: based on the identified fault mode, determining the position and the type of the fault; and fault response: according to the diagnosis result. The method is mainly used for power grid fault diagnosis.

The invention relates to the technical field of intelligent monitoring of power equipment, in particular to an intelligent circuit breaker state monitoring method and system. The method comprises the steps that unified time sequence modeling is carried out on multi-dimensional operation data of the circuit breaker, periodic behavior fragments with internal rhythm characteristics are extracted, state feature vectors based on historical behavior self-reference are constructed, and the state feature vectors are mapped to a continuous interpretable state space to achieve dynamic visual expression of the operation state; on the basis, the state deviation intensity and the change direction consistency are quantified, so that progressive identification and early warning from normal operation to an abnormal state are realized; and combined prediction is further carried out in combination with a state trajectory and an abnormal index, a risk quantification result and an active intervention strategy are generated, and model adaptive optimization is realized through closed-loop feedback. According to the invention, intelligent operation and maintenance closed loop from real-time monitoring and abnormal early warning to predictive maintenance is completed.

The invention provides an Internet of Things data acquisition and abnormity early warning method and system, and relates to the technical field of Internet of Things data processing, and the method comprises the steps: constructing a digital twin model for a physical entity at a cloud end, and issuing prediction data to an edge node; acquiring sensor data by an edge computing node at a basic frequency, and computing a residual error between real-time data and predicted data and an information entropy of a residual error sequence; dynamically adjusting the data acquisition frequency of the edge node based on a two-dimensional decision space formed by the residual error and the information entropy; and when the residual error and the information entropy both exceed the threshold values, potential abnormity is judged, an edge side abnormity analysis program is triggered, and abnormal event information is uploaded. According to the invention, through cloud edge cooperation and intelligent decision making, the acquisition frequency is reduced in a stationary period, resources are saved, the frequency is improved when an abnormal symptom appears, monitoring is enhanced, and optimal balance between resource consumption and monitoring precision is realized; double criteria are adopted to effectively filter noise interference, and the false alarm rate and the missing report rate are reduced.

The invention provides a vibration optical fiber alarm threshold adjustment method, device and equipment and a storage medium, and belongs to the technical field of perimeter security and protection, and the method comprises the steps: obtaining vibration signals and environment parameter data collected based on a vibration optical fiber sensor and an environment sensor which are installed on a perimeter; extracting signal features of the vibration signals and data features of the environmental parameter data; inputting the signal features and the data features into an alarm threshold adjustment model to obtain a reference threshold; and obtaining the current threshold value of the vibration optical fiber, and adjusting the current threshold value of the vibration optical fiber as the reference threshold value. According to the method, the signal features and the data features are input into the alarm threshold adjustment model to obtain the reference threshold, false alarms caused by environmental factors and normal activities are reduced, it is ensured that the alarm can be triggered timely and accurately when a real intrusion behavior occurs, and the alarm accuracy of the perimeter security system is improved.

The invention belongs to the technical field of new energy automobile steering systems, and discloses a new energy automobile electric hydraulic power-assisted steering system and a control method thereof.The system integrates a double-source redundant hydraulic power unit, a hydraulic adjusting unit, a multi-dimensional working condition sensing unit and an intelligent main controller; the multi-dimensional working condition sensing unit is integrated with a road adhesion coefficient detection module and a battery remaining capacity detection module. The control method is layered look-ahead matching control and is executed by an intelligent main controller in parallel: a power-assisted decision-making layer divides a three-stage power-assisted mode according to multi-dimensional perception information, and limits a steering angular velocity when power-assisted is enhanced on a low-attached road surface; the energy optimization layer predicts and implements prospective energy storage and pump rotating speed self-adaptive adjustment based on the intention of a driver; and the fault diagnosis layer realizes rapid fault identification and redundancy switching through multi-parameter collaborative diagnosis. The contradiction of high energy consumption, response delay and weak safety guarantee of a traditional system is solved, and power-assisted steering which is safe, energy-saving, fast in response and high in adaptability is achieved.

The invention provides a training method of a three-dimensional ground penetrating radar underground target recognition network, and relates to the technical field of underground survey and nondestructive testing, and the training method of the underground target recognition network comprises the steps: obtaining three-dimensional ground penetrating radar original data containing a target object; analyzing data characteristics of the three-dimensional ground penetrating radar original data, and obtaining two-dimensional ground penetrating radar slice data corresponding to a horizontal plane, a vertical section and a cross section of the target object; expanding the two-dimensional ground penetrating radar slice data based on a cyclic generative adversarial network, and merging the expanded two-dimensional ground penetrating radar slice data to generate target-containing three-dimensional ground penetrating radar data; the three-dimensional ground penetrating radar original data and the target-containing three-dimensional ground penetrating radar data are converted into the point cloud data, and the point cloud data are utilized to train the preset recognition network to obtain the target recognition network, so that the underground target can be quickly, efficiently and accurately recognized, the target recognition efficiency is improved, and the false detection condition is reduced.

The invention provides a rainfall monitoring method and system based on unmanned aerial vehicle multi-mode noise reduction in the technical field of environment monitoring and unmanned aerial vehicle application, and the method comprises the steps: S1, collecting a visible light image and a long-wave infrared image through a multispectral vision module after an unmanned aerial vehicle takes off, and collecting a rainfall audio from an acoustic cabin through a microphone; s2, carrying out noise reduction processing on the visible light image, the long-wave infrared image and the rainfall audio; s3, extracting a raindrop size distribution histogram and a spatial density thermodynamic diagram based on the visible light image and the long-wave infrared image, and extracting acoustic MFCC features based on rainfall audio; s4, performing feature fusion operation based on the raindrop size distribution histogram, the visual density thermodynamic diagram and the acoustic MFCC features to obtain rainfall intensity; and S5, carrying out cumulant dynamic compensation based on the rainfall intensity to obtain the cumulative rainfall. The rainfall monitoring method has the advantages that the precision, robustness and practical level of rainfall monitoring are greatly improved.

The invention belongs to the field of biological detection, and particularly relates to a cardiac troponin I fragment, a product prepared from the cardiac troponin I fragment and application of the cardiac troponin I fragment. According to the specific technical scheme, the protein fragment comprises a cTnI (31-164) protein fragment, an HSP65 (187-375) protein fragment and a protein fragment combination. The invention provides a protein antigen or composition for detecting acute myocardial infarction, the detection specificity and sensitivity are ideal, and the protein antigen or composition can be further prepared into related reagents or kits according to needs.

The invention relates to the technical field of campus safety protection, in particular to a method and system for preventing campus bullying by using a laser radar imaging technology, and the method comprises the following steps: obtaining 3D point cloud data of an environment in a monitoring region preset in a campus, and collecting sound data in the monitoring region; processing the 3D point cloud data, generating a three-dimensional environment image and extracting a first behavior feature; processing the sound data, and extracting a second behavior feature; performing multi-modal fusion on the first behavior feature and the second behavior feature to generate a unified behavior feature vector; based on the behavior feature vector, identifying whether a bullying behavior exists in the current scene, and calculating a corresponding behavior risk score; according to the method and the device, whether the preset alarm threshold value is reached or not is judged, and if yes, corresponding alarm and early warning operation is triggered, so that non-intrusive active monitoring of non-appearance privacy leakage of the campus secret corner is realized, and the problems of privacy limitation and blind areas of traditional video monitoring are solved.

The invention discloses a multi-modal perception and agent collaborative urban operation event handling method, which belongs to the technical field of artificial intelligence, and adopts the technical scheme that multi-modal front-end equipment is deployed to collect data, a fusion confidence coefficient is generated based on multi-source data, and an event work order is generated when the fusion confidence coefficient reaches a threshold value; the method comprises the following steps: classifying work orders by utilizing an urban management knowledge graph, determining responsibility subjects and disposal guidance, and determining priorities by integrating risks and regions through a weight model; abstracting various resources as disposal resources, and realizing work order and resource matching assignment under the constraint of response time limit; when a complex event condition is met, disassembling into sub-work orders according to a knowledge graph and carrying out parallel processing; the processing resources upload processing feedback, automatic verification is carried out based on computer vision and multi-source evidence, closed loop is qualified, if not, processing or evidence supplementation is carried out, and a closed loop result is archived and used for continuously optimizing the model and scheduling. The beneficial effect of the invention is that the urban operation event handling method based on multi-modal perception and intelligent agent cooperation is provided.

The invention discloses a power transmission line risk identification system and method based on a cloud large model, and the system comprises a cloud platform which is used for pulling a video stream from a corresponding monitoring device according to the identification result of an image identification module, and transmitting the identification result of a video identification module to a large model identification module; the image identification module is used for carrying out risk identification on the alarm image returned by the monitoring and photographing equipment; the video identification module is used for carrying out risk behavior identification on the video stream forwarded by the cloud platform through a pre-trained target trajectory tracking model in the video identification module to obtain an identification result; and the cloud identification module is used for summarizing risk behaviors existing in the identification result of the video identification module forwarded by the cloud platform into a natural language through a risk identification large model pre-trained in the cloud identification module so as to obtain specific risk behaviors. According to the method, the power transmission line risk identification capability can be improved, and omission caused by personnel negligence can be reduced.

The invention provides a vulnerability early warning method and system based on asset fingerprint driving. The method comprises the following steps: acquiring vulnerability information data from a plurality of vulnerability information sources; asset fingerprint information of assets in the target system is collected; based on semantic analysis, version comparison and a fingerprint matching algorithm, performing fine-grained association matching on the vulnerability information data and asset fingerprint information, and identifying target assets affected by vulnerabilities; performing influence range analysis, risk level evaluation and repair priority ranking on the target assets to generate a vulnerability influence analysis report; based on the vulnerability impact analysis report, sending an early warning notification to a related person in charge, and automatically generating an electronic work order; the processing state of the electronic work order is tracked, the repair progress is recorded, and full-life-cycle closed-loop management of vulnerabilities from recognition to repair is achieved. The missing report rate and the false report rate are effectively reduced, and compared with manual matching, the full-automatic mode can form a complete closed loop, and the early warning efficiency is improved.

The invention provides a semantic perception collaborative intrusion detection method for multiple vehicle-mounted networks, and relates to the field of vehicle-mounted network security, and the method comprises the steps: collecting communication data from a plurality of vehicle-mounted network domains such as a controller local area network, a vehicle-mounted Ethernet, a host system and the like; analyzing business features of each domain based on semantic information, and extracting feature representation from the time sequence dependency relationship; and a cross-domain attention mechanism is utilized to realize feature association among multiple network domains so as to identify potential multi-stage intrusion behaviors. Through multi-domain semantic fusion and cooperative detection, the method can effectively recognize complex attack behaviors which only show weak abnormal features, improves the intrusion detection precision and robustness of a vehicle-mounted network, and is suitable for a safety protection scene of an intelligent connected vehicle.

The invention discloses a network traffic anomaly detection method based on a Transform generative adversarial network, and the method comprises the steps: collecting a plurality of traffic data in a normal operation state of a communication network, generating a traffic feature matrix corresponding to each piece of traffic data, and forming a training sample set; constructing a Transform generative adversarial network comprising an encoder, a generator and a discriminator, and training the Transform generative adversarial network by adopting the training sample set; and for network traffic to be detected, generating a traffic characteristic matrix by adopting the same method, inputting the traffic characteristic matrix into the trained Transform generative adversarial network, and calculating a difference value between the traffic characteristic matrix of the network traffic to be detected and the generated traffic characteristic matrix to judge whether the network traffic to be detected is abnormal. According to the method, the network traffic data is converted into the traffic feature matrix, and the features of the normal traffic data are learned by using the Transform generative adversarial network, so that efficient anomaly detection is realized, and the detection accuracy is improved.

According to the thrown object detection method and device based on video anomaly detection and the storage medium, normal continuous video frames without thrown objects are used as input, then an improved auto-encoder model is trained to achieve anomaly detection of the thrown objects, multi-frame smoothing is carried out on an error graph obtained after detection, interference of a running vehicle is reduced, a brightness threshold value is set, and the thrown object detection accuracy is improved. If highlight areas exist in the smoothed error graph, the areas are contained in a minimum bounding rectangular frame, then a result is displayed and stored, it is judged that the thrown objects exist in the current time period, and meanwhile early warning is given to a system. According to the method, the detection precision of the throwing object abnormal event can be improved, a throwing object data set does not need to be marked, the problem that throwing object types cannot be exhaustive is solved, and intelligentization of road surface throwing object detection is achieved.

The application discloses a pipeline threat behavior identification method and device and a storage medium, and relates to the technical field of machine vision. The method comprises the following steps: acquiring a to-be-detected video photographed by unmanned aerial vehicle inspection; performing target detection on image frames of the to-be-detected video, determining target detection boxes of detection objects in the image frames and target categories of the detection objects; performing trajectory tracking on the target detection boxes to obtain target trajectories of the detection objects; extracting behavior features of the detection objects, wherein the behavior features comprise morphological change features of the detection boxes and trajectory features of the target trajectories of the detection objects; and identifying pipeline threat behaviors of the detection objects based on the target categories, the behavior features of the detection objects and a pre-trained classification model. The method can effectively detect small targets such as personnel and vehicles, effectively determine threat behaviors such as personnel loitering, personnel digging and mechanical digging, and the algorithm has the light-weight feature.

The invention discloses a rapid screening and detecting method for vegetable pesticide residues, a multi-dimensional judgment basis is provided for pesticide residue detection by combining a PCR amplification result with the inhibition rate of acetylcholin esterase and butyrylcholin esterase, different types of pesticides may induce different gene expression changes, and the detection result is accurate. According to the rapid screening and detecting method for the pesticide residues in the vegetables, the accuracy of a detection result is improved, meanwhile, the variety of the pesticide residues in the vegetables can be accurately determined, the defect that specific pesticide varieties are difficult to distinguish by purely relying on an enzyme inhibition method is overcome, and the detection result is more targeted and accurate.