An invasive alien species detection system and method

Abstract

The application discloses an alien species invasion detection system and method, and belongs to the technical field of biological control. The application comprises a multidimensional signal sensing module, a feature spectrum construction module, an intelligent identification comparison module, a dynamic tracking positioning module, an abnormal early warning research and judgment module and a collaborative linkage response module. The application constructs a "space-ground-water" three-dimensional monitoring network, realizes non-contact precise detection through multi-sensor collaboration, can precisely trap specific insects, automatically collects and identifies tree insects, and the insect sound wave monitor can also remotely and early warn insect population activities. A three-level progressive feature processing architecture is adopted, multi-source data is uniformly analyzed, high-precision identification is realized, multi-modal insect feature vectors are extracted, large-scale insect screening requirements are met, and with the aid of sensor collaboration and geographic information fusion technology, a multidimensional target motion trajectory model is constructed, insect trajectories are updated in real time, are mapped to a geographic coordinate system and are superimposed on an ecological layer, and dynamic information and spatial decision basis are provided.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of biological control, in particular to an alien species invasion detection system and method. BACKGROUND

[0002] The traditional artificial patrol monitoring method has problems such as low efficiency, limited coverage, and inability to provide real-time early warning, and thus cannot meet the current demand for early detection and rapid response of alien species. Moreover, the existing detection systems mostly rely on a single sensor or detection method, such as image recognition or simple environmental parameter monitoring, which cannot accurately distinguish alien species from local species and has a high risk of misjudgment and missed judgment. Meanwhile, the existing technology lacks comprehensive consideration of the biological characteristics of species, ecological environmental factors, and transmission rules in the aspect of invasion risk assessment, and the scientificity of early warning information and effectiveness of prevention and control measures are insufficient, which leads to the failure to timely block the spread of alien species and causes serious damage to local biodiversity, agricultural and forestry production, and ecosystem function. Therefore, there is an urgent need to develop an alien species invasion detection system that can realize multi-source data fusion, accurate identification, dynamic tracking, and intelligent early warning to improve the level of ecological security protection. SUMMARY

[0003] The purpose of the present application is to provide an alien species invasion detection system and method to solve the problems raised in the background.

[0004] To achieve the above purpose, the present application provides the following technical solution: an alien species invasion detection system, comprising:

[0005] A multi-dimensional signal sensing module configured to collect signal data related to alien species in a target area through a detection device and transmit the signal data to a processing center in real time, wherein the detection device comprises a sensor node, a drone, a hyperspectral imaging device, a water quality sensor, a sonar device, and an insect monitoring device;

[0006] A feature map construction module configured to establish a feature map library of alien species;

[0007] An intelligent identification and comparison module configured to compare the signal data with the feature map library and identify alien species, and generate a preliminary identification report;

[0008] A dynamic tracking and positioning module configured to dynamically track the identified alien species and generate an alien species trajectory map;

[0009] An abnormality early warning and judgment module configured to determine the risk level of alien species based on the preliminary identification report and the alien species trajectory map, and issue an invasion detection information;

[0010] A collaborative and linked response module configured to establish an information sharing platform with forestry, agricultural, and environmental protection departments, and transmit the alien species invasion detection information in real time.

[0011] Further, the multi-dimensional signal sensing module further comprises:

[0012] Deploy sensor nodes and insect monitoring devices in the target area, the sensor nodes containing vibration sensors, infrared sensors and odor sensors, and the insect monitoring devices including insect sex pheromone traps, vibration-induced insect collection devices and insect sound wave monitors;

[0013] The vibration sensor is used to capture the vibration signals generated by animal movement, the infrared sensor is used to monitor the body temperature radiation of living beings, and the odor sensor is used to detect special biological volatile substances;

[0014] The insect sex pheromone trap is used to release artificially synthesized pheromones to trap specific insects, and the number of trapped insects is recorded by weight sensing or image recognition. The vibration-induced insect collection device is used to vibrate trees at low frequency, collect falling insects and identify their species through image sensors. The insect sound wave monitor is used to collect sound wave signals of insects flying or communicating and analyze the frequency spectrum characteristics;

[0015] A drone carrying a hyperspectral imaging device is used to periodically scan the target area according to a preset flight route to obtain vegetation spectral information;

[0016] Water quality sensors and sonar devices are arranged in the water area of the target area to monitor water quality change signals and underwater biological voiceprint signals.

[0017] Further, the feature map construction module comprises:

[0018] Collect the genetic feature map of confirmed alien species samples, conduct morphological analysis on the alien species samples, construct a digital map of the appearance form through 3D modeling, record the behavior patterns of the alien species in different environments, and form a behavior feature map, the behavior patterns including activity rules, foraging habits, migration rules, breeding cycles and host preferences;

[0019] Integrate the genetic feature map, the digital map and the behavior feature map to construct a feature map library.

[0020] Further, the intelligent recognition and comparison module comprises:

[0021] The feature extraction and conversion unit is configured to perform noise reduction processing on the vibration, infrared and odor physical signals collected by the sensor nodes and remove environmental noise interference, and use principal component analysis to extract key feature vectors.

[0022] Further, the key feature vectors include vibration frequency features, infrared radiation features, volatile organic matter features and insect voiceprint features;

[0023] The spectral matching filtering is performed on the vegetation spectral data acquired by the hyperspectral imaging device, and spectral characteristic parameters including absorption peak characteristics and reflectivity characteristics are extracted;

[0024] The time-frequency analysis is performed on the underwater signals collected by the water quality sensor and the sonar device, and multi-dimensional features including water quality parameter features and biological acoustic print features are extracted;

[0025] The extracted key feature vectors, spectral characteristic parameters and multi-dimensional features are standardized to construct a unified feature vector space.

[0026] Further, the intelligent recognition comparison module further comprises:

[0027] The atlas comparison unit is configured to calculate the similarity scores of the feature vectors in the feature vector space and the standard features of each species in the atlas library by using the cosine similarity algorithm, to calculate the sequence homology by using the sequence comparison algorithm for the genetic feature atlas, to set the E value and the similarity threshold for screening, and to generate the morphological feature similarity, the behavior feature similarity and the genetic feature similarity.

[0028] The morphological feature similarity, the behavior feature similarity and the genetic feature similarity are weighted and fused to generate a comprehensive similarity score.

[0029] The discrimination result output unit is configured to determine whether it is an alien species according to the comprehensive similarity score and a preset confidence threshold, to construct a hierarchical discrimination model, to perform classification recognition of the orders, families and genera, and then to perform accurate matching at the species level, to generate a preliminary identification report containing the species name, the similarity score, the confidence and the distribution area information, and to transmit the preliminary identification report to the dynamic tracking and positioning module.

[0030] Further, the dynamic tracking and positioning module comprises:

[0031] The sensor cooperative tracking unit is configured to perform target detection and tracking on the image sequence collected by the multiple cameras, to extract the motion trajectory features of the alien species, and to perform space-time registration of the visual tracking results and the infrared sensor and vibration sensor data.

[0032] A Kalman filter prediction model is constructed to perform real-time prediction and update of the motion trajectory of the alien species, to call the environmental sensor data to speculate the possible position, and to generate an alien species trajectory map.

[0033] Further, the dynamic tracking and positioning module further comprises:

[0034] The geographic information integration unit is configured to establish a coordinate conversion model, map a target position in a sensor coordinate system to a geographic coordinate system, construct an ecological environment information layer of an insect host plant distribution layer and an insect suitable habitat prediction layer, and label vegetation type, water distribution, and human activity region information.

[0035] The alien species trajectory graph is integrated into the geographic coordinate system.

[0036] Further, the anomaly early warning research and judgment module comprises:

[0037] The intelligent early warning decision unit is configured to, based on the preliminary identification report and the alien species trajectory graph, quantize a diffusion speed and direction by comprehensively considering a species reproduction capacity, a transmission path, and a topography and geomorphology factor through a diffusion risk evaluation algorithm.

[0038] A risk level division standard is designed, and the invasion risk is divided into different alien species risk levels, including a low risk, a medium risk, a high risk, and an emergency risk.

[0039] Based on the diffusion speed and direction, the invasion detection information of a corresponding level is automatically triggered according to a risk level and a preset risk threshold, and the invasion detection information comprises basic information of the alien species, possible harm, and suggested measures.

[0040] Further, an alien species invasion detection method is applied to the above-mentioned alien species invasion detection system, and comprises:

[0041] Step one: signal data related to the alien species in a target region is collected by a detection device and is real-time returned to a processing center;

[0042] Step two: a feature spectrum library of the alien species is established, the signal data is compared with the feature spectrum library to identify the alien species, the identified alien species is dynamically tracked, and an alien species trajectory graph is generated;

[0043] Step three: the alien species risk level is determined based on the species of the alien species and the alien species trajectory graph, and invasion detection information is issued, the alien species invasion detection information is real-time delivered to forestry, agricultural, and environmental protection departments through an information sharing platform.

[0044] Compared with the prior art, the present application has the following beneficial effects:

[0045] 1.The application can realize non-contact accurate detection of mobile organisms by constructing a "space-ground-water" integrated three-dimensional monitoring network, and deploying vibration, infrared and odor sensors in coordination. Even at night or in hidden environments, the traces of alien species can be captured through vibration frequency characteristics and body temperature radiation signals. The unmanned aerial vehicle carries hyperspectral imaging equipment, which can periodically cover a large area of monitoring area, identify potential invasive plants through subtle changes in vegetation spectrum, and combine water quality sensors and sonar equipment in water areas. Not only can the soundprint characteristics of underwater organisms be monitored, but also the metabolic influence of alien aquatic organisms can be inferred through abnormal water quality parameters. Specific insects can be accurately trapped, and image sensors can automatically collect and identify tree insects. The insect sound wave monitor can analyze the sound wave spectrum characteristics of insect flight or communication, and can realize early warning of insect population activity at a long distance, especially suitable for insect monitoring at night or in hidden environments, filling the time blind area of traditional visual monitoring.

[0046] 2.The application realizes high-precision identification of alien species through a three-level progressive feature processing architecture, analyzes unified monitoring data from different sources, and comprehensively uses cosine similarity algorithm and sequence alignment technology to realize fast overall feature matching and deep alignment for gene sequences, ensuring the accuracy of the identification result. Through a hierarchical discriminant model and a confidence evaluation mechanism, the identification is gradually refined from the genus classification to the species identification, avoiding the risk of misjudgment, and outputting a preliminary identification report containing detailed information, so that the system has intelligent autonomous identification capability, can quickly locate alien species in massive monitoring data, can flexibly adjust the identification threshold according to actual needs, balance the detection sensitivity and false alarm rate, extract species-specific soundprint features, combine vibration frequency characteristics to form a multi-modal insect feature vector, and determine the order and genus through a hierarchical discriminant model before species matching, meeting the demand of rapid screening of large-scale insect populations.

[0047] 3. The application realizes full-time and space dynamic monitoring of alien species by sensor cooperation and geographic information fusion technology. A multi-dimensional target motion trajectory model is constructed by using multi-camera visual tracking and multi-source sensor data registration. Even in complex environments, the moving direction of the species can be accurately predicted by the Kalman filter, avoiding tracking interruption caused by the temporary disappearance of the target. The tracking data is accurately mapped to the geographic coordinate system, combined with the ecological environment layer information, and the insect host plant distribution layer and the suitable area prediction layer are constructed to realize the ecological tracking of alien insect species. Not only can the real-time position of the species be intuitively displayed, but the insect motion trajectory can also be updated in real time. The potential association between the insect and the sensitive area can be revealed through spatial analysis. The insect trajectory map is integrated into the geographic coordinate system and superimposed on the host plant distribution to intuitively display the spatial association between the insect and the sensitive ecological area, providing spatial decision basis for precise deployment of traps or release of natural enemy insects, and providing real-time and accurate target dynamic information for prevention and control personnel. BRIEF DESCRIPTION OF DRAWINGS

[0048] Figure 1 The figure is a schematic diagram of the alien species invasion detection system of the application. DETAILED DESCRIPTION

[0049] The technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, not all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the application.

[0050] Please refer to Figure 1 The application provides the following technical solutions:

[0051] An alien species invasion detection system comprises:

[0052] A multi-dimensional signal sensing module is configured to collect signal data related to alien species in a target area by a detection device and transmit the data back to a processing center in real time. The detection device comprises a sensor node, a drone, a hyperspectral imaging device, a water quality sensor, a sonar device and an insect monitoring device.

[0053] A feature map construction module is configured to establish a feature map library of alien species.

[0054] An intelligent identification and comparison module is configured to compare signal data with the feature map library and identify alien species, and generate a preliminary identification report.

[0055] A dynamic tracking and positioning module is configured to dynamically track the identified alien species and generate an alien species trajectory map.

[0056] An abnormality early warning and judgment module is configured to determine the risk level of the alien species based on the preliminary identification report and the alien species trajectory graph and issue an invasion detection information;

[0057] A coordinated linkage response module is configured to establish an information sharing platform with forestry, agricultural and environmental protection departments to deliver the alien species invasion detection information in real time.

[0058] The multi-dimensional signal sensing module further comprises:

[0059] Sensor nodes and insect monitoring devices are deployed in the target area, the sensor nodes contain vibration sensors, infrared sensors and odor sensors, and the insect monitoring devices include insect pheromone traps, vibration drop insect collection devices and insect sound wave monitors;

[0060] The vibration sensor is used to capture the vibration signals generated by animal movement, the infrared sensor is used to monitor the biological temperature radiation, and the odor sensor is used to detect special biological volatile substances;

[0061] The insect pheromone trap is used to release artificial synthetic pheromones to trap specific insects, the number of trapped insects is recorded by weight sensing or image recognition, the vibration drop insect collection device is used to vibrate trees at low frequency, collect falling insects and identify the species through image sensors, and the insect sound wave monitor is used to collect sound wave signals of insect flight or communication and analyze the frequency spectrum characteristics;

[0062] A high-spectrum imaging device is carried by a drone to periodically scan the target area according to a preset flight route and obtain vegetation spectrum information;

[0063] Water quality sensors and sonar equipment are arranged in the water area of the target area to monitor water quality change signals and underwater biological voiceprint signals.

[0064] In the above embodiment, the multi-dimensional signal perception module builds an integrated "air-ground-water" three-dimensional monitoring network by deploying insect pheromone traps, vibration-type insect collection devices and insect acoustic wave monitors, breaking through the monitoring limitations of traditional single sensors. The coordinated deployment of vibration, infrared and odor sensors can realize non-contact and accurate detection of mobile organisms. Even at night or in hidden environments, it can capture traces of alien species through vibration frequency characteristics and body temperature radiation signals; drones equipped with hyperspectral imaging equipment can periodically cover large monitoring areas and identify potential invasive plants through subtle changes in vegetation spectra. Compared with manual inspections, the efficiency is increased by dozens of times and visual blind spots can be avoided; the combination of water quality sensors and sonar equipment in water areas can not only monitor underwater The acoustic signature of organisms can also be used to infer the metabolic impact of alien aquatic organisms through abnormal water quality parameters; insect pheromone traps can accurately trap specific insects (such as the gypsy moth) and achieve quantitative monitoring through weight sensing or image recognition, which increases efficiency by more than 50% compared to traditional manual trapping and provides more accurate data recording; the vibration-type insect collection device combined with an image sensor can automatically collect and identify tree insects, solving the problem of insect monitoring on tall trees; the insect acoustic wave monitor can achieve early warning of insect group activities at a long distance by analyzing the acoustic wave spectrum characteristics of insect flight or communication (such as the low-frequency pulse signals of migrating locust swarms), which is particularly suitable for insect monitoring at night or in hidden environments, filling the time blind spot of traditional visual monitoring.

[0065] Feature graph building modules, including:

[0066] Collect genetic profiles of confirmed alien species samples, conduct morphological analysis on the alien species samples, construct digital maps of their appearance through 3D modeling, and record the behavioral patterns of alien species in different environments, including activity patterns, foraging habits, migration patterns, reproductive cycles, and host preferences, to form behavioral profiles;

[0067] Integrate genetic feature maps, digital maps, and behavioral feature maps and construct a feature map library.

[0068] In the above embodiments, the feature map construction module innovatively integrates the species characteristics of three dimensions of genes, morphology and behavior, forming a stereoscopic biological recognition database. The digital map constructed by 3D modeling can accurately record the subtle structural differences of the appearance of species, accurately record the subtle structures such as wing veins and antennae (such as the texture of the thoracic wing of the Monochamus alternatus), and realize the integrity expression of the characteristics of insects in different growth stages (eggs, larvae, adults) through multi-angle image acquisition. The behavior feature map can accurately distinguish closely related species (such as the rice planthopper and the brown planthopper) through long-term dynamic monitoring of insect migration paths, breeding cycles and other data, and realize stable identification when insects are in different states such as migration period and dormancy period, so that the identification accuracy of the system for alien species of insects is improved to more than 92%, which is significantly higher than that of traditional morphological identification methods.

[0069] The intelligent recognition comparison module comprises:

[0070] The feature extraction and conversion unit is configured to perform noise reduction processing and remove environmental noise interference on the vibration, infrared and odor physical signals collected by the sensor node, and extract key feature vectors using principal component analysis.

[0071] The key feature vectors include vibration frequency characteristics, infrared radiation characteristics, volatile organic matter characteristics and insect voiceprint characteristics.

[0072] The vegetation spectral data obtained by the hyperspectral imaging device is subjected to spectral matching filtering to extract spectral feature parameters including absorption peak characteristics and reflectivity characteristics.

[0073] The underwater signals collected by the water quality sensor and the sonar device are subjected to time-frequency analysis to extract multi-dimensional features including water quality parameter characteristics and biological voiceprint characteristics.

[0074] The extracted key feature vectors, spectral feature parameters and multi-dimensional features are standardized to construct a unified feature vector space.

[0075] The map comparison unit is configured to calculate the similarity scores of the feature vectors in the feature vector space and the standard features of each species in the map library using the cosine similarity algorithm. For the genetic feature map, the sequence homology is calculated using the sequence alignment algorithm, and the E value and the similarity threshold are set for screening to generate the morphological feature similarity, the behavior feature similarity and the genetic feature similarity.

[0076] The morphological feature similarity, the behavior feature similarity and the genetic feature similarity are weighted and fused to generate a comprehensive similarity score.

[0077] The discrimination result output unit is configured to determine whether it is an alien species according to the comprehensive similarity score and a preset confidence threshold; a hierarchical discrimination model is constructed to first perform classification and identification of orders, families, genera and then perform accurate matching at the species level to generate a preliminary identification report containing the species name, similarity score, confidence and distribution area information, and the preliminary identification report is transmitted to the dynamic tracking and positioning module.

[0078] In the above embodiment, high-precision identification of alien species is achieved through a three-stage progressive feature processing architecture. Raw signal data is converted into standardized feature vectors using principal component analysis and spectral matching filtering algorithms, effectively eliminating environmental noise and data heterogeneity interference, enabling monitoring data from different sources to have a unified analysis basis. The cosine similarity algorithm and sequence alignment technology are used to achieve fast overall feature matching and in-depth alignment of genetic sequences, ensuring the accuracy of the identification results. The hierarchical discrimination model and confidence evaluation mechanism are used to gradually refine from family classification to species identification, avoiding misjudgment risks. The system has intelligent self-identification capabilities and can quickly locate alien species in massive monitoring data. The identification accuracy is significantly improved compared to traditional methods, and the identification threshold can be flexibly adjusted according to actual needs to balance detection sensitivity and false alarm rate, providing reliable decision-making basis for subsequent tracking and control. Time-frequency analysis is performed on the signals collected by the insect sound wave monitor to extract species-specific voiceprint features (such as the spectral peak of cicada chirping), combined with vibration frequency characteristics (such as the 500Hz high-frequency signal of mosquito wing vibration), forming a multi-modal insect feature vector. The hierarchical discrimination model is used to determine the insect order and family (such as Lepidoptera) and then perform species-level matching, meeting the demand for rapid screening of large-scale insect populations.

[0079] The dynamic tracking and positioning module includes:

[0080] The sensor cooperative tracking unit is configured to perform target detection and tracking on the image sequence collected by the multiple cameras, extract the motion trajectory features of the alien species, and perform spatio-temporal registration of the visual tracking results with the infrared sensor and vibration sensor data.

[0081] A Kalman filter prediction model is constructed to perform real-time prediction and update of the motion trajectory of the alien species, call the environmental sensor data to predict the possible location, and generate an alien species trajectory map.

[0082] The geographic information integration unit is configured to establish a coordinate conversion model to map the target position in the sensor coordinate system to the geographic coordinate system, construct an ecological environment information layer of the insect host plant distribution layer and the insect suitable area prediction layer, and label the vegetation type, water distribution, and human activity area information.

[0083] integrate the alien species trajectory map into a geographic coordinate system.

[0084] In the above embodiments, through sensor coordination and geographic information fusion technology, full-time and space dynamic monitoring of alien species is realized. By using multi-camera visual tracking and multi-source sensor data registration, a multi-dimensional target motion trajectory model is constructed. Even in complex environments, the moving direction of the species can be accurately predicted through the Kalman filter, avoiding tracking interruption caused by the temporary disappearance of the target. The tracking data is accurately mapped to the geographic coordinate system, combined with the ecological environment layer information, and by constructing the insect host plant distribution layer and the suitable area prediction layer, the ecological tracking of alien insect species is realized. Not only can the real-time position of the species be intuitively displayed, but the insect motion trajectory can also be updated in real time. Through spatial analysis, the potential association with sensitive areas can be revealed. The insect trajectory map is integrated into the geographic coordinate system and superimposed on the host plant distribution (such as the pine tree and pine wood nematode associated area), which can intuitively display the spatial association between insects and sensitive ecological areas, providing spatial decision-making basis for precise deployment of traps or release of natural enemy insects, and providing real-time and accurate target dynamic information for prevention and control personnel.

[0085] The abnormality early warning judgment module comprises:

[0086] The intelligent early warning decision unit is configured to, based on the preliminary identification report and the alien species trajectory map, quantize the diffusion speed and direction by a diffusion risk assessment algorithm, comprehensively considering the species reproductive capacity, transmission route, and topographic and geomorphic factors.

[0087] The design risk level division standard divides the invasion risk into different alien species risk levels, including low risk, medium risk, high risk, and emergency risk.

[0088] Based on the diffusion speed and direction, the risk level and the preset risk threshold are used to automatically trigger the invasion detection information of the corresponding level. The invasion detection information includes the basic information of the alien species, the possible harm, and the suggested measures.

[0089] In the above embodiments, through the intelligent risk assessment and grading early warning mechanism, active prevention and control of alien species invasion is realized. Based on the diffusion risk assessment algorithm, the biological characteristics of the species and environmental factors are considered to accurately predict the diffusion trend of the invasive species. By scientifically dividing the risk level and setting dynamic thresholds, the system can automatically trigger the early warning of the corresponding level according to the invasion scale and harm degree, avoiding insufficient or excessive early warning. The generated invasion detection information not only contains the basic information of the species, but also provides targeted prevention and control suggestions such as the best removal time, resource allocation scheme, etc., enabling the management department to quickly respond to invasion events, realizing the transition from passive response to active defense, effectively reducing the ecological and economic losses caused by alien species invasion, and improving the ecological security protection capability.

[0090] In the above technical solutions, the beneficial effects followed by "in the above embodiments" in each of the above technical solutions are beneficial effects of the technical solutions of the present application, which increase the beneficial effects related to detection of alien species of insects while retaining the original beneficial effects

[0091] The application discloses an alien species invasion detection method applied to the alien species invasion detection system.

[0092] Step 1: Collecting signal data related to alien species in a target area by a detection device and transmitting the signal data to a processing center in real time;

[0093] Step 2: Establishing a characteristic atlas library of alien species, comparing the signal data with the characteristic atlas library, identifying the alien species, dynamically tracking the identified alien species, and generating an alien species trajectory map;

[0094] Step 3: Determining the risk level of the alien species based on the species of the alien species and the alien species trajectory map and issuing invasion detection information, and transmitting the alien species invasion detection information to forestry, agricultural and environmental protection departments in real time through an information sharing platform.

[0095] The above merely describes the preferred embodiments of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can make equivalent replacements or changes to the technical solutions and the inventive concept of the present application within the technical range disclosed by the present application, and all of the above should be covered within the protection scope of the present application.

Claims

1. An alien species invasion detection system, characterized in that: include: A multi-dimensional signal perception module, configured to collect signal data related to alien species in the target area through detection equipment, including sensor nodes, drones, hyperspectral imaging equipment, water quality sensors, and sonar equipment, and transmit it back to the processing center in real time; a characteristic map building module configured to build a characteristic map library of alien species; An intelligent identification and comparison module is configured to compare signal data with a feature map library and identify alien species, generating a preliminary identification report; a dynamic tracking and positioning module configured to dynamically track identified alien species and generate an alien species trajectory map; The abnormal warning and analysis module is configured to determine the risk level of alien species and issue invasion detection information based on the preliminary identification report and alien species trajectory map; A collaborative response module is configured to establish an information sharing platform with forestry, agriculture, and environmental protection departments to transmit alien species invasion detection information in real time; The feature map construction module includes: Collect genetic profiles of confirmed alien species samples, conduct morphological analysis on the alien species samples, construct digital maps of their appearance through 3D modeling, and record the behavioral patterns of alien species in different environments, including activity patterns and foraging habits, to form behavioral profiles; Integrate genetic feature maps, digital maps, and behavioral feature maps and construct a feature map library; The dynamic tracking and positioning module includes: A sensor collaborative tracking unit is configured to detect and track targets in image sequences captured by multiple cameras, extract the motion trajectory characteristics of alien species, and perform spatiotemporal registration of visual tracking results with infrared sensor and vibration sensor data; Construct a Kalman filter prediction model to predict and update the movement trajectory of alien species in real time, call environmental sensor data to infer possible locations, and generate an alien species trajectory map.

2. The alien species invasion detection system according to claim 1, characterized in that: The multi-dimensional signal perception module also includes: Deploy sensor nodes in the target area. The sensor nodes include vibration sensors, infrared sensors, and odor sensors. The vibration sensors are used to capture vibration signals generated by animal movement, the infrared sensors are used to monitor biological body temperature radiation, and the odor sensors are used to detect special biological volatiles. Use drones equipped with hyperspectral imaging equipment to periodically scan target areas along preset routes to obtain vegetation spectral information; Water quality sensors and sonar equipment are deployed in the waters of the target area to monitor water quality change signals and underwater biological soundprint signals.

3. The alien species invasion detection system according to claim 1, characterized in that: The intelligent recognition and comparison module includes: The feature extraction and conversion unit is configured to perform noise reduction processing on the vibration, infrared and odor physical signals collected by the sensor nodes and remove environmental noise interference, and use principal component analysis to extract key feature vectors.

4. The alien species invasion detection system according to claim 3, characterized in that: The key feature vectors include vibration frequency features, infrared radiation features and volatile organic compound features; Perform spectral matching filtering on vegetation spectral data acquired by hyperspectral imaging equipment to extract spectral characteristic parameters including absorption peak characteristics and reflectance characteristics; Perform time-frequency analysis on underwater signals collected by water quality sensors and sonar equipment to extract multidimensional features including water quality parameter characteristics and biological soundprint characteristics; The extracted key feature vectors, spectral feature parameters and multidimensional features are standardized to construct a unified feature vector space.

5. The alien species invasion detection system according to claim 3, characterized in that: The intelligent recognition and comparison module further includes: The map comparison unit is configured to use the cosine similarity algorithm to calculate the similarity score between the feature vector in the feature vector space and the standard features of each species in the map library. For the gene feature map, the sequence alignment algorithm is used to calculate the sequence homology, and the E value and similarity threshold are set for screening to generate morphological feature similarity, behavioral feature similarity and gene feature similarity; The morphological feature similarity, behavioral feature similarity and genetic feature similarity are weighted and fused to generate a comprehensive similarity score; The discrimination result output unit is configured to determine whether it is an alien species based on the comprehensive similarity score and the preset confidence threshold; construct a hierarchical discrimination model, first perform classification and identification of phylum, class, order, family and genus, and then perform precise matching at the species level, generate a preliminary identification report containing species name, similarity score, confidence and distribution area information, and transmit the preliminary identification report to the dynamic tracking and positioning module.

6. The alien species invasion detection system according to claim 1, characterized in that: The dynamic tracking and positioning module further includes: A geographic information integration unit is configured to establish a coordinate conversion model, map the target position in the sensor coordinate system to the geographic coordinate system, construct an ecological environment information layer, and annotate vegetation type, water distribution, and human activity area information; Integrate alien species trajectory maps into geographic coordinate systems.

7. The alien species invasion detection system according to claim 1, characterized in that: The abnormal warning analysis module includes: An intelligent early warning decision-making unit is configured to quantify the spread speed and direction based on preliminary identification reports and alien species trajectory maps, using a diffusion risk assessment algorithm that integrates species reproductive capacity, transmission pathways, and topographic factors; Designing risk classification standards to classify invasion risks into different alien species risk levels, including low risk, medium risk, high risk and urgent risk; Based on the speed and direction of spread, the corresponding level of invasion detection information is automatically triggered according to the risk level and preset risk threshold. The invasion detection information includes basic information of the alien species, possible harm caused, and recommended measures.

8. A method for detecting invasion of alien species, applied to the system for detecting invasion of alien species as claimed in claim 1, characterized in that: include: Step 1: Use detection equipment to collect signal data related to alien species in the target area and transmit it back to the processing center in real time; Step 2: Establish a characteristic map library of alien species, compare the signal data with the characteristic map library and identify alien species, dynamically track the identified alien species, and generate an alien species trajectory map; Step 3: Determine the alien species risk level based on the type of alien species and the alien species trajectory map and issue invasion detection information. Transmit the alien species invasion detection information to the forestry, agriculture and environmental protection departments in real time through the information sharing platform.

Images