1055 results about "Region detection" patented technology

The invention discloses a pump shell welding seam quality detection method based on image segmentation. The method comprises the following steps: generating a steady-state pump shell welding seam image flow under the driving of motion compensation; obtaining a domain adaptive DINOv2 visual embedded feature map; performing adaptive pyramid fusion and cross-scale attention operation on the domain adaptive DINOv2 visual embedded feature map to generate a semantic form segmentation map; generating a semantic-texture fusion mask; performing uncertainty weighted optimization on the semantic-texture fusion mask in combination with the pixel-level confidence map to obtain a weld defect instance map; generating an interpretable texture anomaly heat map; and through multi-view supplementary shooting or manual auditing, supplementary pump shell welding seam image data is obtained, and the steady-state pump shell welding seam image flow is updated. According to the method, the system can continuously keep accurate positioning of the pixel-level segmentation boundary in a weak-label or even non-label migration scene, and boundary drift and area missing detection of a segmentation result are effectively avoided.

The invention relates to the technical field of data processing, and provides a target detection method and device, a model training method and device, electronic equipment and a medium. The target detection method comprises the steps that a to-be-recognized image and a query text are acquired, and the query text is used for querying a target object corresponding to the query text in the to-be-recognized image; performing image recognition on the to-be-recognized image to obtain image description features and region detection visual features; performing regional multi-modal fusion processing on the image description features and the regional detection visual features to obtain regional multi-modal fusion features; performing feature fusion processing on text features obtained based on the query text and the regional multi-modal fusion features to obtain text regional fusion features corresponding to the query text; and a target detection result is obtained based on the text features and the text region fusion features, so that the fusion degree of text semantics and image region features is improved, and the accuracy and robustness of target detection in a complex scene are improved.

The invention relates to the field of image cultural relic disease recognition and evaluation, in particular to a cultural relic disease recognition and evaluation system and method based on image analysis, and the system comprises a multispectral image collection module, an image processing module, a disease recognition module, a repair evaluation module, a decision optimization module and a disease database. The multispectral image acquisition module optimizes a light source through a reflective area detection algorithm to obtain a multispectral image; the image processing module uses a multi-band collaborative filtering algorithm to eliminate noise and extract fusion features, and divides disease areas; the disease identification module determines disease positions through a connected region marking algorithm, and performs disease classification by means of a neural symbol model; the repair evaluation module outputs a quantitative score; the decision optimization module weighs the repair effect, the cost and the time by introducing a multi-objective optimization model of a genetic algorithm, and outputs an optimal scheme; according to the invention, the disease identification precision and the automation and scientificity of repair evaluation are improved.

The invention discloses an ancient textile image restoration system based on artificial intelligence. The system comprises a multi-source image acquisition module, a damaged area detection module, a pattern generation module, a color restoration module, a texture synthesis module and a multi-scale fusion module. The system introduces a wavelet guidance-frequency domain attention mechanism and a rotation invariant Haar wavelet basis function to realize accurate identification and classification of a damaged area; a saliency-guided wavelet decomposition control and self-adaptive threshold denoising method is combined, so that the perception capability of slant textures and edge details is improved; the texture synthesis module constructs a hierarchical modeling strategy fusing Gram style loss, Wasserstein style loss and a total variation regular term, and realizes generation of high-quality textures with unified styles and smooth edges; the system can be widely applied to cultural relic digital repair and display scenes.

The invention discloses a multi-modal imaging method and system based on acoustic-thermal coupling, and relates to the field of artificial intelligence, and the method comprises the steps: firstly obtaining thermal radiation data and ultrasonic reflection data of a target equipment region, and obtaining thermal radiation embedded features and ultrasonic embedded features through feature representation learning; performing multi-stage compensation on the thermal radiation embedding characteristic to generate a thermal field compensation reference characteristic of each stage; synchronously carrying out equal-stage multi-stage compensation on the ultrasonic embedded features, coupling the ultrasonic compensation result of the previous stage with the thermal field reference features of the corresponding stage between every two continuous stages of compensation, and combining the ultrasonic embedded features and coupling output in the later stage of compensation; and finally, performing imaging by using the acoustic-thermal coupling characteristics after multi-stage compensation to obtain an acoustic-thermal coupling imaging result fusing the thermal distribution characteristics of the target equipment region and the ultrasonic reflection spectrum characteristics. According to the method, deep fusion of acoustic and thermal information is realized through multi-stage feature compensation and dynamic cross-modal coupling, and the comprehensiveness and accuracy of equipment area detection are improved.

The invention discloses a transformer substation defect identification method and system based on cooperation of large and small models. The method comprises the following steps: S1, acquiring image data and preprocessing the image data; s2, acquiring a scene understanding score, and if the score is higher than a preset scene threshold value, synchronously executing S3 and S4; otherwise, only executing S3; s3, inputting the image data into the small model to obtain a detection result, and if the detection result is higher than a first preset threshold value, directly taking the detection result as a current defect identification result; if the detection result is lower than the second preset threshold value, abandoning the detection result; if the image is between the first preset threshold value and the second preset threshold value, obtaining a region detection result through image cutting and local large model reasoning; s4, inputting the image data into the transformer substation defect detection large model to obtain a global detection result; and S5, obtaining a final defect identification result according to the small model and / or regional and / or global detection result. According to the invention, substation defect identification precision can be improved.

The invention relates to the technical field of intelligent diagnosis, in particular to a pressure vessel health monitoring method based on an intelligent algorithm, which comprises the following steps: acquiring pressure, stress and temperature data in real time by using a sensor array, calculating a track evolution parameter set, identifying a damaged area, detecting a fault event, and predicting a health state and residual service life. And establishing a damage grade classification framework, and obtaining a damage grade classification result. According to the method, through multi-source data real-time acquisition and spatial gradient refining processing, by using a pressure and stress distribution coupling relation, accurate damage positioning is realized, the anomaly detection sensitivity is improved, damage boundary coordinates are marked, the expansion rate of adjacent damage areas is quantified, and phase delay is judged in combination with a multi-period pressure track; fault recognition stability is enhanced, abnormal event classification precision is optimized, a material fatigue accumulation and pressure uniformity correlation means is adopted, health score attenuation observation is enhanced, health state quantification depth is improved, and life prediction reliability is expanded.

The invention discloses a natural resource supervision method based on three-dimensional GIS scene and video fusion, and relates to the technical field of intelligent natural supervision. Comprising the steps of collecting a video stream through a preset observation point, extracting a continuous frame sequence, and calling a space parameter set; performing dynamic region detection on the video frame sequence to generate change feature data; mapping the change characteristic data into a topological structure to be updated based on the projection matrix; calling a pre-constructed three-dimensional GIS scene model, and positioning an update area; according to the type identifier of the change feature data, executing an operation of deleting the associated geometry or constructing and fusing a new geometry; adding a state attribute label to the updated geometry, and storing an update model; the resource change rate is calculated, and when the change rate exceeds a preset industry threshold value, an early warning instruction is generated and pushed to the control terminal. And the space accuracy, the model updating efficiency and the early warning reliability of resource change identification in a complex natural scene are remarkably improved.

The invention discloses a multi-spectral image fusion building surface biological attachment area detection method and device and a medium, relates to the technical field of image processing, and discloses a multi-spectral image fusion building surface biological attachment area detection method comprising the following steps: based on a to-be-detected building, obtaining a visible light image collected by a visible light camera of an unmanned aerial vehicle, the multispectral camera acquires a multispectral image sequence based on at least two different frequency bands; registering the visible light image and the multispectral image based on a calibration and preprocessing module to obtain a pixel-level aligned visible light image and multispectral image sequence; and according to a deep learning feature identification module, identifying the visible light image and the multispectral image sequence after pixel-level alignment, and obtaining a pixel-level segmentation result of the organism attachment area of the to-be-detected building. Therefore, detection is carried out based on the unmanned aerial vehicle, deep learning and an image feature fusion mode are combined, and the building surface bioattachment recognition accuracy is improved.

The invention provides a short-baseline binocular three-dimensional human body posture reconstruction method and system, and the method comprises the steps: collecting original left and right image pairs, and carrying out the detection of a human body region; carrying out human body image pair matching and scale transformation on the detected human body region; parallax features are obtained based on the processed left and right human body area image pairs, feature fusion is carried out on the parallax features and human body features extracted by the three-dimensional human body posture estimation sub-network, a parallax image initial result is obtained based on feature fusion information, a loss function is established with the human body features to carry out parallax optimization, and an optimized parallax image and a scene depth image are obtained; human body features are obtained based on left and right human body area image pairs, feature fusion is carried out on the human body features and parallax features, two-dimensional human body joint points are obtained through two-dimensional posture estimation according to feature fusion results, and a three-dimensional human body posture initial result is obtained based on binocular camera parameters and a triangulation calculation method; and establishing a loss function with the scene depth map and human body prior supervision, and performing three-dimensional human body posture optimization to obtain an optimized three-dimensional human body posture.

The invention relates to an unmanned aerial vehicle autonomous exploration method for indoor / underground unknown space. The method comprises the following steps: S1, acquiring a pose of an unmanned aerial vehicle and a depth image provided by a depth camera, and constructing an ESDF environment map; s2, performing boundary search in the constructed environment map, and generating high-quality candidate viewpoints by adopting a mixed viewpoint method based on an existing boundary; s3, formulating a more reasonable boundary exploration sequence by adopting a novel boundary priority strategy and an isolated small region detection method; s4, recording a global path of each time by adopting a historical perception strategy, and calculating the motion smoothing cost to obtain an expected global exploration path; and S5, according to path planning, an LKH algorithm is adopted to solve the traversal problem of a global boundary viewpoint, an optimal traversal sequence is obtained, and an A * algorithm is utilized to search a feasible local path from the current position of the unmanned aerial vehicle to a first candidate viewpoint in a map. And S6, adopting a third-order uniform B spline curve, and introducing a penalty function to optimize the trajectory to obtain an expected trajectory. And S7, the expected flight path is sent to a flight controller of the unmanned aerial vehicle, and the unmanned aerial vehicle flies according to the flight path by applying a PD controller.

The invention discloses a focus segmentation method fusing PET and CT bimodal images, and relates to the technical field of computers. The method comprises the following steps: acquiring focus image data, separating the focus image data to obtain CT data and PET data, and inputting the CT data and the PET data into a bimodal medical image segmentation model to obtain a preliminary segmentation result; a difference region is generated based on the preliminary segmentation result, difference region detection is carried out on the difference region, and click signal data is generated; the difference region is a region which is not marked as a focus in the preliminary segmentation result; training the bimodal medical image segmentation model for a preset number of times through the click signal data, the CT data and the PET data to obtain a segmentation result; and determining a segmentation result generated by the last training as a lesion image segmentation result. The method can improve the medical image lesion segmentation precision.

Systems and methods for video coding and decoding using region packing are provided. At an encoder, a region detection module receives a video frame for encoding, identifies regions of interest in the video frame, and generates a bounding box for each region of interest. A region extractor module obtains the pixels within the bounding box from the video frame. A region packing module receives the identified regions of interest and arranges the bounding boxes within a packed frame substantially reducing the data to be encoded outside the identified regions of interest. A video encoder receives the packed frame and generates an encoded bitstream therefrom. At the decoder, the encoded bitstream is decoded and parameters sufficient to place the regions within a reconstructed frame are extracted. A reconstructed frame is generated which substantially maintains the spatial relationship and size of regions of interest in the original video frame.

The invention relates to the technical field of face recognition, and discloses a face recognition method and system suitable for an outdoor electronic instrument to solve the problem of low recognition precision under complex illumination, posture change and shielding conditions in the prior art, and the method comprises the steps: S1, collecting image data, and carrying out the preprocessing; s2, performing face region detection and face key point positioning on the illumination enhanced image; s3, performing affine transformation based on the face detection result set to perform face alignment; s4, extracting a face feature vector based on a ResNet100 structure; s5, performing attitude-guided feature reconstruction processing on the face feature vector to obtain an attitude-enhanced face feature vector; s6, performing feature normalization and identity classification on the posture-enhanced face feature vector, and outputting a face recognition result; and S7, outputting a final identity recognition result and confidence. According to the method, an efficient and scientific optimization scheme can be provided in outdoor face recognition, and remarkable technical values and economic benefits are brought to practical application.

The invention discloses a power line anomaly detection method and system based on an unmanned aerial vehicle. The method comprises the steps that a server analyzes a power line detection request to obtain a detection area and a detection time period; planning an initial detection track, generating a power line detection instruction based on the initial detection track, the detection area and the detection time period, and issuing the instruction to the unmanned aerial vehicle; the unmanned aerial vehicle executes an inspection task in the electronic fence, the initial detection track is dynamically corrected in the inspection process, and a flight time sequence image is collected; analyzing the flight time sequence image through a line anomaly detection model, and outputting a line anomaly detection result; an actual detection track is recorded, and abnormity marking is carried out on the actual detection track; and recording, encrypting and uploading an inspection log to the server. The method has the advantages that the detection efficiency, the intelligent level and the safety management capability of power line anomaly detection are greatly improved.

A region detection device (1) according to the present disclosure includes a line segment detection unit (32) that detects a line segment from a captured image including an image of a target object having a linear band shape, a main line segment extraction unit (33) that extracts a main line segment (SL) that is a line segment having a length equal to or more than a predetermined value; a correction unit (34) that generates, as a corrected image, a rotated image obtained by rotating the captured image such that the main line segment (SL) is perpendicular or parallel to an arrangement direction of pixels in the captured image, and a region detection unit (35) that detects a target object region indicating the image of the target object from the corrected image.

According to the method, firstly, SAR data are mapped to an optical image domain by using a conditional diffusion model, pseudo-optical images with consistent spatial spectrums are generated, and fusion distortion caused by difference of SAR imaging mechanisms in a traditional method is overcome; secondly, a refined cloud region detection mechanism of a Fmask cloud mask is introduced, a cloud pollution region and a cloudless region are dynamically distinguished in combination with an adversarial training strategy, and the problem that the cloudless region is mistakenly changed in the reconstruction process of an existing method is effectively solved; besides, a multi-source integrated sample data set is constructed in stages, and a training normal form of multi-index joint optimization of PSNR, SSIM and the like is adopted, so that texture detail recovery and spectrum fidelity of a thick cloud coverage area are realized in a complex scene. In downstream application tasks such as land utilization classification and disaster dynamic monitoring, the visual quality and the quantitative index of the cloud removal result have good effects, and reliable technical support is provided for high-precision reconstruction of remote sensing information of a multi-cloud area.

The invention relates to the technical field of computer vision, and discloses a feasible region detection method based on uncertainty perception and boundary enhancement, and the method mainly comprises the steps: designing a three-branch encoder to respectively encode an RGB image, a depth image and a boundary image, designing two branch decoders to decode the encoded RGB feature map and the depth feature map, processing the encoded boundary feature map by using a layer of up-sampling module, and then carrying out weighted fusion on the decoded RGB feature map, the decoded depth map and the up-sampled boundary feature map to obtain a fused image; and then uncertainty is calculated through weighted features, selective fusion is performed on feasible region detection suggestions of the RGB feature map and the depth image, and a final feasible region is obtained, so that a part with high correlation with boundary features is improved, accurate segmentation of road and non-road regions is improved, and the accuracy of road and non-road region segmentation is improved. And the generalization ability and robustness of the model are improved by designing a loss function optimization model training process containing boundary segmentation loss.

The invention discloses an operation interaction method and system applied to camera image editing, and relates to the technical field of image processing, and the method comprises the steps: obtaining a voice semantic heat map, a pointing intensity map, a touch confidence map and a gazing confidence map based on a multi-modal interaction data packet, and calculating an image feature matrix at the same time; fusing into a multi-modal evidence graph through a normalized scale; performing semantic segmentation according to the image feature matrix to obtain a semantic segmentation first draft and a pixel-by-pixel category confidence coefficient, and performing position correlation weighting on the pixel-by-pixel category confidence coefficient by taking the multi-modal evidence graph as a confidence coefficient modulation factor to generate a candidate object mask sequence; and performing highlight display on the candidate object mask sequence, and performing conflict resolution and priority rearrangement in combination with the multi-mode evidence graph to generate a target object mask. According to the method, deep fusion of the interaction intention and image segmentation is realized, the precision and consistency of candidate region detection are improved, and the stability of real-time rendering and the reliability of an editing result are improved.

The invention discloses a target detection method and device based on a visual language large model. The method comprises the following steps: constructing a target detection data set for training; analyzing the image by using area detection and target center point regression, and extracting center point coordinates of a target; and taking the central point as a prompt, and inputting a segmentation model to obtain an initial segmentation mask of the target. The initial segmentation result is verified by means of a visual language large model, the initial result is subjected to reasoning analysis by means of a text prompt function guide model, and false positive and adhesion targets are recognized; and removing target adhesion and false positive objects by using an improved watershed method. Compared with the prior art, the scheme of the invention effectively alleviates the problem that the existing automatic target detection method fails under the complex conditions of fuzzy target gray distribution, adhesion and the like, and can improve the reliability and accuracy of target detection.

The invention discloses an automatic parking method and device and a computer program product, and the method comprises the steps: screening ground point cloud from collected three-dimensional point cloud data of the surrounding environment of a vehicle; performing clustering processing on the ground point cloud to generate a plurality of point clusters; extracting a space boundary parameter of each point cluster, and calculating the length and width of a rectangular region corresponding to each point cluster; based on the size of the vehicle, the rectangular areas with the length and the width larger than the corresponding size of the vehicle are screened out to serve as candidate berthable areas; and parking path planning and automatic parking operation are executed based on a target available area selected by a user from the candidate available areas. Aiming at the inherent defect that a traditional automatic parking system depends on structured parking space characteristics, a three-dimensional terrain flatness quantitative evaluation mechanism is innovatively introduced, and the technical problems of parking area detection and vehicle mechanical protection in an unstructured scene are effectively solved.

The invention provides a remote sensing building group depth detection and change intelligent evaluation method for urban planning, and the method comprises the steps: carrying out the multi-modal data collection of a target urban region, and carrying out the standardization processing, abnormal value elimination, multi-modal alignment and interference suppression processing, and obtaining a multi-modal data set; constructing a multi-branch hybrid network, and performing triplet feature extraction on the multi-modal data set through the multi-branch hybrid network to obtain a building group fusion feature map; performing change area detection and change type classification on the two building group fusion feature maps with different time phases to obtain building group change information; and constructing a dynamic evaluation index based on the urban planning core demand, and performing building group change evaluation in combination with the building group change information. According to the method, through multi-source and multi-modal data acquisition and processing, multi-branch hybrid network triplet feature extraction and change detection and dynamic evaluation index application, urban planning core requirements are adapted, and building group detection precision and change evaluation effectiveness are improved.

The invention discloses a system and a method for producing a glue injection industrial brush by using an injection molding machine, and relates to the technical field of industrial brush processing, a multi-parameter coupling index is generated according to acquired working parameters, and the working parameters, the multi-parameter coupling index and a batch identifier in a corresponding time period are bound; the method comprises the following steps: performing multi-angle imaging on brushes, adding mark information sections, performing preprocessing, extracting candidate areas which may have defects, after detecting a plurality of defect areas, constructing a morphological synergy index to quantify the overall defect degree, and obtaining defect data of each brush; after a comprehensive index structure is constructed, an injection molding process feature vector is constructed, kernel mapping and an AWCCA method are utilized to calculate nonlinear correlation and local sensitivity between each working parameter and a form cooperation index, a working parameter interval is formulated, and a parameter modification suggestion is generated; in the production process, parameters are continuously corrected in a small-stride mode, the defect degree of the brush and the stability of the injection molding process are balanced, and more flexible regulation and control are achieved.

The invention discloses an urban environmental sanitation operation optimization method based on big data, and relates to the technical field of intelligent environmental sanitation optimization, and the method comprises the steps: collecting urban environmental sanitation data, building a pollution region model, abstracting a detection process of mobile detection equipment into a Poisson random process, and carrying out the optimization of the Poisson random process; the method comprises the following steps: deducing a probability distribution function detected in a polluted area, then calculating the lowest detection frequency of each area, calculating the optimal detection frequency of each area by adopting a simulated annealing algorithm, and carrying out global planning and scheduling on a sanitation operation path by using an improved NSGA-III multi-objective optimization algorithm. Through combination of a Poisson random process model and a simulated annealing algorithm, scientific quantification and optimal distribution of detection frequency are realized, the purpose of accurate detection is achieved, the utilization rate of detection equipment is effectively improved, the regional detection completion degree is improved by using the improved NSGA-III, and meanwhile, resource consumption of invalid operation is reduced. And the environmental sanitation task execution is more efficient.

The invention relates to the technical field of three-dimensional reconstruction, in particular to an electric power facility surrounding environment three-dimensional reconstruction method and system. The method comprises the following steps: acquiring electric power facility data, performing electric power facility layout structure analysis, and constructing an electric power facility three-dimensional model; obtaining electric power facility environment data, carrying out dynamic environment evolution, and constructing an electric power facility environment dynamic evolution model; performing rendering and model alignment embedding processing on the electric power facility three-dimensional model based on the electric power facility environment dynamic evolution model to generate an environment-electric power facility fusion model, and performing electric power facility corona loss fluctuation detection and environment fluctuation factor analysis; corona environment disturbance area detection and error calculation are carried out on the environment-electric power facility fusion model, disturbance error data are generated, and corona environment disturbance reconstruction processing is carried out on the environment-electric power facility fusion model. According to the invention, the electric power facility environment combined corona loss dynamic three-dimensional model reconstruction can be realized.

A collation device includes a processor configured to, by executing a program: (a) acquire a photographed image including a collation area provided on an object and a reference position area that serves as a reference for a position of the collation area; (b) detect the reference position area from the photographed image; (c) set a peripheral image area in the photographed image based on the reference position area and predetermined relative coordinates; and (d) detect the collation area in the peripheral image area.

The invention relates to the technical field of computer vision, in particular to a product design optimization system and method based on an image model. The method comprises the following steps: obtaining a product image, and carrying out image preprocessing to obtain a to-be-processed product image; performing image enhancement processing based on the to-be-processed product image to obtain a product enhancement image; constructing an image model based on the product enhanced image; detecting product surface scratches based on the product enhanced image to obtain product scratch data; marking a seriously scratched area according to the product scratch data; evaluating the anti-corrosion capability of the coating based on the seriously scratched area; a product anti-corrosion layer covering structure is optimized according to the anti-corrosion capacity of the coating; detecting product stains according to the severely scratched area to obtain product stain data; and speculating the product pollution process flow based on the product stain data. According to the invention, integration of defect identification and process optimization driven by a product image is realized based on a computer vision technology, and the precision and response efficiency of product design optimization are improved.

The invention discloses a method for detecting an oxtail area in a complex environment, which comprises the following steps of: firstly, acquiring oxtail data, and constructing a data set; then performing data processing on the oxtail in a complex environment based on a CBS-YOLOV8n model, wherein the model comprises a CS-Backbone network, a BS-Neck neck network and a Head head network; and finally, training the model based on the obtained data set, and realizing oxtail area detection through the trained model. According to the method, the CS-Backbone network and the BS-Neck neck network are introduced, and a multi-level feature optimization strategy is combined, so that the detection performance in a complex scene is remarkably improved, the performance indexes in a normal scene, a shielding scene and a multi-oxtail scene are improved, the problem of oxtail missing detection caused by shielding is effectively relieved, the problem of feature confusion under multi-target coexistence is solved, and the detection efficiency is improved. While the size of the model is maintained, the model detection precision is obviously improved compared with that of YOLOV8, and optimal balance of precision and efficiency is realized.

The invention provides a fault detection method for a switch power distribution cabinet and related equipment. The fault detection method comprises the following steps: acquiring operation power data of switch equipment in each area in the switch power distribution cabinet and a preset load weight of each area; acquiring a thermal signal information set of the switch power distribution cabinet by using an optical fiber type temperature sensing device; obtaining an area detection grade of each area according to the operation electric data of the switch equipment in each area and the thermal signal information of each switch equipment in the switch power distribution cabinet; according to the area detection grade of each area and the corresponding preset load weight, identifying a key area of the switch power distribution cabinet in the current detection period; and generating prompt information according to the operation electric data and the temperature information of the key area, and sending the prompt information to the central control equipment for display. According to the invention, the operation state of the equipment can be evaluated more comprehensively, so that the accuracy of fault detection is improved; and the regional detection level reflects the operation state of the equipment, so that inspection operation and maintenance resources are reasonably distributed.

The present disclosure relates to a method for detecting a region of interest in an image, a video encoding method, apparatuses, a computer device, a storage medium, and a computer program product. The method includes: obtaining a current to-be-detected image frame, determining a mapping block size parameter value from encoding parameters corresponding to the current to-be-detected image frame, dividing the current to-be-detected image frame to obtain multiple mapping blocks based on the mapping block size parameter value, performing a texture region detection on each mapping block to obtain a texture region of interest detection result. performing a motion region of interest detection on each mapping block to obtain a motion region of interest detection result, and determining a region of interest of the current to-be-detected image frame based on the texture region of interest detection result and the motion region of interest detection result.