94 results about "Scene segmentation" patented technology

The invention discloses a building construction intelligent safety monitoring method based on the Internet of Things, and the method comprises the following steps: obtaining construction environment data, structure state data and operation behavior image data, and carrying out the preprocessing; environment state modeling, local structure strain and behavior recognition and operation scene segmentation are carried out through the edge intelligent processing unit; feature fusion is carried out, and a fusion situation vector is constructed; performing high-frequency anomaly identification and emergency preliminary screening, and generating an edge preliminary early warning result and a high-risk data fragment; constructing a safety evolution trajectory crossing a time window, and fusing historical data to generate a risk semantic map; cloud semantic reasoning operation is executed, and a final risk level judgment result and a corresponding trigger source identifier are generated; and automatically triggering a safety response instruction according to a risk level judgment result. According to the method, the Internet of Things and intelligent semantic analysis are fused, multi-source safety monitoring and self-adaptive response are realized, and the method has the advantages of high real-time performance, global perception and continuous optimization.

The invention discloses a double-arm clothes folding robot control method and device, equipment and a storage medium. The method comprises the following steps: determining three-dimensional point cloud data of a target workbench according to a collected image through a visual perception assembly; determining a scene label graph and a desktop edge line set through a scene division assembly according to the three-dimensional point cloud data, determining a clothing mask of the to-be-processed clothing according to the scene label graph through a clothing classification assembly, and determining a clothing description vector according to the clothing mask; determining a low-risk action set and a protection area mask from the candidate clothes folding action set through a safety protection component according to the scene label graph, the desktop edge line set and the clothes mask; determining a target clothes folding action sequence through an action planning component according to the clothes description vector, the low-risk action set and the protection area mask; and folding the to-be-processed clothes through the robot control assembly according to the target clothes folding action sequence. According to the scheme, the clothes folding efficiency and reliability of the robot are improved.

The invention belongs to the technical field of computer vision, embedded edge calculation and intelligent video monitoring, and discloses a yolk-based night smoke and fire identification optimization method, which can effectively detect flames at night or in a scene with disordered light. A multi-source data fusion and lightweight scene segmentation technology is adopted, an on-site perception model is built, and the model is combined with a small sample learning mechanism, so that night common interference factors such as vehicle lamps and street lamps can be identified; then, a federal learning algorithm and a time sequence attention module are used for modeling the dynamic characteristics of the smoke and fire, and an obtained characteristic model has high generalization ability; then, the system accurately screens out real smoke and fire candidate targets through self-adaptive threshold matching and pixel-level interference elimination operation; and finally, based on a multi-factor decision model and a dynamic edge transmission technology, rapid alarm of smoke and fire identification is realized. The whole system can also automatically optimize the whole process parameters of the method through rule mining and reinforcement learning.

The invention relates to a self-adaptive perception strategy switching method and system for long-distance automatic driving, and the method comprises the steps: carrying out the analysis of a public data set through employing a multi-target joint optimization clustering method, generating a standard scene prototype, and constructing an initial scene-optimal strategy mapping database; acquiring multi-dimensional scene features of a navigation route, performing global optimal scene division and recognition on a target road section, and generating a perception strategy map between continuous cells; querying a scene-optimal strategy mapping database continuously optimized by reinforcement learning, and selecting an optimal perception strategy for each cell based on a Q value maximization principle; when the vehicle enters the new cell, the self-adaptive switching control module automatically activates the preloaded optimal sensing strategy; and evaluating a strategy execution effect, generating an instant reward, transmitting an experience tuple containing a state, an action and the reward to the cloud, and continuously optimizing the Q-value database. The method and the system can improve the perception performance and the resource utilization efficiency of the automatic driving system.

The invention provides a scene segmentation and editing method and system based on three-dimensional Gaussian sputtering, and the method comprises the steps: carrying out the two-dimensional instance segmentation of a three-dimensional scene multi-view two-dimensional image, obtaining a two-dimensional instance mask, initializing the three-dimensional reconstruction through three-dimensional Gaussian sputtering, and obtaining a three-dimensional Gaussian body set; associating cross-view consistent semantic features extracted by the pre-training visual language model for each Gaussian body, constructing and iterating a three-dimensional instance prototype library based on a two-dimensional instance mask, and performing conversion to obtain a cross-view consistent two-dimensional supervision signal; adding a learnable instance identity code for each Gaussian body, constructing a multi-dimensional loss function in combination with a two-dimensional supervision signal, a spatial neighborhood relationship and cross-view consistent semantic features, and optimizing learnable parameters containing the instance identity codes; and realizing Gaussian body instance grouping based on the optimized instance identity codes to complete instance-level scene segmentation and editing. According to the method, the technical problems of instance identity association and high-quality instance level generation under the conditions of sparse view angle and close adjacent objects are solved.

A method and processing device for providing a scene segmentation map for a total field of view of an image capturing device comprises obtaining a scene segmentation map for the total field of view; receiving an indication that a new focus value has been set for the image capturing device for acquiring images of a current field of view; comparing the new focus value with a stored focus value associated with a focus region in the current field of view, wherein the stored focus value represents a previously used focus value; upon the new focus value deviating from the stored focus value more than a trigger threshold, triggering a scene segmentation map update process; and otherwise maintaining the scene segmentation map.

The invention relates to an automatic generation method and device of a plot abstract and electronic equipment. The method comprises the following steps: performing scene segmentation and key plot anchor point identification on each single-set original script of a target video, and generating a corresponding single-set draft abstract by using a large language model; performing multi-dimensional quality evaluation and screening processing on each single-set draft abstract, and converting the single-set draft abstract into a structured data object; sequentially arranging all the data objects to obtain a single-set abstract sequence of the target video; inputting the single-set abstract sequence into a large language model to enable the large language model to generate a whole draft abstract of the target video in combination with a preset narrative structure guide prompt; and performing multi-dimensional quality evaluation on the whole drama draft abstract, and optimizing the whole drama draft abstract based on an evaluation result to obtain a drama abstract of the target video. According to the method and the device, the technical problem that the effect and the reliability of an existing method in automatic abstracting of the long series are poor is solved.

The invention discloses a process planning model pre-training method and system based on multi-processing scene segmented imitation learning, and relates to the field of computer-aided manufacturing, comprising the steps of: for various processing scenes comprising different geometric features, material characteristics and processing requirements, generating processing paths of various strategies by using a mature process database of CAM software; virtual trial cutting is carried out through a processing process world model to generate a large number of initial states, rich and diversified training samples are provided for reinforcement learning pre-training, and on the basis, large-scale pre-training is carried out by adopting a segmented behavior cloning method to obtain a process autonomous planning base agent which learns processing strategies in different processing scenes; in the face of a new processing task, a processing path can be quickly generated through transfer learning. According to the method, the generalization ability is remarkably improved, meanwhile, geometric-physical-control collaborative planning is achieved, and an intelligent solution is provided for efficient planning of the modern manufacturing industry technology.

The invention discloses a semi-supervised adaptive unstructured scene segmentation method, and relates to the technical field of computer vision. The method comprises the following steps: acquiring label-free image data of an unstructured scene; inputting the weakly enhanced image into a teacher model to generate a first prediction result; inputting the strong enhancement image into the student model to generate a second prediction result; calculating the JS divergence between the first prediction result and the second prediction result, and dynamically adjusting the attenuation coefficient of the index moving average according to the JS divergence; updating teacher model parameters according to the adjusted index moving average attenuation coefficient to obtain an unstructured scene segmentation model; and inputting a to-be-predicted unstructured scene image into the trained unstructured scene segmentation model, and outputting an unstructured scene segmentation result. According to the method, the teacher model weight updating rate is reduced in the model divergence significant stage such as the initial training stage or the difficult sample processing stage so as to suppress noise propagation, and the prediction precision of unstructured scene segmentation is effectively improved.

This invention discloses a 3D scene segmentation and interaction method based on 3D Gaussian, comprising: Step 1, instance discovery: inputting 3D Gaussian scene data, dividing the 3D Gaussian points into structurally coherent instance-level Gaussian groups to obtain refined instances; Step 2, instance and scene semantic assignment: selecting representative viewpoint images of refined instances and inputting them into a visual-language model to generate semantic description labels for the instances; filtering instance pairs in the scene through spatial geometric relationships, and clarifying the spatial relationship description of instance pairs through a large model, constructing a static scene graph that integrates geometric proximity relationships and instance semantic relationships, forming a structured description of all instances; Step 3, natural language-driven instance localization and interaction: receiving user input commands, combining the instance semantic description, the static scene graph, and the real-time viewpoint direction relationship during the query to perform multi-dimensional matching, determining the target instance ID, and executing interactive operations.

Embodiments of the present application disclose a video scene segmentation method, device, equipment and storage medium. The method comprises: performing video segmentation on the video to obtain a plurality of shot pictures; performing feature extraction on the plurality of shot pictures respectively to obtain multi-modal features of each shot picture in the plurality of shot pictures; performing fusion processing on the multi-modal features of each shot picture in the plurality of shot pictures respectively to obtain fusion semantic information of each shot picture in the plurality of shot pictures; determining scene segmentation positions in the plurality of shot pictures according to the fusion semantic information of each shot picture in the plurality of shot pictures, and performing scene segmentation on the plurality of shot pictures. By using the method, the accuracy of video scene segmentation is improved.

The invention provides a three-dimensional scene segmentation method and device, equipment and a storage medium, and relates to the technical field of artificial intelligence and computer vision technologies. The method comprises the following steps: inputting an RGB rendered image into a coder-decoder module, and processing the input RGB rendered image through a two-dimensional visual language model and a coder to obtain Gaussian semantic features; fusing the Gaussian semantic features with other Gaussian attribute features of the three-dimensional Gaussian rendering model to obtain all Gaussian attribute information, inputting the Gaussian attribute information and text information into a large language model, and outputting segmentation feature vectors; inputting the Gaussian semantic feature and the segmentation feature vector into a segmentation information output module to generate a semantic segmentation mask; and based on the semantic segmentation mask, outputting a segmentation result of the target object in the three-dimensional scene. According to the invention, automatic identification and region segmentation of the target object can be realized in a complex three-dimensional environment, so that the intelligent level of a three-dimensional multi-mode interaction and application system is improved.

The application discloses a self-supervised video scene boundary detection method based on a timing scene creator, which selects video clips from different pseudo scenes respectively, splices two clips to synthesize a semantic transition point as a pseudo scene boundary. In order to enhance the diversity of the synthesized scene boundary, the application performs shot exchange between the involved video clips. In addition to the pseudo boundary, the application also provides the most likely non-boundary scene through adjacent shots from the same pseudo scene or the shots at the end of the repeated pseudo scene. The application effectively provides high-quality pseudo label data for self-supervised pre-training of video scene segmentation, and significantly improves the accuracy of the video scene segmentation model.

The application provides a three-dimensional point cloud segmentation method, system, device and medium, the method comprising: constructing an initial three-dimensional Gaussian point cloud according to multi-view image data of a target scene; obtaining first base elements located in a boundary blur region in all three-dimensional Gaussian base elements of the initial three-dimensional Gaussian point cloud according to initial semantic masks of each frame of image in the multi-view image data, and performing an adaptive splitting operation on each first base element to obtain a plurality of second base elements; performing multi-scale semantic feature training on a target three-dimensional Gaussian point cloud with the initial semantic mask as a supervision signal to obtain a semantic feature vector of each base element in the target three-dimensional Gaussian point cloud; and assigning a corresponding semantic label to each base element in the target three-dimensional Gaussian point cloud according to the semantic feature vector to obtain a three-dimensional Gaussian point cloud after semantic segmentation. The application realizes optimization of a boundary splitting process of Gaussian splashing and a semantic feature matching process, and improves the accuracy, robustness and flexibility of three-dimensional Gaussian scene segmentation.

The present application relates to the technical field of information monitoring, in particular to a kind of bidding informationization platform data security monitoring analysis method, comprising: collecting bidding platform data, according to the operation object, operation quantity and operation type of bidding platform data under continuous time period, user behavior is divided into multiple monitoring points, obtain the user behavior sequence of each monitoring point composition;Scene segmentation is carried out to user behavior, determine the abnormal behavior relative to historical behavior baseline under each scene segmentation dimension;Each abnormal behavior is incorporated into multiple correlation sets, determine the behavior correlation result of each correlation set and operation object;The correlation path under different scene segmentation dimensions is determined by the distribution form of monitoring point with the behavior correlation result;The intersection of the correlation path under all scene segmentation dimensions is updated the path list after the combination of each correlation path, and the updated path list is used as the output early warning target;The response speed and processing efficiency of platform to abnormal behavior are realized.

The application discloses an IPTV program time period analysis method and system, and mainly relates to the big data analysis technical field of IPTV programs. The method comprises the following steps: key frame extraction and scene segmentation are performed on media video to obtain a plurality of semantic time periods and content labels corresponding to each semantic time period; user behavior logs are analyzed, key time points in the video are recognized and clustered to obtain a plurality of behavior hotspot time periods and behavior characteristics corresponding to each behavior hotspot time period; the semantic time periods and the behavior hotspot time periods are matched and aligned, and analysis and merging are performed according to preset merging rules to output final time period division results and corresponding labels. The application has the beneficial effect that it can intuitively display content corresponding to the time periods, help users jump to watch and provide more efficient and accurate watching experience.

The present invention relates to a method of segmenting scenes in a video and a system therefor. Specifically, the present invention relates to a method and system for determining whether there is a transition between scenes and segmenting each of the scenes by extracting semantic characteristics of shots constituting a scene, particularly a specific shot and shots adjacent thereto, and comparing these characteristics.

The invention discloses an auxiliary operation method based on an AI visual identification algorithm, a medium and equipment, and the method comprises the steps: carrying out the video image collection of power failure detection operation, and carrying out the frame extraction and deblurring of collected video image data; recognizing a sub-scene corresponding to the image scene subjected to frame extraction and deblurring processing through a scene recognition network FOSNet; and carrying out identification registration on the starting image scene and the ending image scene of the sub-scene, and comparing the registered image scenes to judge the scene state. Scene segmentation is performed on a video by using a scene recognition model, and a starting time point and an ending time point of a scene are extracted. Meanwhile, the sub-scenes are segmented, the subsequent recognition operation is simplified, and necessary conditions are provided for state comparison of the subsequent sub-scenes; whether the equipment state change is correct or not is judged by comparing the scene starting equipment state with the scene ending equipment state, so that whether the scene operation is completed and reasonable or not is inferred. And the complexity caused by the process of directly identifying the action behavior is avoided.

The present application belongs to the technical field of unmanned aerial vehicle monitoring, and particularly relates to a method and device for filtering hidden danger targets of unmanned aerial vehicles, an electronic device and a storage medium. The method comprises: obtaining real-time data of unmanned aerial vehicles and preprocessing the real-time data to obtain target data; performing target reasoning and scene segmentation reasoning on scene images in the target data respectively, and correspondingly outputting hidden danger targets containing label information, confidence and target detection frame information and scene region masks, and constructing the hidden danger targets and the scene region masks into a first data set; obtaining GPS coordinates and feature vectors of the hidden danger targets based on unmanned aerial vehicle GPS data, unmanned aerial vehicle three-axis attitude angles, unmanned aerial vehicle mounted camera parameters and target detection frame information of the hidden danger targets, and constructing the GPS coordinates and the feature vectors into a second data set; and filtering the hidden danger targets based on the first data set and the second data set. The present application aims to solve the problems of single filtering dimension, poor multi-model coordination and insufficient real-time performance of unmanned aerial vehicle targets in the prior art.

The invention discloses a priori knowledge-driven railway track traffic scene segmentation processing method. The method comprises the following steps: S1, carrying out point cloud data voxel filtering; s2, performing fitting plane filtering on the point cloud data screened in the step S1; s3, obtaining a new optimal fitting plane based on the filtered point cloud data in the S2, and updating the reference frame; rotating the original point cloud into a reference frame; s2, rotating the point cloud filtered in S2 into a reference frame to obtain a reference point cloud; s4, the railway section length is set; s3, obtaining segmentation masks for segmenting the original point cloud and the reference point cloud after attitude adjustment obtained in the step S3, and constructing corresponding scene indexes; adjusting the scene index of the segmented original point cloud of which the number of points is lower than the quartile lower limit into an index value of an adjacent scene; and S5, carrying out local scene attitude adaptive adjustment. The scene segmentation strategy can be applied to large-scale rail transit scene point cloud processing; feature offset is reduced through dynamic adaptive calibration.

The invention discloses an end-side collaborative video understanding method and system based on a multi-modal large model, and the method comprises the steps: taking the efficient perception and memory construction of an end side as a front end, and taking edge node multi-modal large model reasoning as a rear end, and forming an overall architecture combining end-side preprocessing and edge node reasoning. At the end side, scene segmentation and incremental clustering are carried out, and a hierarchical memory structure comprising an original memory layer and an index memory layer is constructed; when a user initiates a natural language query, a key frame is retrieved and cross-modal reasoning and generation are carried out. The system comprises a video stream scene segmentation module, an intra-segment frame clustering module, a hierarchical memory structure construction module and a key frame retrieval module. By using the method, end-side calculation, storage economy and semantic retrieval efficiency are taken into consideration, and the method can be effectively applied to an end-side collaborative intelligent scene. The method can be widely applied to the field of man-machine interaction.

The invention provides a tag generation method and device, electronic equipment and a storage medium. The method comprises the following steps: inputting a video frame sequence of film and television content and related text description into a multi-modal large model; analyzing each frame of image in the video frame sequence through the multi-modal large model, and generating a picture-level label containing visual elements and semantic information; based on a video scene segmentation result of the video frame sequence, performing time sequence correlation analysis on a plurality of primary tags in the same scene to generate a scene-level semantic tag; and performing context association analysis on the plurality of scene-level semantic tags to generate a global semantic tag of the film and television content. Therefore, while the system structure is simplified, the accuracy and semantic coherence of tag generation are remarkably improved.

The application discloses a low-quality film image repair and enhancement method and system based on a dual network, and the method comprises the following steps: using an arbitrary scene segmentation method to segment an original video to be repaired into a plurality of video clips; extracting key frames of each video clip to form a key frame set, and extracting video frames in the original video to form a video frame set; combining the key frames and corresponding key frames repaired by a manual picture to form a low-quality-high-quality paired data set; the paired data set is divided into a plurality of groups and sequentially input into a pre-established and pre-trained pre-training repair and enhancement model, a transfer learning strategy is used for parameter updating, and a trained repair and enhancement model is obtained; the video frame set is input into the repair and enhancement model to obtain a repaired and enhanced picture set; and the picture set is recombined into a video according to an original video frame rate; wherein the pre-training repair and enhancement model is a dual network, comprising a generation network and a degradation network; and the trained repair and enhancement model is the generation network.

The invention relates to the technical field of interactive program design, in particular to an interactive program generation method based on three-dimensional scene segmentation, complementation and editable attribute recognition. Through deep analysis and intelligent processing of a three-dimensional scene, accurate identification of objects in the scene, interaction attribute analysis and user interaction task design and evaluation are realized by utilizing the capability of a large language model, object interaction attributes are automatically analyzed by utilizing the large language model, attribute tags are generated, and the user interaction task design and evaluation can be realized through natural interaction modes such as voice and gestures. According to the method, interaction content is edited in real time based on the object attribute analysis, and interaction logic is dynamically optimized based on deep learning until a complete interaction program is formed, so that full-process automation of three-dimensional scene processing, object attribute analysis and interaction content generation is realized, and a content creation threshold is reduced; the technical problems that in the prior art, interaction attributes are not considered in a traditional object recognition and numbering method, and the degree of supporting interaction content generation is poor are solved.

The invention discloses an IPTV program time period analysis method and system, and mainly relates to the technical field of big data analysis of IPTV programs. Comprising the following steps: carrying out key frame extraction and scene segmentation on a media asset video to obtain a plurality of semantic time periods and content tags corresponding to the semantic time periods; analyzing the user behavior log, identifying key time points in the video and performing clustering to obtain a plurality of behavior hotspot time periods and behavior characteristics corresponding to each behavior hotspot time period; and matching and aligning the semantic time period and the behavior hotspot time period, analyzing and merging according to a preset merging rule, and outputting a final time period division result and a corresponding label. The method has the advantages that the content corresponding to the time period can be visually displayed, and more efficient and accurate watching experience is provided while a user is helped to skip watching.

The embodiment of the invention discloses a video clip generation method and electronic equipment. The method comprises the following steps: receiving an original video material submitted by a user and video creation demand information expressed through a natural language; respectively preprocessing the original video material and the video creation requirement; performing scene segmentation and picture content understanding on the key frame picture sequence through an AI image understanding model, and generating a video understanding result in a text format; reasoning the video creation requirement and the video understanding result through an AI language model, and generating a video editing scheme in combination with video editing knowledge; and determining a tool corresponding to the atomization task according to the video editing scheme, constructing required parameter information for the tool, and calling the tool to generate a target video. According to the embodiment of the invention, the efficiency and the commissioning ratio of video creative production can be improved.

In a cloud-based system for encoding high dynamic range (HDR) video, each node receives video segments and bumper frames. Each segment is subdivided into primary and secondary scenes to derive a scene-based forward reshaping function. This minimizes the amount of reshaping-related metadata when encoding a video segment while maintaining temporal continuity between scenes processed by multiple nodes. Methods for generating scene-based forward and backward reshaping functions are also explored to optimize video encoding and improve the coding efficiency of the reshaping-related metadata.

The application provides a kind of fusion size model coordination mechanism multi-modal sentiment data automatic labeling method, it is related to sentiment computing and multi-modal data processing technical field, including the following steps: multi-modal data preprocessing and event level segmentation: the original multi-modal sentiment data of input is scene segmentation, semantic screening, modality separation and time alignment, generates the standardized structured multi-modal sample;Small model is used to the respective fast sentiment recognition of structured multi-modal sample each mode, and the confidence of each mode prediction result is output;The application is scene segmentation and semantic screening to video by scene event consistency principle, effectively eliminates redundant fragments, simultaneously realizes the event level accurate alignment of each mode data, solves the problem of difficult cross-modal alignment and insufficient preprocessing accuracy in the prior art, provides high-quality structured sample for subsequent automatic labeling, and significantly improves the effect of multi-modal fusion.

The invention relates to the technical field of image processing, and provides an image segmentation method, electronic equipment and a computer readable storage medium, and the method comprises the steps: obtaining a to-be-segmented image; carrying out portrait segmentation on the to-be-segmented image by adopting the portrait segmentation model to obtain a portrait segmentation result; obtaining a screened mask pattern, wherein the screened mask pattern is a mask pattern screened based on other segmentation results; combining the screened mask pattern and the portrait segmentation result to obtain a target object segmentation result; based on the target object segmentation result, performing shadow segmentation on the to-be-segmented image by using a shadow segmentation model to obtain a shadow segmentation result; and fusing the shadow segmentation result and the target object segmentation result to obtain a fused segmentation result. According to the method, full-scene segmentation can be realized, the image segmentation accuracy is improved, the image generation quality is further improved, and the user experience is improved.

The invention provides a dynamic cartoon generation method, device and equipment and a computer program product, and relates to the technical field of image processing. The dynamic cartoon generation method comprises the following steps: acquiring cartoon image information; performing scene segmentation processing based on the cartoon image information, and determining at least one cartoon scene sub-mirror and a subtitle sub-mirror corresponding to the cartoon scene sub-mirror; generating a dynamic cartoon image sequence based on a target cartoon object in the cartoon scene sub-mirror; and generating a dynamic cartoon based on the dynamic cartoon image sequence and the subtitle sub-mirror.