52 results about "Object tracking algorithm" patented technology

The invention relates to the technical field of cableway platform intelligent management, in particular to a cableway platform tourist falling detection method, system and device based on visual identification and a medium, and the method comprises the steps: collecting a video stream of a platform region, carrying out the pedestrian detection, obtaining the position of a bounding box of a tourist, and storing the position of the bounding box; a unique track ID and continuous track data are generated for each tourist by using a multi-target tracking algorithm; for each tourist, extracting a human body posture key point coordinate in each frame of the video stream and calculating a posture feature, and when the posture feature meets a preset posture collapse judgment rule, judging that the posture collapse is suspected; carrying out time sequence fusion on the continuous tracks of each tourist, and carrying out real falling event judgment based on the judgment condition of suspected posture collapse; and matching a preset platform area according to the position of the real falling event, outputting a risk level and triggering a corresponding control instruction. According to the invention, the falling behavior can be accurately and stably identified, and the safety protection capability of the cableway platform is improved.

The invention relates to the technical field of computer vision, in particular to a motion perception rockfall intelligent monitoring method and device based on deep learning. The method comprises the following steps: receiving a monitoring video from a monitoring area; constructing a rockfall detection and tracking framework based on a YOLOv8 target detection network and a ByteTrack target tracking algorithm; preprocessing the monitoring image, inputting the monitoring image into a YOLOv8 detection network to carry out moving target feature extraction, and outputting a rockfall detection result; and track matching is carried out by using a ByteTrack algorithm in combination with Euclidean distance and motion direction constraint, and a rockfall motion track is generated. According to the method, a traditional image algorithm and a deep learning algorithm are combined, moving target detection and multi-target tracking are constructed, and rockfall in a complex rock background is accurately captured from multiple dimensions; according to the method, the space coordinate position of the rockfall target can be accurately obtained, a complete movement track can be generated for each rockfall target, statistical information of rockfall events is effectively obtained, and a reliable basis is provided for disaster grade evaluation and early warning.

The invention discloses a target tracking method and device based on machine vision, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence or other related fields, and the method comprises the steps: obtaining a target video sequence containing at least two video frames, performing feature collection in the current video frame according to a predetermined to-be-tracked target to obtain a feature point set; performing matching analysis according to the feature point set and a previous feature point set corresponding to a previous video frame to obtain a feature point pair set; calculating a scale change value and a displacement value corresponding to the target according to the feature point pair set, and obtaining position information of a target frame in the previous video frame; and updating the position of the target frame in the current video frame according to the scale change value, the displacement value and the position information of the target frame in the previous video frame to obtain a target tracking result. Through the target tracking method and device, the technical problem that the tracking precision and continuity of a target tracking algorithm in a complex changing environment are reduced in the related technology is solved.

The application discloses a kind of based on target tracking algorithm's gas detection operation compliance identification method, belong to gas detection technical field.The method includes: high-definition video camera is arranged in the methane detection area of mine, real-time acquisition video data in methane detection area and image is preprocessed;By YOLO target detection method, the gas detector in the methane detection area in video is identified;If detecting that gas detector hand holds gas detector and arrives specified methane detection area on time, then it is judged as compliance operation, otherwise it is judged as non-compliance operation;After verifying that gas detector hand holds gas detector arrives specified methane detection area on time, the gas detection operation of scene is tracked in real time by CSRT target tracking algorithm;Then with standardized operation is compared, if gas detection operation meets standardized operation, then it is judged as compliance operation, otherwise it is judged as non-compliance operation.The application can improve the reliability and safety of gas detection operation, reduce the safety risk brought by illegal operation or non-operation.

Techniques for performing object tracking of objects in video images using both an object detection algorithm and an object tracking algorithm. Because the object detection algorithm is generally slower but more accurate than the object tracking algorithm, only certain sampled video frames are subjected to the object detection algorithm. Non-sampled frames use the object tracking algorithm to locate objects, using the most recent previous object detection frame as a starting frame. In this way, the object tracking algorithm is periodically, effectively calibrated using the object detection algorithm, by hiding the latency introduced by the object detection algorithm using the lagging detection results.

The application discloses a tracking target loss detection method based on color histogram distance, comprising: obtaining a tracking image, wherein the tracking image comprises a target region and a background region; determining a tracking frame scaling ratio based on the target region of the tracking image to adjust tracking frame parameters to obtain a target center region, so that the ratio of the number of pixels of a target object in the target center region to the number of pixels of the background satisfies a preset condition; generating a color histogram according to the target center region; storing color histogram feature values in time sequence based on the color histogram to detect target loss according to the feature values; wherein the tracking frame is a rectangle, and the tracking frame parameters comprise a side length and a rotation angle. The application can accurately detect the occurrence of abnormal feature values to improve the long-time working reliability and intelligent level of a target tracking algorithm and an application system.

The application discloses a production line specification operation behavior intelligent detection management system. The technical scheme points of the system are as follows: the system adopts a hierarchical fusion type architecture, and comprises a data acquisition layer, a pretreatment layer, a core AI algorithm layer, a business logic layer and a data storage and output layer from top to bottom. The data acquisition layer collects production line high-definition video streams and account data; the pretreatment layer optimizes image quality and decodes; the core AI algorithm layer integrates object recognition, behavior recognition, pose estimation and multi-target tracking algorithms, and perceives employee operation behavior in all dimensions; the business logic layer realizes five-dimension compliance determination, real-time line following snapshot storage and two-hour storage data cycle; and the data storage and output layer archives data and provides monitoring, report and traceability functions. The application solves the problems of low manual evaluation efficiency, poor working condition adaptation and single supervision dimension in the prior art, realizes real-time traceable intelligent evaluation of industrial production line operation, and is suitable for fine management scenes of various industrial production lines.

The application discloses an unmanned ship-oriented target detection and tracking method and system, and the method comprises the following steps: collecting a video frame of a water surface environment; establishing a YOLOv8 target detection model and a ByteTrack target tracking model, wherein the YOLOv8 target detection model adopts an HGNetv2 backbone network structure, and the ByteTrack target tracking model comprises a BYTE association strategy; inputting the video frame of the water surface environment into the YOLOv8 target detection model for water surface target detection, and outputting a water surface target detection frame set; inputting the water surface target detection frame set and the video frame of the water surface environment into the ByteTrack target tracking model for water surface target tracking, and outputting a water surface target tracking path set. The application solves the problems in the existing unmanned ship target detection and tracking method, i.e., the relatively large calculation amount and parameter amount in water surface target detection by using a Mobilenetv3-YOLOv4 target detection algorithm, and the possible missing detection situation in water surface target tracking by using a KCF correlation filtering target tracking algorithm, thereby reducing the tracking accuracy.

The invention discloses an object tracking method and device, a storage medium and electronic equipment, and relates to the technical field of computer vision and artificial intelligence. The method comprises the following steps: acquiring historical state data of a scene object; determining an inter-frame size difference and a size standard difference based on the historical state data; determining an anomaly detection result of the scene object according to the inter-frame size difference and the size standard deviation; when the abnormal detection result shows that the size of the detection frame is abnormal, adjusting observation noise in the initial tracking algorithm to obtain a target tracking algorithm; and tracking the scene object by using a target tracking algorithm to obtain a tracking trajectory. The object tracking method and device solve the technical problems of low accuracy and poor stability of an object tracking method provided in the related technology.

The invention discloses a target behavior recognition method and device for a boundary area. The method comprises the following steps: collecting video data of the boundary area; performing multi-target identification and tracking on the video data by adopting an improved target tracking algorithm, and giving a current track of each target; based on the current track of each target, determining a three-dimensional motion track of each target within a predetermined period after the current moment; and according to the current track and the three-dimensional motion track of each target, a target behavior recognition result is given in combination with the structural characteristics of the boundary region. The target behavior recognition precision of the boundary region can be improved.

The application discloses a safety helmet wearing detection method and system, which comprises a data acquisition module, a target detection module, a target tracking module and a camera equipment automatic control module, adds on-site monitoring images on the basis of the disclosed safety helmet wearing detection data set, obtains a new data set after data enhancement, constructs a safety helmet wearing detection network, simultaneously optimizes the initial anchor frame and the hyperparameter by using a genetic algorithm, trains the network to obtain a safety helmet wearing detection model, then combines a target tracking algorithm with a monitoring device to realize automatic tracking of the camera equipment on the target working personnel. The tracking algorithm automatically analyzes and extracts the motion trajectory features of the target, considers the interframe correlation, thereby making up for the shortcomings of the visual target detection method, improving the detection accuracy and the identification degree of small targets. The application can effectively solve the problems of small target missed detection in the construction environment and false detection in the complex background, and realizes automatic tracking detection of the camera equipment on the illegal target.

The invention discloses a target tracking algorithm-based sowing seed hole-falling counting method of a sowing machine. The method comprises the following steps of A, acquiring a sowing seed hole-falling video in a sowing process of the sowing machine in real time; b, constructing a sowing grain hole-falling data set based on the hole-falling video; c, constructing a sowing seed detection model for detecting and positioning sowing seeds; d, training to obtain a trained sowing grain detection model; and E, performing real-time target detection on the seeding grain hole-falling video to be subjected to hole-falling counting from a first frame by using the trained seeding grain detection model, and calculating the inter-frame grain distance of the same grain among different frame numbers by combining a target tracking algorithm from a second frame, when the inter-frame grain distance meets a set threshold condition, continuous tracking is carried out, and hole falling event judgment and counting are completed. According to the invention, the sowing grain hole falling condition in the sowing process can be accurately detected in real time, the non-sowing position and the sowing quantity are fed back, and the sowing precision and efficiency are improved.

The application relates to the technical field of video object tracking, and proposes a video object tracking trajectory generation method, an electronic device and a program product. The method comprises the following steps: after completing a video object tracking task, obtaining frame-by-frame detection results of the video object tracking task, wherein the frame-by-frame detection results comprise object detection boxes contained in each video frame of a video file respectively, and object names corresponding to each object detection box respectively; converting the frame-by-frame detection results into trajectory results aggregated according to the object names and sorted according to frame numbers, wherein the trajectory results comprise arrangement trajectories of all object detection boxes corresponding to each object name in turn appearing in each video frame of the video file. By using the method, the frame-by-frame detection results output by a video object tracking algorithm can be automatically converted into object trajectory results required by a business layer, so that the business layer can carry out subsequent object retrieval, display and evidence association and the like.

The application provides a method for tracking and counting oil pipe materials, which comprises the following steps: S1, preprocessing and data enhancement processing are performed on pre-acquired images of different types of oil pipe materials, and an oil pipe material target detection model for detecting oil pipe materials is constructed and trained; S2, the oil pipe materials in an oil pipe material video are identified through the oil pipe material target detection model, and each oil pipe material is given a unique ID tag according to the identification result, and the oil pipe materials are counted and tracked according to the ID tags by using a multi-frame cooperative unified calculation algorithm. The application also provides an electronic device. The application gives each oil pipe material a unique ID tag by using a target tracking algorithm, realizes accurate detection and tracking of oil pipe materials, and effectively solves the situation that a single frame of picture cannot contain all oil pipe materials laid on the ground by using a multi-frame cooperative unified calculation algorithm, realizes accurate counting of oil pipe materials, and is more in line with actual application requirements.

This invention provides an RSU-based signal anomaly detection device and method that uses a multi-object tracking algorithm to determine whether fluctuations are natural phenomena or the result of a spoofing attack. [Solution] Combined voxel data is generated by combining voxel data from lidar and radar installed at a roadside base station and 3D feature vectors from multiple cameras installed at the roadside base station, with voxels at corresponding locations. Based on the combined voxel data, the voxel at the first location where the fluctuation is detected is masked. The vectors for the masked voxel and the remaining voxels other than the masked voxel are input to a neural network to obtain predicted point information for the masked voxel. Based on the predicted point information for the masked voxel and the lidar voxel data, it is determined whether the fluctuation detected at the first location is due to abnormal activity.

The invention discloses a smoke and fire detection method and device based on a video sequence, and relates to the related field of computer vision, and the method comprises the steps: carrying out the target detection processing of a single-frame image in a video stream, and obtaining a detection frame set containing a smoke and fire potential region; for each potential smoke and fire area in the detection box set, processing continuous multi-frame images of the video stream based on a target tracking algorithm, and generating a plurality of smoke and fire trajectories representing the motion state of the potential smoke and fire area; and on the basis of the plurality of smoke and fire tracks, intercepting a corresponding continuous image sequence from the video stream to construct a video sequence sample, and processing the video sequence sample by using a pre-trained sequence classification model to obtain a judgment result of whether the video sequence sample is a real smoke and fire phenomenon. The technical problems that an existing smoke and fire detection method is high in false alarm rate and insufficient in dynamic smoke and fire characteristic recognition are solved, and the technical effects of reducing the false alarm rate and improving the accuracy of real smoke and fire dynamic behavior recognition are achieved.

The invention belongs to the field of traffic signal control, and relates to a traffic signal optimization method based on model predictive control and trust region Bayesian optimization. The method comprises the following steps: firstly, based on intersection video data, using a target detection and target tracking algorithm to realize automatic collection of traffic flows in different turning directions; then designing a road section flow and intersection steering ratio estimation method based on a traffic flow theory based on three kinds of heterogeneous data including radar data, video data and map data; and finally, establishing a microscopic traffic simulation model based on a traffic state reconstruction result, designing a traffic signal optimization combination framework based on centralized model predictive control and trust region Bayesian optimization, and solving a real-time optimal regional traffic signal timing scheme according to the dynamic change of traffic flow. The vehicle average delay in the network can be effectively reduced, and high efficiency and expandability are achieved when the problem of large-scale signal optimization is solved.

This invention discloses a method, system, and device for resource identification of roller-compacted concrete dam surfaces based on YOLOv10: The method involves acquiring a real-time video stream of the roller-compacted concrete dam surface; standardizing and enhancing each frame after frame decomposition to obtain enhanced surface images; defining resource target identification categories for the roller-compacted concrete dam surface, refining the surface images to obtain labeled images, and constructing a dedicated dataset for roller-compacted concrete dam surface resources; building and training a deeply optimized roller-compacted concrete dam surface resource identification model using the YOLOv10 model; using this model to infer the real-time video stream of the roller-compacted concrete dam surface, and post-processing the inference results using a spatiotemporally correlated target tracking algorithm to obtain structured resource information. This invention, through deep optimization of the YOLOv10 framework, specifically addresses the challenges of resource identification under multi-scale, dense occlusion, and strong background interference in RCCD surface scenarios, thereby achieving automated, accurate, and real-time monitoring of all construction elements.

This invention discloses a high-speed pose detection method based on vision optimization. First, a QR code marker is affixed to the target to be detected, and a target tracking algorithm is used to locate the region of interest (ROI) where the target is located. Second, an image segmentation algorithm is used to segment the image within the ROI to extract the QR code markers. Finally, a global coordinate transformation model of the scene is constructed, and the pose information is calculated using the PnP algorithm based on the pixel coordinates of the QR code markers. The pose detection method proposed in this invention has high detection accuracy, good real-time performance, and high detection success rate and speed.

The application discloses a video monitoring method and device. The method comprises the following steps: collecting a video frame image of a pan-tilt camera in a current visual angle range at each collection time; analyzing the video frame image by using a multi-target tracking algorithm to obtain a first position detection box of each to-be-tracked object in the video frame image at the current collection time and a first position prediction box of each to-be-tracked object at a next collection time; determining a target visual angle range comprising each first position detection box and each first position prediction box; and adjusting the current visual angle range of the pan-tilt camera to the target visual angle range by adjusting the rotation angle and / or focal length of the pan-tilt camera. The application solves the technical problem that the camera lacks flexibility in collecting video and the target tracking effect is poor in the related video monitoring scheme.

This invention proposes a method for identifying and monitoring the tail-wagging state of passenger luggage in transportation hubs. The method includes the following steps: setting up monitoring cameras and loudspeaker alerts in densely populated areas of the transportation hub; activating the monitoring cameras to capture video frames and providing them to a monitoring processor; the monitoring processor calculating the angular force, rate of change of center of mass distance, and angular velocity of the luggage in the monitored area using single-target tracking algorithms MMTrack and findContours, respectively; and detecting the tail-wagging state of the luggage based on a luggage tail-wagging state identification model. This invention identifies the motion characteristics of the luggage throughout its entire motion and can predict its subsequent motion state. Based on the identification results, timely warnings can be issued, effectively avoiding potential hazards caused by luggage tail-wagging, which is of great significance for safety management in densely populated transportation hubs.

A method for tracking identical objects within an image performed on a computing device of the present invention may include: detecting an object within an image and generating object detection data corresponding to the detected object; tracking each object within the image based on an object tracking algorithm and generating tracklet data for the movement path of the tracked object; and grouping the tracklet data of objects determined to be identical objects to map a unique identification code. The present invention identifies each identical object by assigning a unique identification code, thereby allowing the user to quickly search for tracked images using the unique identification code and verify the movement path of a specific object.

The application provides a real-time single-target long-time tracking method, comprising the following steps: step 1, obtaining a current image frame, selecting a template in a template library to determine a tracked target; matching the image frame with the tracked target to detect whether the target exists in the image frame, if the target exists, entering step 2, if the target does not exist, re-detecting; step 2, tracking by using an FDSSST target tracking algorithm, when the output confidence is greater than or equal to a set target confidence threshold value, considering that correct tracking is achieved, entering step 3; otherwise, considering that tracking fails, entering step 1 to detect a next image frame; step 3, judging whether deviation occurs according to the feature similarity of the target in adjacent two image frames, if the deviation does not occur, updating the target template in the template library, otherwise, re-selecting the template to re-detect the target in the current image frame. The application combines a deep learning algorithm with a filter algorithm, improves the accuracy and success rate of target tracking, and also guarantees the timeliness of tracking.

An automatic control system for a cabin hatch cover comprises a hatch cover control module, a personnel detection module and a data processing and display module. The hatch cover control module comprises a servo motor, a gear rack mechanism and an infrared sensor array; the personnel detection module comprises an infrared thermal imager and an AI visual unit, the infrared thermal imager is used for scanning a cabin area in real time and counting the number of personnel, the AI visual unit carries a high-definition camera and an edge computing device, personnel identities are confirmed through a face recognition technology, personnel coordinates are positioned in combination with an object tracking algorithm, and personnel detection and positioning are carried out. According to the automatic hatch cover control system, automatic hatch cover control is achieved, operation steps are simplified, the stability and accuracy of hatch cover opening and closing are improved through cooperation of a servo motor and a gear and rack mechanism, meanwhile, clamping accidents are effectively avoided through an infrared sensor array, and the safety risk is reduced; hatch cover control and personnel monitoring data are integrated, information islands are broken, and data analysis of a central processing unit and visual display of a display screen are carried out.

The invention provides a domestic SOC-based efficient target tracking algorithm implementation method, which is characterized in that a key calculation module of a KCF algorithm is implemented at a programmable logic (PL) end through an FPGA (Field Programmable Gate Array), including operations such as fast Fourier transform (FFT), kernel correlation calculation and inverse transformation, and meanwhile, a combinable image operator strategy is adopted at a PS (Packet Switching) end; and feature extraction and filtering parameters are dynamically adjusted according to different scenes, so that the tracking precision and robustness are improved. Compared with traditional CPU or GPU-based software implementation, the method has remarkable advantages in the aspects of power consumption, speed and system integration, and is particularly suitable for a localized embedded visual system and a tracking scene of a real-time target.

The application provides an FTIR ship exhaust remote sensing detection method based on YOLOv8 and SORT target tracking, comprising the following steps: collecting ship video stream data in real time; inputting the ship video stream frame by frame into a YOLOv8 target detection model for feature extraction, obtaining an optimal target detection frame, and obtaining a ship target position; synchronizing the ship target position information and the detection frame information detected by the YOLOv8 to a SORT target tracking algorithm, predicting the ship target motion trajectory through a Kalman filter, realizing cross-frame target association in combination with a Hungarian algorithm, and obtaining a tracking result; based on the tracking result, inferring a ship exhaust area plume area, controlling an FTIR holder to scan the plume area, and obtaining an interference graph; performing Fourier transform and quantitative calculation on the interference graph, outputting exhaust concentration after removing background concentration; and according to the sulfur-carbon ratio in the exhaust concentration, whether the sulfur content of the crude oil of the ship exceeds the standard is inversely deduced.

The application discloses a kind of fish fry dynamic technical method, system based on computer vision, related to image processing technical field, the visible light video data of fish fry group and multispectral image data are synchronously collected;The visible light video data and multispectral image data are fused and analyzed, and individual fry is identified and associated in time sequence;Kinematics features extracted from the visible light video data and spectral reflection features extracted from the multispectral image data are cooperatively encoded, and the encoding result is obtained.The application establishes multi-modal feature vector for each individual, which fuses motion representation and intrinsic physiological spectral information.Even when the individual motion trajectory mutates or is temporarily lost, its unique spectral features can serve as a stable identity auxiliary identifier.Combined with the appearance matching mechanism in multi-target tracking algorithms, the continuity of ID can be effectively maintained, significantly reducing the probability of losing or misidentifying individuals in complex and highly dynamic aquaculture environments.

The invention relates to the field of psychological analysis, in particular to a multi-source data acquisition method for sand table psychological assessment, which comprises the following steps: firstly, acquiring multi-source data and marking a timestamp, then extracting a person and a moving track thereof by using a multi-target tracking algorithm, positioning a face area and matching person information; the method comprises the following steps: constructing an expression extraction model and an expression recognition model, recognizing an expression sequence based on the expression extraction model and the expression recognition model, ensuring the synchronism of multi-source data in time and space through data alignment, finally constructing a multi-modal fusion model by using deep learning, integrating the multi-source data, and judging whether data acquisition fusion is qualified based on the sum of key principal component interpretation ranges. And relevant parameters are corrected according to abnormal reasons when the product is unqualified. The acquisition method provided by the invention effectively solves the problem that the existing method is insufficient in data acquisition precision in a multi-person entity sand table scene, provides more accurate data support for sand table psychological assessment, and remarkably improves the accuracy of data acquisition.

The invention discloses an improved target tracking method, system and device and a medium, and relates to the technical field of target tracking, and the method comprises the steps: optimizing an appearance feature extraction module of a multi-target tracking algorithm BYTETRACK through a feature recognition model OSNet, and obtaining an improved target tracking method STYOLOTRACK; and tracking the target by using the STYOLOTRACK according to the video image data of the target to be tracked. According to the invention, the tracking effect of target tracking can be enhanced.

The invention belongs to the technical field of airport production and operation, and discloses a tracking and expelling method and system for preventing runway intrusion based on a millimeter wave radar. The method comprises the following steps: carrying out intrusion early warning and alarm area setting of the millimeter wave radar, and judging an occurred intrusion early warning event; reminding of departure of related vehicles and personnel is carried out; determining intrusion information and preparing related expelling measures in advance; analyzing and judging the runway intrusion event by using a multi-target tracking algorithm MOT; and carrying out comprehensive research and judgment. According to the invention, the intrusion condition of the runway is effectively monitored by using a millimeter wave radar technology, the specific conditions of vehicles and personnel entering the runway are judged in an auxiliary manner by combining a camera video technology, flight data and the like, the intrusion path can be effectively tracked through radar data, and the intruded vehicles or personnel are repelled by using broadcast and communication equipment around the runway, so that the safety of the runway is improved. Management personnel are assisted to effectively manage and control running safety of the runway.