128 results about "Camera tracking" patented technology

The invention discloses an MViT-based dense visual field reconstruction method and system, and the method is realized based on a monocular ViMGS-SLAM framework, and comprises the steps: inputting a to-be-reconstructed image into the monocular ViMGS-SLAM framework, and carrying out the depth estimation of a monocular RGB image through a cross-scale attention mechanism in an MViT module; in the 3D Gaussian representation module, re-parameterization processing is carried out on the monocular RGB image based on the estimated depth image to obtain a 3D Gaussian body; based on the monocular RGB image and the depth image, performing camera pose optimization in a camera tracking module; key frame selection is carried out in a key frame management module based on the obtained camera pose information and the 3D Gaussian body; and on the basis of the key frame information and the 3D Gaussian volume, generating new view rendering through isotropic regularization in the mapping module, and realizing dense visual field reconstruction. According to the method, real-time high-precision 3D reconstruction of monocular RGB input is realized.

The invention relates to a semantic simultaneous localization and mapping method and system based on Gaussian splashing. The method comprises the following steps: firstly, collecting a frame of RGB-D image, modeling a scene into a 3D semantic Gaussian field containing a plurality of 3D semantic gausses according to the RGB-D image, and rendering the 3D semantic gausses by using a tile rasterization technology to obtain 2D image plane gausses; rendering results of RGB color, depth and semantic features are extracted from the 2D image plane in a Gaussian mode, and the semantic features are decoded into semantic tags; constructing a mapping and tracking loss function by using an RGB color rendering result, a depth rendering result, a semantic tag and a truth value, and jointly optimizing a camera pose and a semantic Gaussian field based on a tracking stage and a mapping stage; and repeating the steps for each new frame of RGB-D image to complete the construction of the incremental semantic Gaussian map. Compared with the prior art, the method has the advantages of realizing robust camera tracking, real-time high-quality rendering, accurate 3D semantic reconstruction and the like.

The invention relates to a high-definition monitoring camera tracking method and system for multi-angle face detection. The method comprises the following steps: preprocessing an original image collected by a high-definition monitoring camera to obtain a first preprocessed image and a second preprocessed image; performing feature extraction and feature fusion on the first preprocessed image and the second preprocessed image to obtain a multi-scale fusion feature map; face positioning and posture analysis are carried out through a position sensitive convolutional network, and a face detection result is obtained; performing face region subdivision and angle characteristic analysis on the face detection result to obtain enhanced face representation; and calculating a cross-camera matching cost matrix based on the enhanced face representation, and performing trajectory prediction and updating processing to obtain a face tracking result in the multi-camera environment. According to the method, the capability of capturing facial micro-expressions and fine features is improved, high-precision face association and smooth trajectory handover among different cameras are realized, and the problem of trajectory fragmentation in view crossing areas of the cameras is solved.

The invention discloses a long-distance identity recognition method for a large area, which belongs to the technical field of computer vision and comprises the following steps: S1, initializing a system; s2, collecting video data; s3, pedestrian detection and segmentation; s4, performing gait recognition; s5, multi-target cross-camera tracking is carried out; and S6, result output and application service. According to the invention, an effective solution is provided for large-scene video intelligent security and protection in a complex environment of a park, the accuracy and traceability of personnel identity recognition in a high-risk area are ensured, and the safety production level of the park is improved; a long-distance multi-target identity recognition scheme is provided, real-time monitoring and early warning of illegal person invasion in key protection areas are achieved, and reliable safety guarantee is provided for public places.

The invention discloses a communication optical axis autonomous correction method based on tracking point nutation, which comprises the following steps: controlling a fine-following fast reflector to scan, monitoring the output power of an erbium-doped fiber amplifier (EDFA) within scanning residence time, searching the position of the maximum power by adopting a sliding window average algorithm, and recording the position; and after scanning for one period, returning to the tracking point with the maximum recorded power, thereby realizing rapid and accurate calibration of the tracking optical axis of the laser communication terminal. According to the invention, a closed loop is formed based on tracking point nutation and a pre-amplification output signal, so that high-precision correction of a camera tracking point is realized, the stability of precise tracking of the system can be improved, and the signal-to-noise ratio received by the laser communication system can also be improved; the traditional receiving optical axis calibration convergence speed and precision are improved; higher real-time performance and automation degree are achieved, relevant data can be acquired and processed in real time, and correction of a receiving optical axis is achieved; the method has wide applicability and expandability, and can be applied to other spacecraft systems needing high-precision tracking control.

The invention relates to a night vehicle cross-camera trajectory tracking method. The method comprises the following steps: acquiring video data information of a plurality of night road cameras; a multi-scale fusion feature map is obtained; an MCAM-YOLO network model is constructed, each vehicle is detected, and a detection result is obtained; obtaining the track of the detected vehicle; obtaining a unified global track ID obtained through matching under different cameras; and outputting a video stream with the detection frame, the trajectory and the vehicle information. According to the invention, cross-camera trajectory tracking of the night vehicle is realized, the vehicle can be accurately detected in the night environment by generating multi-scale fusion of the daytime data and the night data and combining the MCAM-YOLO network model, cross-camera trajectory tracking is realized, the defects in the aspect of cross-camera tracking at night in the prior art are effectively made up, and the method and the device have the advantages of being high in practicability and the like. And the night vehicle management capability in intelligent traffic is greatly improved.

A system for robot-assisted surgery includes a surgical robot having a robotic arm, an end effector coupled to the robotic arm, wherein the end effector is adapted to receive, translate, and orient a navigated surgical instrument; a camera tracking system adapted to intra-operatively track a pose of the navigated surgical instrument relative to a defined coordinate system; and a computer platform including a processor and a memory. In embodiments, the computer platform operative to display to a user an image of a target location on the patient and the pose of the navigated surgical instrument; and selectively control translation and orientation of the navigated surgical instrument based on a defined operational mode, to perform a surgical process under user control that comprises one or more of: reaming an acetabulum of the patient to a planned center of an acetabular prosthesis, or positioning the acetabular prosthesis in the reamed acetabulum.

The invention discloses a multi-camera collaborative pedestrian and vehicle cross-view tracking method and system, and relates to the technical field of intelligent monitoring. The method comprises the following steps: carrying out video stream acquisition on a monitoring area to obtain a multi-view video data set; multi-target detection of pedestrians and vehicles is carried out, tracking is carried out according to a plurality of detection targets, and a local tracking trajectory set of a plurality of cameras is generated; carrying out collaborative analysis on the plurality of cameras, constructing a multi-camera collaborative strategy to carry out cross-view trajectory matching on the local tracking trajectory set, and generating a global tracking trajectory set; and updating target states of the plurality of detection targets according to the global tracking trajectory set, and generating a multi-target cross-view tracking result of the pedestrian and the vehicle. The technical problem that in the prior art, information of different visual angles is difficult to integrate effectively in a multi-camera scene, so that target loss and track discontinuity easily occur in cross-camera tracking of pedestrians and vehicles is solved, and the technical effect of improving the continuity and accuracy of cross-camera tracking is achieved.

Conferencing systems and methods configured to generate true talker coordinates for use in camera tracking of talkers and objects in an environment and other room intelligence use cases are disclosed. The initial configuration and ongoing usage of conferencing systems can be improved by detecting and converting the locations of objects and talkers in an environment into a common coordinate system. The amount of time and effort by installers, integrators, and users, can be reduced leading to increased satisfaction with installation and usage of the conferencing system.

The invention discloses a double-layer dynamic probability SLAM (simultaneous localization and mapping) method for high-fidelity mapping in a dynamic environment, and belongs to the technical field of dynamic three-dimensional map building and positioning. The method comprises the following steps: a camera tracking module performs pixel-level dynamic probability estimation on input continuous image frames by using optical flow information and semantic tags, and optimizes and solves the camera pose of each frame of image through a probability weighting mechanism; the map building module converts the two-dimensional image into a three-dimensional map according to the camera pose of the frame, calculates the three-dimensional dynamic probability of each object in the image based on the two-dimensional dynamic probability graph of the frame, removes the object judged to be dynamic from the map, corrects the dynamic probability of the object in the image based on a feedback mechanism of a static map, and sends the corrected dynamic probability to the camera; and correcting and complementing the semantic tag of the object. According to the method, the adaptive capacity of a system to a dynamic scene can be remarkably improved, the dynamic artifacts are effectively eliminated while the tracking stability is ensured, and a static map reconstruction result with higher fidelity is obtained.

The invention discloses a single-wheel self-balancing rail inspection device and method based on sound detection. The single-wheel self-balancing rail inspection device comprises a single-wheel self-balancing rail inspection device body and a server terminal. The single-wheel self-balancing track inspection device is placed on a rail, the posture and the balance state of the inspection device are detected through a gyroscope in the moving process, a rail image is recognized through a tracking camera, and the single-wheel self-balancing track inspection device is controlled to keep a self-balancing state so as to perform tracking movement along the single rail. In the moving process, the rail is knocked at fixed time or fixed distance, sound is collected, sound data is transmitted to the server terminal for real-time sound detection, and the working condition of the rail is distinguished according to sound classification. According to the invention, the inspection device is driven by means of camera tracking, self-balancing control and single-wheel advancing, so that the inspection device can walk on a single rail and can be kept stable; meanwhile, sound generated by knocking the rail is collected, the sound is detected through a machine learning or deep learning method, the sound is recognized in a multi-classification mode, the rail working condition is judged, and sound-based rail abnormal working condition detection is achieved.

The invention relates to the technical field of computer vision and artificial intelligence, and discloses a public area pedestrian trajectory monitoring system based on cross-camera tracking and hybrid simulation completion. The system comprises a camera array module, a pedestrian detection and cross-camera tracking module, a monitoring blind area information base module, a hybrid drive pedestrian simulation engine module, a track fusion and complementation module and a simulation integration propulsion module. According to the invention, monitoring blind area tracks can be effectively filled, track continuity and prediction accuracy are improved, existing hardware is fully utilized to reduce cost, and modular design is easy to integrate and convenient to use. The generated complete track can be widely applied to scenes such as public safety monitoring, passenger flow analysis and emergency evacuation plan making in public places such as ports, subway hubs, cruise ship wharfs and commercial complexes, and supports a real-time monitoring or post-analysis mode.

The invention relates to the field of computer vision and navigation, and provides an SLAM acceleration method based on three-dimensional Gaussian rendering, and the method comprises the steps: initializing a three-dimensional Gaussian point cloud and a camera pose parameter based on input data, executing the camera tracking of a target frame in the input data, optimized camera pose parameters are output based on a staged switching strategy and an iteration mechanism, and camera tracking utilizes a floating point format with reduced precision; and executing a hierarchical screening mechanism in the optimized camera pose parameter to determine a key frame from the color image and the depth image, and performing mapping through a renderer supporting multichannel data by using the key frame and the optimized camera pose parameter to update the three-dimensional Gaussian point cloud. According to the method, through staged switching and iteration, pose optimization can be rapidly converged, a precision reduction floating point format is used, the numerical processing burden is relieved, a layered screening mechanism can be used for reducing the calculation cost lower than that of frame-by-frame fine comparison, and then the problem that the efficiency of an SLAM process is low is solved.

Methods provide computer-navigation assisted total hip arthroplasty (THA) procedures. Such procedures include the use of a navigated instrument, e.g., a navigated reamer construct or a navigated inserter construct to prepare the acetabulum and insert an acetabular shell, a camera tracking system adapted to track a pose of the navigated inserter or reamer construct relative to the patient in use, and a computer platform adapted to receive pose tracking information and generate and display navigational guidance for the user.

A production process involves predetermined number of cameras simultaneously filming a background at predetermined angles, and filming actors in a studio with the same number of cameras and the same angles, used in conjunction with a virtual studio system. In studio, the actors perform before a green screen and the virtual studio system composites the actors onto the background in real-time. Camera tracking allows the in-studio cameras to pan, tilt, focus, zoom, and make limited other movements as the virtual studio system adjusts display of the background in a corresponding manner, resulting in a realistic scene without transporting actors and crew to the background location.

Conferencing systems and methods configured to generate true talker coordinates for use in camera tracking of talkers and objects in an environment and other room intelligence use cases are disclosed. The initial configuration and ongoing usage of conferencing systems can be improved by detecting and converting the locations of objects and talkers in an environment into a common coordinate system. The amount of time and effort by installers, integrators, and users, can be reduced leading to increased satisfaction with installation and usage of the conferencing system.

This application provides a camera tracking control system and intelligent care device, belonging to the field of intelligent elderly care technology. The system includes a motion drive module, a posture sensing module, a face recognition module, and a controller communicating with these three modules. The posture sensing module outputs corresponding drive signals based on the left and right displacement of the human body. The face recognition module outputs a stop signal after recognizing a face. The controller drives the camera to adjust its position according to the human body's movement, locking and recording upon face recognition. The camera tracking control system and intelligent care device provided by this invention can achieve fully automatic tracking and recording of the elderly, solving the problem of blind spots that are common with fixed cameras, effectively improving the reliability of home-based elderly care, and reducing the cost of manual care.

A surgical system for computer-assisted navigation during a surgical procedure includes at least one processor that obtains a 3D radiological representation of a target anatomy of a patient and a fiducial set of a registration fixture. An attempt is made to register a position of the fiducial set in the 3D radiological representation to a 3D imaging space tracked by a camera tracking system. Based on a determination that one fiducial of the fiducial set has an unsuccessful registration to a position of the 3D imaging space, the following operations are performed: displaying at least one view of the 3D radiological representation having a graphical overlay indicating that the fiducial has an unsuccessful registration to the 3D imaging space; receiving user-provided position information identifying where the fiducial is located in the 3D radiological representation; and registering the position of the fiducial to the 3D imaging space based on the user-provided position information.

The application discloses a multi-sensor fusion SLAM positioning method based on a direct method, and relates to the field of mobile robot positioning and navigation. The direct method is used for camera tracking by using the pixel point information with obvious gradient in an image, IMU pre-integration information is used as an initial pose, and the direct method is provided with an initial value. According to whether tracking is successful, the image frame is divided into a key frame and a non-key frame. A visual factor graph is constructed, an IMU residual term and a GPS residual term are inserted into the visual factor graph to construct a new fusion factor graph, and the optimization process of the system algorithm is completed through fusion factor graph optimization. A rear-end optimization strategy based on a sliding window optimization is used, the calculation complexity of rear-end pose optimization is fixed, a multi-sensor tight coupling fusion strategy is used, the advantages of marginalization are retained and the defects of marginalization are made up by using old information, and the system accuracy is improved. The system can work in a pure vision mode. Even if a GPS signal cannot be normally received, the system can continue to work in a vision inertial odometer mode.

The invention discloses a three-dimensional scene real-time reconstruction method fusing a symbol distance field and three-dimensional Gaussian representation. The method comprises the steps of firstly receiving a color-depth frame captured by a camera, obtaining a camera pose of a current frame through camera tracking estimation, then fusing and updating color and depth information of the current frame and a global symbol distance field, adaptively adding, optimizing and removing three-dimensional gauss, and finally correcting the color of a symbol distance field rendering result, so as to obtain a target image. And the reconstruction reality sense is improved. According to the invention, through fusion of three-dimensional Gaussian and symbol distance field representation, high-quality scene reconstruction can be realized by using a symbol distance field and a small amount of three-dimensional Gaussian, ultra-high-speed real-time reconstruction of a three-dimensional scene is realized, and high-precision geometry and high-quality textures are kept at the same time.

The present invention provides a system for monitoring and improving toothbrushing effectiveness. The system comprises a camera device comprising a camera or similar visual sensor configured to capture real-time footage of a user brushing their teeth an AI-powered software module is designed to analyse the footage using object recognition, pose estimation, and motion tracking algorithms to detect the user's hand, toothbrush, and face, a feedback device that comprises a feedback interface that provides real-time visual, auditory, or haptic feedback based on brushing technique, including parameters such as angle, coverage, and movement speed and movement patterns. Wherein the feedback provided comprises instructions to the user to alter their toothbrushing technique to bring the parameters closer to a predetermined set of ideal values. Thereby providing a system operates independently of sensors, accelerometers, or physical markers embedded in or attached to the toothbrush.

The invention discloses a semantic 3D Gaussian sputtering SLAM (Simultaneous Localization and Mapping) method based on illumination invariance. The method comprises the following steps: step 1, performing 3D Gaussian-based scene representation and joint micro-rendering on a to-be-constructed target area to obtain a multi-dimensional rendered initial scene model; 2, an internal appearance normalization IAN module is constructed, and decoupling of internal attributes of an initial scene model and transient illumination is achieved; 3, performing offset correction on a radiation field of a rendering graph in the initial scene model, and designing DRB-Loss loss to dynamically adjust correction intensity; step 4, through camera tracking optimization, combining a stable map and exposure compensation to realize robust pose estimation, and through double-stage key frame screening, improving SLAM system efficiency; step 5, constructing joint map loss, and optimizing all parameters of the 3D Gaussian primitive; and map updating is completed, invalid 3D Gaussian primitives are pruned, and a complete synchronous positioning and map building cycle is formed.

The invention provides a television program shooting system and method. The television program shooting system comprises a rendering display subsystem, a shooting synthesis subsystem and a director subsystem, wherein the rendering display subsystem comprises a large screen, a rendering server and a large screen processor; the shooting synthesis subsystem comprises a plurality of cameras, a camera tracking device and a synthesis server; the camera tracking device acquires camera tracking data, the rendering server forms a rendered image in real time according to the camera tracking data, and the large screen processor processes the rendered image and outputs the rendered image to the large screen for display; the camera captures a real image; the synthesis server expands the virtual scene outside the large screen of the real image to generate a synthesis image; and the video switching equipment switches and selects the composite image, and triggers the rendering server to perform camera position switching. And the video switching table switches the synthesis server to trigger the machine position switching of the rendering server, so that the technical problem of relatively poor support of multi-machine position switching of television program shooting in the prior art is solved.

Paving machines and paving machine control systems utilize sensors to identify the location and orientation of paving machines and corresponding attachments. The control system implements a design profile by automatically adjusting actuators. The control system receives transition values to calculate a smooth transition including continuously adjusting actuator values with reference to the location and orientation of the paving machine. The control system may identify resurfacing values to repair a damaged surface by identifying an offset value of an existing surface to an ideal surface with reference to a disposition of the paving machine to minimize material usage.

The application relates to the technical field of computer vision, and discloses a vehicle cross-camera tracking method and system based on a twin network, which comprises the following steps: collecting a track segment of a target vehicle under a camera; performing Kalman filtering on the track segment to obtain a motion state sequence, performing time series interpolation on the motion state sequence to obtain a speed fluctuation curve; constructing a directed connected graph based on the layout characteristics of the camera, mapping the speed fluctuation curve to the directed connected graph to obtain a topological behavior correlation graph of the target vehicle; jointly encoding the speed fluctuation curve and the topological behavior correlation graph to obtain a behavior feature vector of the target vehicle, and inputting the behavior feature vector into a twin network to obtain a behavior consistency score of the target vehicle; and associating the identity of the target vehicle based on the behavior consistency score, and determining that the target vehicle is the same target vehicle if the behavior consistency score is greater than a preset association threshold; and the application can improve the accuracy and robustness of vehicle cross-camera tracking.

A handheld three-dimensional (3D) measuring system is tracked using at least two camera tracking systems. Each camera tracking system has at least one motorized axis of rotation. The camera tracking systems use cameras to accurately measure the pose of the 3D measuring system based the position of visible targets on the 3D measuring system and the rotated angle of each camera tracking system.

The invention relates to the technical field of high-speed shooting, and discloses a method for automatically tracking and switching a camera in a long-distance high-speed object moving process. The method comprises the steps that the running speed and the running position of an object are acquired in real time; the method comprises the following steps: calculating the switching offset of a camera currently in a display state according to the running speed of an object, and judging whether a camera switching opportunity is met or not according to the running position of the object, the switching offset of the camera, the position of the camera currently in the display state and the position of a next to-be-displayed camera; and when the camera switching opportunity is satisfied, the corresponding camera is controlled to be switched to a display state. Therefore, the effect of fast switching without the black screen can be achieved, and the method can adapt to the scene of long-distance multi-camera tracking shooting.

A surgical system for computer assisted navigation during surgery, includes at least one processor that obtains a 3D radiological representation of a targeted anatomical structure of a patient and a set of fiducials of a registration fixture. The operations attempt to register locations of the set of fiducials in the 3D radiological representation to a 3D imaging space tracked by a camera tracking system. Based on determining one of the fiducials of the set has a location that was not successfully registered to the 3D imaging space, the operations display at least one view of the 3D radiological representation with a graphical overlay indicating the fiducial has not been successfully registered to the 3D imaging space, receive user-supplied location information identifying where the fiducial is located in the 3D radiological representation, and register the location of the fiducial to the 3D imaging space based on the user-supplied location information.

The invention provides a visual SLAM (Simultaneous Localization and Mapping) algorithm based on multi-scale neural tensor representation, which belongs to the technical field of indoor scene real-time reconstruction, and can efficiently capture the global structure and fine details of a scene by utilizing a tensor decomposition technology, and reduce the memory usage amount and the calculation overhead at the same time. In addition, the invention further introduces an efficient pixel-based color query method, and each pixel only needs neural network forward regression once in the method, so that the real-time performance of the neural radiation field-based SLAM (Simultaneous Localization and Mapping) is further improved. Experiments on a synthetic data set and a real data set show that the method is superior to the most advanced method in the aspects of reconstruction quality and camera tracking precision, and the efficiency in the aspects of running time and memory use is very high.

The present invention discloses a multi-twin adversarial network cross-camera vehicle tracking method for coupling platoon following enhancement, including: training an object detection neural network and an image normalization adversarial network, which are respectively used for extracting object positions and image normalization; the multiple twins of the above networks are used for multi-threaded synchronous processing of multiple surveillance videos; extracting vehicle trajectories, obtaining vehicle platoon following motion characteristics and the morphological characteristics of each vehicle; dividing vehicle following states, and constructing a dynamic platoon feature extraction model; fusing vehicle motion, traffic state propagation and camera spatial distribution, establishing an iterative vehicle spatio-temporal prediction; fusing the dynamic platoon model and the morphological distribution characteristics of vehicles within the platoon, realizing cross-camera matching of platoon groups under multiple surveillance; and sequentially tracking and numbering individuals within the dynamic platoon to complete vehicle cross-camera tracking. The adversarial network excludes background and perspective interference, and the following characteristics and dynamic platoon model add stable spatio-temporal constraints for re-identification, greatly improving the re-identification effect.