14 results about "Feature tracking" patented technology

The application discloses a video instance segmentation method and system based on global feature enhancement, and belongs to the technical field of computer vision and deep learning, which comprises the following steps: inputting continuous video frames into a double-channel decoupling feature extraction module to obtain appearance and position features; inputting the two types of features into a tracker and a global feature memory updating module to dynamically update and obtain long-time sequence global context features; completing instance detection matching by the tracker, judging target state to obtain disappeared and newly appeared target queries; combining long-time sequence features to model current frame time sequence to generate enhanced features; finally, the tracker completes segmentation and tracking based on the enhanced features and the target queries, and outputs a segmentation mask sequence, an instance ID, a category ID and a tracking state. Through double-channel decoupling, double-memory block updating, multi-cost matching and multi-weight feature fusion, the application strengthens appearance feature representation and long-time sequence information utilization, and significantly improves segmentation accuracy and tracking robustness in complex scenes.

This invention discloses a real-time target tracking method for unmanned aerial vehicles (UAVs) based on asynchronous semantic correction. It employs a spatiotemporally decoupled architecture of a high-frequency geometric main thread and an asynchronous semantic correction thread. The main thread estimates the target's geometric state frame-by-frame using sparse feature tracking and filtering models, outputting a target prediction bounding box. The asynchronous thread calls a lightweight semantic segmentation model at low frequency according to trigger conditions to generate a target semantic mask and uses the motion trajectory within the delay period for spatiotemporal alignment compensation. The system performs dual reliability checks on semantic input and output, updating the target state through a hierarchical write-back mechanism. When the main thread's geometric propagation fails, an emergency fallback tracker takes over the output to ensure tracking continuity. This invention enables category-independent, real-time, robust target tracking in open scenes on edge platforms.

This invention relates to direct scale level selection for multi-level feature tracking. A method for mitigating motion blur in a visual-inertial tracking system is described. In one aspect, the method includes: accessing a first image generated by an optical sensor of the visual tracking system; accessing a second image generated by the optical sensor of the visual tracking system, the second image following the first image; determining a first motion blur level of the first image; determining a second motion blur level of the second image; identifying a scale change between the first and second images; determining a first optimal scale level for the first image based on the first motion blur level and the scale change; and determining a second optimal scale level for the second image based on the second motion blur level and the scale change.

Embodiments are disclosed for automatic display alignment using feature tracking. In some embodiments, a method comprises: capturing, with a first camera of a first display, a first image; capturing, with a second camera of a second display, a second image, where the respective fields of view for the first camera and the second camera are at least partially overlapped; transforming the first head pose into a first reference frame for the first display; transforming the second head pose into a second reference frame for the second display; generating a dual-display environment for the first and second displays based on the first and second head poses in the first and second reference frames, respectively; presenting a first portion of the dual-display environment on the first display; and presenting a second portion of the dual-display environment on the second display.

The present application belongs to the technical field of industrial automation and safety monitoring, and particularly relates to an industrial door anti-pinch safety early warning method based on video stream motion target detection, comprising the following steps: S1, collecting real-time video stream of an industrial door area, pre-processing and feature tracking the real-time video stream, mapping image coordinates to a world coordinate system, and obtaining real-time position parameters and motion speed parameters of a motion target; S2, calculating a radial approaching equivalent threat speed index according to the motion speed parameters of the motion target and the direction relative to the door body, the radial approaching equivalent threat speed index being used to represent the equivalent threat speed of the motion target sprinting towards the door body. The present application realizes differentiated and accurate response to high-speed forklifts and low-speed pedestrians by establishing a multi-dimensional dynamic collision risk model, and maximizes the passing efficiency of the industrial door under the premise of ensuring safety.

The present application belongs to the field of geological disaster monitoring and early warning, and discloses a landslide deformation monitoring method based on SAR image offset tracking and multi-stage filtering. The registered SAR image data set is divided into image pairs, the original offset field of each image pair is calculated by using the block phase cross-correlation algorithm, and the original offset field is comprehensively processed by multi-stage filtering based on correlation threshold and signal-to-noise ratio threshold filtering, median filtering, statistical aggregation, amplitude threshold filtering, vector consistency filtering and density clustering analysis, so that noise is effectively removed, systematic deviation is corrected, and real and coherent landslide deformation signals are refined, thereby providing a more accurate and reliable landslide deformation monitoring solution. The present application focuses on image pixel feature tracking and post-processing, integrates various technologies to filter noise step by step, can realize the identification and long-term dynamic monitoring of landslides, improves the accuracy and reliability of landslide monitoring, and provides technical support for preventing and controlling landslide disasters.

The application discloses a parking method based on a semantic topological map, and the method comprises the following steps: constructing a semantic topological map; in response to a trigger event of entering a satellite signal-free area, determining an initial pose of a vehicle in the semantic topological map through multi-modal feature recognition and fusion positioning; screening available parking spaces based on vehicle parameters, and performing physical pre-locking of the parking spaces in response to user selection; planning a semantic navigation path in combination with vehicle parameters and channel attributes, and performing navigation through segmented feature tracking and semantic steering guidance; performing parking confirmation and state resetting when the vehicle reaches a target parking space; and dynamically maintaining the semantic topological map based on crowd-sourced perception data. The application realizes accurate parking guidance in a satellite signal-free environment, avoids the problem of occupied parking spaces, and improves the adaptability and reliability of the parking process.

The application discloses a constraint visual servoing method and system based on imitation learning, and a device and a medium, and belongs to the technical field of visual servoing, and comprises the following steps: acquiring target object data, mechanical arm data and camera data, and establishing a target object model, a mechanical arm model and an image feature model; modeling the constraint of the mechanical arm through an imitation learning method, generating demonstration data, and generating demonstration trajectories by combining the demonstration data with an optimized trajectory generation strategy; calculating image feature tracking errors according to the demonstration trajectories, designing a cost function and a Hamilton function of the constraint visual servoing based on the image feature tracking errors, and obtaining an optimal control strategy and optimal control input of the mechanical arm through the Hamilton function; estimating the cost function by using a neural network estimator, obtaining an estimated value of the optimal control strategy, and updating the neural network estimator according to the Hamilton function. The application can generate a mechanical arm trajectory with optimal cost and smoothness without matrix inversion.

Embodiments are disclosed for automatic display alignment using feature tracking. In some embodiments, a method comprises: capturing, with a first camera of a first display, a first image; capturing, with a second camera of a second display, a second image, where the respective fields of view for the first camera and the second camera are at least partially overlapped; transforming the first head pose into a first reference frame for the first display; transforming the second head pose into a second reference frame for the second display; generating a dual-display environment for the first and second displays based on the first and second head poses in the first and second reference frames, respectively; presenting a first portion of the dual-display environment on the first display; and presenting a second portion of the dual-display environment on the second display.

The application discloses a logistics sorting main line control system with self-detection and fault positioning, and belongs to the technical field of automatic control of logistics sorting. A speed acquisition module collects real-time sorting speeds of each sorting station, and a difference calculation module generates a speed difference sequence of adjacent stations; an abnormality judgment module detects the speed difference sequence and marks a corresponding station interval as a suspected fault interval; a feature acquisition module reads the identification of a sorting product and a timestamp of passing through each station, a time interval calculation module tracks the same product and calculates an actual time interval between adjacent stations, a fault point determination module compares the actual time interval with a standard time interval, and determines a deviation starting station as a fault point; and an output module sends fault point position information to a monitoring terminal. The application combines speed difference conduction analysis with product passing time feature tracking, realizes automatic positioning of a fault interval on a sorting main line, and accurately identifies a fault point.