19 results about "Optical flow computation" patented technology

This invention relates to a bidirectional unsupervised method and system for calculating optical flow in an event camera. The method includes: acquiring a discrete event stream and converting it into forward and reverse event volumes through discrete sampling; extracting features using an optical flow computation convolutional network and enhancing features using a shift-window attention network; constructing a total loss function by combining bidirectional consistency loss, temporal consistency loss, image consistency loss, and smoothing loss; pre-training the optical flow computation convolutional network in an unsupervised manner using the total loss function, and then performing supervised fine-tuning training on a dataset containing real optical flow labels to obtain the final optical flow computation convolutional network. Based on the bidirectional losses for forward and reverse optical flow computation, unsupervised pre-training is achieved, and fine-tuning training is performed on existing real-world scene datasets, enabling the final optical flow computation convolutional network to achieve high-precision and robust event optical flow calculation.

This application provides a vehicle control method, device, storage medium, and vehicle terminal. The method includes: performing optical flow calculations on a first target image and a second target image using an optical flow algorithm to generate optical flow data; extracting at least one optical flow feature from the optical flow data; inputting the at least one optical flow feature into a deep learning model to generate a recognition result; generating a collision risk assessment based on the recognition result; generating a target driving strategy based on the collision risk assessment; and controlling vehicle driving based on the target driving strategy. This allows for the processing of image frames through optical flow calculations, enabling accurate calculation and evaluation of obstacle movement in continuous image data, effectively identifying and tracking dynamic obstacles in image sequences, providing crucial information for subsequent obstacle avoidance decisions, and quickly determining whether to take obstacle avoidance measures by combining the collision risk assessment of the obstacle and the current vehicle. This timely obstacle avoidance decision-making effectively avoids potential collisions and improves driving safety.

An add-on module for an injection device including a dispense indicator visible through a viewing window in a device housing and the housing defines a longitudinal axis for the injection device. The add-on module includes an optical flow sensor fixed to the add-on module and configured to track movement of the dispense indicator relative to the housing through the viewing window. A processor programmed to run an algorithm enabling optical flow computation from optical flow sensor data is provided, and the add-on module is adapted to be i) releasably attached to the housing and ii) axially and rotationally fixed to the housing when attached.

This application provides a stereo matching ranging method and system for dynamic occlusion scenes. The method includes: acquiring an image dataset and a point cloud dataset of a ranging area over a preset time period, and determining target image data; performing optical flow calculation on the target image data based on the image dataset to generate motion information of each pixel in the target image data; inputting the target image data into a preset convolutional neural network to determine several dynamic object regions; generating tilt support windows for each pixel based on the motion information of each pixel and each dynamic object region using a preset stereo matching algorithm, and then generating a disparity map corresponding to the target image data based on each tilt support window; and generating a corresponding complete depth map based on the disparity map, the image dataset, and the point cloud dataset using occlusion repair technology to determine the distance measurement value from each pixel to the subject being photographed.

The application provides an endoluminal surgery bleeding event detection method based on optical flow-color double-flow fusion and related devices. The method comprises the following steps: S1, acquiring an endoluminal surgery video frame sequence; S2, performing HSV color space conversion and red channel enhancement on each frame to obtain a color anomaly map; S3, performing dense optical flow calculation on adjacent frames to obtain an optical flow field; S4, performing double-flow fusion detection based on the color anomaly map and the optical flow field to obtain a bleeding candidate region; S5, performing time sequence persistence verification on the bleeding candidate region to obtain a time sequence stable bleeding region; and S6, outputting a bleeding event classification and a position coordinate based on the area and the diffusion speed of the time sequence stable bleeding region. The application also provides related devices corresponding to the method, and the related devices comprise devices, electronic equipment, computer readable storage media and computer program products.

This invention relates to an online monitoring and dosing control method for flocculant morphology based on optical flow and machine learning. The method comprises the following steps: S1. Acquiring and preprocessing the raw video stream; S2. Extracting static morphological feature vectors and dynamic rheological feature vectors in parallel using a dual-stream network, then adaptively weighting and fusing them through a feature fusion module to obtain a fused feature vector. The dynamic rheological feature vector is obtained sequentially through dense optical flow calculation, bubble interference suppression, and dynamic feature encoding; S3. Constructing and training a prediction model, inputting the fused feature vector obtained in S2 into the trained prediction model, and outputting the current predicted flocculation degree value; S4. Constructing and training a feedforward prediction module and a feedback correction module, calculating the feedforward dosing acceleration rate and feedback correction rate of the flocculant, and generating a final control signal to adjust the flocculant dosage. This method not only provides high-precision and robust real-time assessment of the flocculation state but also achieves advanced and stable dosing control based on prediction information.

The present invention is a method for calculating optical flow considering the relative speed of a processor, and may include the steps of acquiring driving images of the surroundings of a moving object as the moving object moves, acquiring camera movement speed data as the moving object moves, and calculating optical flow within the driving images based on the camera movement speed data.

The present invention provides an object detection method and object detection apparatus that can smoothly detect objects present around a vehicle using a particle filter. [Solution] Optical flow of objects surrounding the vehicle is obtained from images captured by the vehicle's imaging device, and particles with initial velocities based on the velocity of the objects calculated from the optical flow are generated at positions corresponding to the distance measurement points of the objects.

The present application relates to the technical field of weather forecast, and particularly relates to a sea fog forecasting method based on cloud life cycle, comprising the following steps: carrying out sea fog identification to obtain a binary grid field, and dividing a sea fog single cloud life cycle stage; carrying out multi-scale optical flow calculation on the binary grid field, outputting a sea fog field per-grid optical flow vector field, and extrapolating to obtain a sea fog advection forecasting field per hour in the future 6 hours; constructing a sea fog appearance and disappearance probability forecasting model per hour in the future 1-6 hours; deeply fusing the sea fog advection forecasting field and the sea fog appearance and disappearance probability forecasting model to obtain a sea fog forecasting grid field, and carrying out secondary revision; the present application integrates the cloud life cycle into the whole process of the sea fog 6-hour extrapolation forecasting, solves the inherent defects of the traditional extrapolation method that is only translation and does not appear and disappear, prolongs the effective sea fog forecasting time from 2-3 hours to 6 hours, and the per-hour forecasting can greatly improve the 6-hour forecasting accuracy, and can accurately forecast the sudden new sea fog and the rapidly dissipating sea fog which cannot be captured by the traditional technology.

The present invention provides an object detection method and an object detection device capable of distinguishing between moving objects and stationary objects. [Solution] The probability of an object being present in a defined section is calculated by dividing the area in front of the vehicle V1 in the direction of travel into a grid pattern, based on the positional information of the distance measurement points of objects present around the vehicle V1. Optical flow F of objects present around the vehicle V1 is obtained from the image captured by the vehicle V1's imaging device 12. A set of sections is generated by associating multiple sections based on the probability of occupancy and at least one of the speed and amount of movement of the object in the vehicle width direction in the image, calculated from the optical flow F.

A target tracking method, a target tracking system and an electronic device are disclosed. The target tracking method comprises: sequentially obtaining N frames of images. N is greater than or equal to 2 and is an integer. The target tracking method further comprises: performing target detection on the Nth frame of image to generate a target region; performing optical flow calculation and Kalman filtering prediction on the target region of the (N-1)th frame of image to respectively generate an optical flow predicted target region and a Kalman filtering predicted target region of the Nth frame of image; performing first matching on the target region and the optical flow predicted target region of the Nth frame of image; if the two do not match, performing second matching on the target region and the Kalman filtering predicted target region of the Nth frame of image which do not match; determining a prediction condition for the Kalman filtering predicted target region which does not match; if the prediction condition is met, updating the Kalman filtering model and performing optical flow point resampling by using the optical flow predicted target region of the Nth frame of image corresponding to the Kalman filtering predicted target region.

This application provides a radar echo extrapolation and thunderstorm / strong wind data processing method, apparatus, and electronic device based on optical flow, relating to the field of meteorological forecasting. The method includes: acquiring radar base data of a target area over a continuous historical period to generate a corresponding radar reflectivity factor image sequence; inputting the preprocessed radar reflectivity factor image into an optical flow calculation model to obtain a dense optical flow field; calculating the vorticity field and divergence field based on the dense optical flow field; stitching and fusing the radar reflectivity factor image, optical flow field, vorticity field, and divergence field at the same historical moment to form a multi-feature fused spatiotemporal sequence data; inputting the spatiotemporal sequence data into a pre-trained spatiotemporal sequence prediction model to output prediction results for a future preset time period; and generating and outputting a short-term thunderstorm / strong wind forecast product. This method can more accurately capture the nonlinear evolution of the micro-scale structure of thunderstorm / strong wind systems, significantly improving the accuracy of extrapolation forecasts.

The application belongs to the technical field of image processing, and provides an animation video frame rate adjustment method and system based on artificial intelligence, which comprises the following steps: obtaining an initial optical flow field through pixel-level optical flow calculation, combining optical flow amplitude and local spatial variance to calculate motion saliency features, generating a binary motion gating mask according to the motion saliency features, dividing a picture into a static background area and an effective motion area, generating corresponding intermediate frame pixels for the effective motion area by using a deep learning frame insertion network, not performing network reasoning for the static background area, directly mapping original image corresponding position pixels as intermediate frame pixels, finally splicing the pixels of the two types of areas, outputting a complete interpolation frame and inserting the original video sequence, and realizing frame rate improvement.

The present application relates to the technical field of medical image navigation, in particular to a lung nodule four-dimensional optical flow field real-time navigation system and method thereof, the system comprising a data acquisition module, a micro-region optical flow calculation module, a high-dimensional tensor analysis module, a nonlinear dynamics prediction module, a navigation fusion module and a surgical navigation module, the data acquisition module acquiring a CBCT image sequence and respiratory monitoring point motion information; the micro-region optical flow calculation module establishing a dynamic mapping relationship based on differential topology principles, generating a lung tissue motion displacement field; the high-dimensional tensor analysis module constructing a five-dimensional tensor structure and performing singular value optimization, extracting essential motion patterns; the nonlinear dynamics prediction module establishing a chaotic system model of respiratory motion, predicting future motion trajectories of lung nodules; the navigation fusion module integrating multi-modal data to generate a four-dimensional optical flow field; the surgical navigation module providing accurate real-time navigation information, the present application improving navigation accuracy to 1-3mm and being able to predict lung nodule motion trajectories within 2 seconds in the future.

The present disclosure provides a moving target tracking method, device, equipment and computer readable storage medium, the method comprises: target detection is carried out according to the image frame collected, and the target detection frame of the target detected is obtained;Event data acquisition is carried out in a target time range;The target time range is the time range determined based on the acquisition interval duration of the current image frame and the preset image frame;According to the event data collected, the optical flow calculation result is obtained by optical flow calculation;According to the optical flow calculation result, it is judged whether the target in the target detection frame is moving, and the target is tracked, and the target tracking result is obtained. According to the embodiment of the present disclosure, the accuracy of tracking the moving target can be improved.