14results about How to "Reduce motion blur" patented technology

The invention belongs to the technical field of interventional robots, and discloses a method, device and equipment for automatically adjusting the collection frame rate and a medium, and the method comprises the steps: obtaining the current movement speed of an interventional robot; adjusting a corresponding collection frame rate according to the movement speed; and controlling a camera to perform data acquisition based on the acquisition frame rate. The appropriate frame rate is selected according to the real-time movement speed of the interventional robot, the high frame rate is provided during high-speed movement by dynamically adjusting the collection frame rate of the camera so as to reduce movement blur, and the frame rate is reduced in a low-speed or static state so as to save bandwidth resources. According to the method, unnecessary data transmission quantity is reduced, network congestion and processing burden are relieved, the overall performance and stability of the system are improved, real-time and accurate transmission of image information is ensured, smooth and clear visual feedback is provided, the accurate control capability in the intervention process is improved, and the safety of the intervention process is improved.

The invention provides a lens-free dynamic imaging system and a lens-free dynamic imaging method with distinguishable motion. The system comprises a laser light source, a binary optical mask, an image sensor and image processing equipment, coherent light emitted by the laser light source is coded and modulated by the binary optical mask and then propagated to the image sensor, the image sensor collects multiple frames of diffraction images of a moving sample and transmits the collected images to the image processing device, and the image processing device reconstructs the images through a neural network method. According to the image reconstruction method, physical priori knowledge of a lensless diffraction propagation model is fused into implicit neural representation, and a space-time priori loss and bidirectional memory training method is designed for network training, so that artifacts and blur generated by moving target imaging can be effectively reduced, and a high-resolution and high-quality imaging result can be obtained.

This invention discloses an all-weather autonomous road defect detection method and system, relating to the field of computer vision. It includes a hybrid vision sensor for all-weather autonomous road defect detection mounted on an unmanned vehicle (UAV). The hybrid vision sensor is equipped with a computing unit, which runs a hybrid vision road defect recognition and localization algorithm. The hybrid vision in the UAV sensor includes traditional RGB vision and DVS pulse vision. The traditional RGB vision is used to detect the texture details of the road, while the DVS pulse vision is used to detect road anomalies at high speeds. By utilizing the rich texture details of RGB and combining the sensitive response of DVS vision to low light and dynamic lighting changes, the accuracy of road defect detection is improved. This invention features real-time asynchronous response, high dynamic range, information capture capability in low-light scenarios, and reduced motion blur.

The invention belongs to the field of computer vision and video generation, and particularly discloses a portrait animation generation method and system based on consistent distillation. The method comprises the steps that a reference image sample and a human body posture sequence sample are collected to serve as a training set, a pre-trained teacher model is constructed based on the training set, and the teacher model is used for generating a target video; initializing a consistency distillation model to obtain a student model, and transmitting knowledge of the teacher model to the student model through a track segmentation consistency distillation method; optimizing the student model through auxiliary loss optimization, dynamic region weighted optimization and facial detail injection to obtain an optimized model; and inputting a reference image to be reasoned and the human body posture sequence into the optimization model to obtain a portrait animation video. According to the invention, the time sequence consistency, coherence and detail fidelity of the generated video can be effectively improved.

A driving circuit suitable for a display panel includes a driving transistor connected between a first power supply voltage and a light emitting diode; and two capacitors controllably connected to the driving transistors and corresponding data lines providing image signals. One of the two capacitors is used as a driving capacitor which controllably drives the driving transistor by a current image signal, and the other capacitor is used as a preloading capacitor which controllably preloads a subsequent image signal.

The invention relates to the technical field of liquid crystal display control, in particular to a thin film liquid crystal display control panel control method based on time sequence adjustment, which comprises the following steps: applying a test voltage within a frame blanking duration of a thin film liquid crystal display panel, and detecting an aging characterization voltage; determining the establishment delay duration of the output data signal relative to the gate signal; adjusting the starting pulse width of the grid signal according to the established delay duration; determining a common electrode voltage according to the starting pulse width; forming a test frame picture; detecting the response duration of the thin film liquid crystal display panel for displaying the test frame picture, and correcting the matching parameters of the establishment delay duration and the starting pulse width according to the response duration; outputting a corrected establishment delay time length and a corrected starting pulse width according to the matching parameters; and driving the thin film liquid crystal display panel to display an image. According to the invention, the image display stability is improved.

A display device and its driving method are discussed. The display device includes: a display panel having data lines, gate lines, and pixel lines, the pixel lines having pixels; a data driver connected to the data lines; a gate driver connected to the gate lines; and a timing controller configured to receive first pixel data or second pixel data of an input video from a set-up device, and to control the data driver and the gate driver based on the received pixel data. The timing controller is configured to write the second pixel data to a pixel during a write period in a frame when the second pixel data is received from the set-up device at a faster transmission rate than the first pixel data. The timing controller is then configured to write black data with a black grayscale value to the pixel during a vertical blanking period.

This utility model relates to the field of UD fabric impurity detection technology, and in particular to a finished UD fabric impurity detection device; it includes a winding machine, with frames arranged on both sides in front of the winding machine's inlet, and a gantry support spanning across the frames. The gantry support is located in front of the winding machine's inlet, and several industrial cameras are mounted on the crossbeams of the gantry support for capturing images of the UD fabric surface; a parallel jet assembly is arranged along the running front of the UD fabric on the gantry support, and the jet assembly includes a connecting rod arranged along the width direction of the UD fabric, with a movable sleeve fitted on the connecting rod, and multiple sets of jet modules arranged in an axial array on the sleeve, each set of jet modules including a pressing jet nozzle and a repelling jet nozzle; the scientific spacing between the jet assembly and the imaging unit enables process coordination, and the directional slit airflow of the pressing jet nozzle and the diffusion air curtain of the repelling jet nozzle form a complementary function, fundamentally solving the problems of dynamic missed detection of suspended impurities and airborne insect intrusion.

The utility model relates to the technical field of camera shooting, and discloses a remote sensing image ground object classification camera, which comprises a cylindrical base, the surface of the cylindrical base is in threaded connection with a connecting plate, and the top end of the connecting plate is in threaded connection with a camera body. According to the camera for classifying the ground objects in the remote sensing images, through the arrangement of the cylindrical base, the gravity block, the rotating mechanism and the stabilizing mechanism, the microcontroller is started, the gyroscope starts to rotate, and the angular momentum generated by the rotating motion enables the gyroscope to keep the motion direction unchanged; further, the camera body on the cylindrical base can be kept stable and does not shake left and right under the condition of inclining left and right, the faster the gyroscope rotates, the larger the angular momentum of the gyroscope is, the stronger the resistance to the direction change is, and the gravity action of the gravity block can enable the camera body to keep left-right balance in the vertical pitching motion process; the gravity block and the stabilizing mechanism can help the camera body to keep stable and reduce jitter and motion blur, thereby improving image quality.

The embodiment of the utility model provides an imaging module for realizing DVS and RGB fusion. The imaging module for realizing DVS and RGB fusion comprises a DVS imaging device, an RGB imaging device, a fusion device and a main control device. The DVS imaging device is used for generating an event image; the RGB imaging device is used for generating an RGB image; the fusion device is used for fusing the event image and the RGB image to obtain a corresponding target image and outputting the target image; the main control device is electrically connected with the DVS imaging device, the RGB imaging device and the fusion device and used for controlling the DVS imaging device, the RGB imaging device and the fusion device to operate according to a preset sequence. In addition, the utility model also provides a camera and electronic equipment. According to the technical scheme, the problems that the image of the moving object is blurred and a clear image cannot be output when the object moves at a high speed are effectively solved.

The invention relates to the technical field of intelligent sensors, in particular to an image transmission method for remote detection of the ophthalmology department. According to the method, multiple frames of fundus grayscale images are continuously collected in preset exposure time, the detail definition degree in the images is evaluated according to the grayscale distribution condition, and the ambient light suitability degree of the current collection environment is obtained; and then the micro-motion degree of the eyeballs is evaluated according to the difference between the fundus grayscale images between the adjacent frames, so that the preset exposure time is adjusted in combination with the ambient light suitability, the high-quality fundus grayscale images are obtained for remote transmission, and the remote transmission effect of the fundus grayscale images is improved.

The invention discloses a television picture processing method and related device based on MEMC technology, and the method comprises the steps: converting a television audio and video signal into video sequence frame data when a smart television receives the television audio and video signal; performing calculation processing on motion vectors of the moving targets in two adjacent video frames in the video sequence frame data based on an MEMC technology to obtain motion vector data of the moving targets; based on the motion vector data of the moving target, starting an intelligent frame insertion algorithm to perform frame insertion processing on the video sequence frame data to form video sequence frame data after frame insertion; performing light and shade contrast enhancement processing on each piece of video sequence frame data in the video sequence frame data after frame insertion to form enhanced video sequence frame data; and loading the enhanced video frame sequence data to the smart television for playing control. According to the embodiment of the invention, the motion blur and smear phenomena of the moving target during television playing are reduced, and meanwhile, higher detail colors are achieved.

The invention discloses a geothermal well internal foreign matter rapid identification and salvage control system, and relates to the technical field of geothermal well internal foreign matter identification and salvage control. Comprising an initial identification and positioning module, a real-time data acquisition module, a data analysis and flow prediction module, a flow state classification module, a stable flow identification module and a dynamic flow optimization module. And the initial recognition and positioning module is used for deploying a high-resolution camera in the geothermal well and carrying out initial foreign matter recognition and positioning operation according to the set initial exposure time. The high-resolution camera and the built-in measurement module are used for collecting hot water flow data in real time, the exposure time is dynamically adjusted in combination with a machine learning model, high-precision recognition under static flow is achieved, the exposure time is shortened under dynamic fluctuation so as to reduce motion blur, the recognition accuracy and efficiency are effectively improved, the missing detection risk is reduced, and the recognition efficiency is improved. And the response speed and parameter setting of the camera are optimized, so that the camera can flexibly cope with complex environment changes.

The invention provides a sole contour scanning system based on a point laser sensor, which relates to the technical field of shoemaking and comprises a conveying mechanism, the point laser sensor and a control unit. The control unit is used for executing the following steps that real-time height difference data are collected and judged based on the point laser sensor at the initial position; when it is judged that the height difference data is larger than the first set value, the control point laser sensor reciprocates in the second direction; in the reciprocating motion process of the point laser sensor, when it is judged that the height difference is larger than a second set value, the point laser sensor continues to move by a set movement distance and then moves reversely; after it is detected that the height difference data is kept stable and unchanged, the point laser returns to the initial position; and judging the height difference data, screening effective data and outputting the effective data. Efficient scanning and data processing are achieved, motion blur is effectively reduced, effective data are screened, and the detection precision and stability are improved.