4results about How to "Improve pose estimation accuracy" patented technology

The invention discloses a biased binocular visual odometer method and device based on strawberry cuttlefish bionics. The biased binocular visual odometer method comprises the following steps: synchronously acquiring a bright field image and a dark field image collected by a biased binocular camera and inertial data of an inertial measurement unit; constructing a perceptual attention weight grid according to the bright field image and the dark field image, and performing brightness normalization processing on the bright field image and the dark field image; extracting lateral visual features based on the normalized image and the perceptual attention weight grid; and fusing the biased visual features with the inertial data, and solving through nonlinear optimization to obtain a carrier pose estimation result. According to the invention, the dynamic range of the binocular vision system is expanded, and the imaging and sensing capabilities of the system in an HDR scene are improved. And meanwhile, the positioning precision and robustness of the binocular visual odometer in an HDR scene are improved.

The invention relates to a tight coupling vision inertial odometer method based on a pulse camera brightness change rate, and belongs to the field of computer vision and robot positioning and navigation. The method comprises the steps of 1) VIO system preparation and data preprocessing, 2) visual feature extraction and pulse observation value calculation, 3) IMU pre-integration, and 4) tight coupling optimization model construction and solution. During operation of the system, for each sliding window, the optimization process of a predicted state vector is completed through the steps 2)-4), carrier motion state estimation at the latest moment in the current sliding window is output, then the sliding window is updated, and the steps 2)-4) are cycled, so that the system continuously outputs high-frequency and high-precision real-time motion state estimation. According to the invention, the microsecond brightness differential signal of the pulse camera is converted into continuous physical supervision on the motion state, and the precision and robustness of the system in challenging scenes such as high speed and dynamic illumination are remarkably improved in a tight coupling mode on the premise of not changing the VIO main body architecture.

A colon endoscope camera pose estimation method based on an iterative refinement strategy relates to the technical field of medical image processing and computer vision, and comprises the steps of construction and preprocessing of an image data set, construction of an overall framework of a network model, design and implementation of a feature extraction network, and design and implementation of a camera motion classification network. Designing and realizing an iterative relative pose refining network; training and using a network model; and the like. According to the method, two camera motion modes of insertion and withdrawal are distinguished by using the camera motion classification network, the pose estimation precision is improved by combining a coarse-to-fine iteration refining strategy of the iteration relative pose refining network, the learning ability and generalization performance of the whole method are effectively improved, accurate estimation of the colon endoscope camera pose is realized, and the method is suitable for popularization and application. The method can be widely applied to the camera pose estimation task of the colon endoscope, and provides accurate camera pose support for clinical application scenes such as three-dimensional reconstruction and polyp screening of the colon endoscope.

The invention discloses a panoramic imaging method and device, equipment and a medium, and relates to the technical field of automatic driving, and the method comprises the steps: carrying out the projection transformation of an original image collected by a vehicle camera, and generating an aerial view; determining the size of an adaptive target window according to the distance from each pixel to a central pixel in the aerial view, and performing optical flow estimation on each pixel in two adjacent frames of aerial views in the size of the target window based on vehicle motion information measured by an inertial measurement unit to obtain a dense optical flow field; extracting inner points from the dense optical flow field by using a preset improved RANSAC algorithm, and estimating global motion parameters based on an extracted inner point set; fusing the global motion parameters and motion parameters measured by the inertial measurement unit and the positioning system by using a Kalman filtering method to obtain fused motion parameters; and projecting the historical panoramic image to an aerial view coordinate system by using a homography matrix calculated based on fusion motion parameters, and splicing the historical panoramic image with the current aerial view to generate a new panoramic image.