7results about How to "Meeting Imaging Needs" patented technology

This application relates to an image processing method, apparatus, and computer device. The method includes: performing face recognition on a target image to obtain a target face region; determining target pixel information for each target pixel in the target face region based on reference pixel information of each reference pixel in a reference face region of each frame of the original image; for each target pixel, converting the target pixel information into color coordinates, and determining the weight of the target pixel based on the hierarchical relationship between the color coordinates and the range of human face coordinates; for each frame of the original image, determining the reference brightness of each reference pixel in the reference face region of the original image based on the weight of each target pixel and the original brightness of each reference pixel in the reference face region of the original image; and determining the current brightness of the target face region based on the reference brightness of each reference pixel in the reference face region. This method can improve the accuracy of face region brightness.

This invention provides an imaging method and image acquisition system, relating to the technical field of computer vision. The method includes: acquiring 3D point cloud data of a target object and image data acquired by each camera at different exposure levels; projecting the 3D point cloud data onto the imaging plane corresponding to each camera to generate a sparse depth map; performing Gaussian processing on the sparse depth map to output a dense depth map; using the dense depth map and the camera's intrinsic parameters, back-projecting the pixels of the image data corresponding to each camera onto the world coordinate system to obtain pixels in the world coordinate system; selecting a preset reference viewpoint and reprojecting the pixels in the world coordinate system onto the imaging plane of the reference viewpoint to obtain the target image. The imaging method and image acquisition system provided by this invention can achieve 3D-guided 2D alignment, making the imaging process independent of the image's own grayscale or texture features, thereby improving the image acquisition effect to meet imaging requirements.

The embodiment of the application discloses a fixed focus lens, which comprises a first lens, a second lens, a third lens, a fourth lens, a fifth lens, a sixth lens, a seventh lens and an eighth lens arranged in sequence along an optical axis from an object plane to an image plane; the first lens is a negative focal length lens, the second lens is a negative focal length plastic aspheric lens, the third lens is a positive focal length plastic aspheric lens, the fourth lens is a positive focal length glass lens, the fifth lens is a positive focal length plastic aspheric lens, the sixth lens is a negative focal length plastic aspheric lens, the seventh lens is a positive focal length plastic aspheric lens, and the eighth lens is a positive focal length plastic aspheric lens. By adopting the technical scheme, the fixed focus lens comprises eight lenses, the focal lengths and surface shapes of the lenses are reasonably distributed, the design of the fixed focus lens with excellent comprehensive performance which takes into account imaging requirements and compact structure is finally realized, and the comprehensive performance meets the use requirements of a general sensor of security monitoring.

The utility model relates to the technical field of endoscope, disclose a kind of endoscope imaging system and hyperspectral endoscope, system includes: light source device, including light source module, light source adjusting assembly, light source module emits light after passing through light source adjusting assembly and emits;Light source adjusting assembly is used to adjust the light intensity when irradiating to target object;Lens device, including light emitting component, imaging component;Light emitting component is used to emit the illumination light produced by light source device to target object, camera lens is used to receive the illumination light reflected from target object back, and image in image sensor;Data processing device is connected with image sensor communication, for obtaining the spectral data after image sensor, to generate the image data corresponding to target object.The utility model provides an endoscope imaging system by light source adjusting assembly adjusts light intensity, so that endoscope imaging system can be under different irradiation conditions Stable output suitable light intensity, improve the stability and imaging quality of endoscope imaging.

The high-pressure injector capable of adjusting the injection pressure in real time comprises a machine body, a piston rod arranged in the machine body and a driving mechanism controlling the piston rod to stretch and move, a needle cylinder is detachably installed at the position, corresponding to the piston rod, of the machine body, and the piston rod can reciprocate in the needle cylinder. Pressure sensors are mounted at the ends of the piston rods; a displacement detection assembly is arranged in the machine body; a control module is integrated in the machine body, and the driving mechanism, the pressure sensor and the displacement detection assembly are all in electrical feedback connection with the control module. When the pressure sensor monitors that the internal pressure of the needle cylinder reaches a critical value, the control module can control the piston rod to retreat by a certain stroke through the driving mechanism and then control the piston rod to decelerate and advance forwards. The utility model has the beneficial effects that a contrast agent can be prevented from being injected into the blood vessel of a patient under the condition that the critical pressure is exceeded, so that the conditions of vascular rupture, vascular intima injury, contrast agent exosmosis and the like are prevented.

The application provides a fisheye lens, which comprises first to eighth lenses and a protection glass in sequence along an optical axis from an object side to an image side, and a diaphragm is located between the fourth and fifth lenses; the first to third lenses all have negative refractive power, the object side surface is a convex surface, and the image side surface is a concave surface; the fourth and fifth lenses have positive refractive power and are biconvex; the sixth lens has negative refractive power, the object side surface is a concave surface, and the image side surface is a convex surface; the seventh lens has positive refractive power and is biconvex; the eighth lens has negative refractive power and is biconcave; all the lenses are glass spherical lenses; through specific refractive power arrangement, surface configuration, refractive index and Abbe number range limitation, a miniaturized structure with an optical total length less than 21 mm and an effective diameter of each lens less than phi 12 mm is realized, the MTF is greater than 0.6 in a 0.8 field of view at a spatial frequency of 83 lp / mm, the total field of view is greater than 0.45, the target surface height is greater than 4.6 mm to match a 1 / 2.4 inch sensor, the F-Theta distortion is less than 1%, and the relative luminance at the maximum field of view is greater than 55%.

The invention relates to the technical field of fruit and vegetable processing equipment, in particular to a fruit and vegetable maturity visual identification sorting device which comprises a conveyor body, the output end of the conveyor body is fixedly connected with a hopper, the output end of the hopper is provided with a conical conveying mechanism, and the output end of the conical conveying mechanism is provided with a detection mechanism. The sorting mechanism is fixedly installed at the bottom end of the detection mechanism, the detection mechanism comprises a bottom plate, a clamping mechanism and a detection platform, the clamping mechanism is installed at the top end of the bottom plate and located at the output end of the conical conveying mechanism, and fruits and vegetables are automatically contracted and arranged through the conical conveying mechanism before entering a detection area and enter a cylinder in a single-row ordered posture; the problems of rolling deviation and uncontrollable postures of the fruits and vegetables easily caused by a straight conveying belt are avoided; when fruits and vegetables fall, a rectangular block slides along an inclined groove to compress a spring, a clamping silica gel plate is pushed to adaptively clamp the fruits and vegetables with different sizes, the fruits and vegetables are kept stable in the detection process, and image blurring caused by shaking and displacement is avoided; and grading damage is effectively avoided.