71results about How to "Solve uneven lighting" patented technology

The invention discloses a low-rank partitioning sparse representation human face identifying method, which adopts low-rank matrix decomposition, introduces a reference item, adopts a DCT (discrete cosine transform) algorithm to realize the normalization of images and effectively solves the problem of uneven lighting in a human face image. At a classifying stage, a clustering thought is used, and the identifying speed is effectively improved. The algorithm is used on a standard human face database to perform multiple times of tests, and the test result shows that compared with the existing human face identifying method, the low-rank partitioning sparse representation human dace identifying method has the advantage that the identifying accuracy and computing efficiency of the algorithm are all consistently improved. The precision and stability on human face identifying are improved under the complex conditions, such as shielding, disguising and illumination varying, of the human face image.

The invention discloses an underwater image enhancement method in combination with bilateral filtering and Retinex. The method comprises the steps of converting an RGB color space of an input image toan HSV color space; for a brightness component, filtering image noises in combination with the bilateral filtering, and separating out a reflective component and an irradiation component based on Gaussian center surrounding multi-scale Retinex for the denoised brightness component; for the separated irradiation component, adjusting illumination by adopting gamma correction to obtain a new irradiation component; realizing fusion enhancement of the irradiation component and the reflective component based on a Retinex theory, thereby obtaining a brightness component after non-uniform illumination correction; recombining the enhanced brightness component with a hue component and a saturation component, and converting the HSV color space to the RGB color space; calculating grayscale value ratios of red and green channels to a blue channel, and remapping the grayscale values of the three channels; and finally performing histogram equalization on the R, G and B channels of the image to realize image contrast enhancement. According to the method, the blue and green color deviation of the underwater image is effectively eliminated, so that the image contrast is improved; and the partial image noises are filtered, so that the signal-noise ratio of the image is increased.

The invention discloses a simultaneous positioning and mapping method for an autonomous mobile platform in a rescue scene, which is applied to a search and rescue autonomous mobile platform and can beused for positioning and mapping in extreme environments such as a fire rescue scene, a complex dangerous accident scene and the like. The method is mainly divided into three parts of sensor information processing, pose estimation and pose correction. The method comprises the following steps: firstly, performing operations such as deblurring and feature extraction on omnibearing image informationacquired by a four-eye camera module; secondly, fusing with the measurement information of the inertial navigation sensor and estimating the pose, and finally, carrying out global pose optimization and correction. According to the method, a full-automatic end-to-end defogging method is designed based on the convolutional neural network, a post-processing step is not needed, the application rangeis wide, and the method can be applied to defogging of indoor and natural scenes at the same time. And meanwhile, a relatively stable binocular vision SLAM method based on a feature point method is adopted to fuse IMU sensor data to perform positioning and mapping of the autonomous mobile platform.

Provided is a light reflecting plate capable of reducing glare of reflected light while maintaining high light reflectance by regular reflection. The light reflecting plate includes a base, a light reflecting layer that is formed on the base and made of silver or silver alloy, or aluminum or aluminum alloy, in which arithmetic average roughness (Ra) is 0.10 to 0.30 μm and arithmetic average waviness (Wa) is 0.30 to 2.50 μm on a surface of the light reflecting layer.

The invention relates to a light emitting diode (LED) light guide plate lamp component. The component comprises a framework, at least one light source in any color, a light guide plate, fluorescent powder and a reflecting plate, wherein the at least one light source and the light guide plate are fixed by the framework; the fluorescent powder is adhered to the side part of the light guide plate corresponding to the light source, and receives light rays from the light source to be transited to an excited state, so that the light guide plate only receives mixed light rays from the light source and the fluorescent powder; and the reflecting plate is arranged on the back side of the light guide plate and reflects the light rays towards the light guide plate. Compared with the prior art, the technical scheme has great advantages in the aspects of cost, technical difficulty and an actual using effect; and the technical performance of the component greatly exceeds that of the conventional similar products under the condition of the same material or an inferior material, so the application prospect of the component can be foreseeably great.

The invention relates to a device and method of intelligent light supplementation of flammulina velutipes in different growth periods based on a convolutional neural network. The device of light supplementation is composed of a bearing device, a camera (the revolution is 1920*1080), a full spectrum LED lamp, a computer, a flammulina velutipes culture medium and a plastic pipe. The method comprises the steps of using image samples of massive manually labeled flammulina velutipes in the different growth periodss to train the convolutional neural network to obtain a trained classification model; using the camera to shoot growing flammulina velutipes in a planting room to conduct sampling, and using the trained model to judge which growth periods the flammulina velutipes samples belong to; then using the computer to control the light color of the full spectrum LED lamp according to the requirement of flammulina velutipes for light quality in the growth period, so that the light color of the full spectrum LED lamp meets the requirement most suitable for light quality of flammulina velutipes in the current growth period, and finally a promotion effect is played on the growth of flammulina velutipes by controlling the light quality to achieve the production aim of planting personnel. According to the device and method of the intelligent light supplementation of flammulina velutipes in the different growth periods based on the convolutional neural network, the yield of flammulina velutipes is increased, the quality of flammulina velutipes is improved, so that producers make a profit, and consumers are benefited.

The invention discloses an apparatus for acquiring images of rock core and rock debris, which comprises a lamp bracket, a master control circuit system and a sample shift mechanism. A light conversion device, a filter lens and a filter lens shift mechanism are provided within the lamp bracket, the filter lens and the filter lens shift mechanism are connected; the sample shift mechanism comprises stepping motors and reduction boxes along two directions of X shaft and Y shaft in a horizontal plane, the control signal input terminal of the stepping motors, light conversion equipment and the filter lens shift mechanism are respectively connected with the corresponding signal output terminal of the master control circuit system. The present invention also discloses a method for acquiring images of rock core and rock debris, the clearest image can be found by automatically searching a clear focal length direction for realizing an automatic focusing. The invention also discloses a method forprocessing the images of rock core and rock debris, an automatic splicing of the images can be completed by successively finding the optimum splicing line in an overlap area. Small rock core (plungertype rock core and the like) and rock debris images can be collected according to the invention, which has the advantages of light mass and small size, high intelligent degree.

The invention discloses a strawberry planting device. The strawberry planting device comprises a strawberry planting frame and two conveying mechanisms, wherein the strawberry planting frame comprises a step-type supporting frame, a solar rotating device and a high-pressure nozzle; a planting groove is formed in each layer of step of the supporting frame; a water pipe is arranged in the supporting frame; the solar rotating device is mounted in the middle of the step on the uppermost layer of the supporting frame; the high-pressure nozzle is mounted at the central position of the top of the solar rotating device; the solar rotating device comprises a solar panel, a rotating body and a rotary shaft; the solar panel is mounted at the top of the rotating body; the high-pressure nozzle is mounted at the central position of the solar panel; one end of the rotary shaft is connected with the rotating body and the other end of the rotary shaft is connected with the bottom of the supporting frame; the rotary shaft is fixedly connected into the center of the supporting frame; the rotary shaft is a hollow rotary shaft; each of the two conveying mechanisms is composed of a material containing barrel, a retractable rod and a base. The strawberry planting device provided by the invention is simple in structure and reasonable in design; phenomena of existing single-layered planting and placement that light illumination is not uniform and the growth vigor of strawberries is not good can be effectively solved.

The invention discloses a cylindrical pot surface defect detection method, which comprises the following steps of: fixing a product to be detected on a rotating device, and enabling a detection surface of the product to be detected to be positioned on a focal plane of an area-array camera to synchronously rotate along with the rotating device; driving coaxial light source equipment to provide illumination for the to-be-detected product; driving the area-array camera to carry out image acquisition on the surface of the to-be-detected product to generate a target image; driving the industrial personal computer to recognize the target image so as to extract feature information of the target image; and driving the industrial personal computer to carry out dimension reduction and classification processing on the feature information so as to identify the defects of the to-be-detected product. The invention further discloses a controller, an industrial personal computer and a cylindrical pot surface defect detection system. By adopting the method, the classification of the surface defects of the high-brightness reflective metal cylindrical pot can be accurately completed.

The utility model provides an imaging method and terminal, wherein the method comprises the following steps: whether the current photo environment is a low-light environment is checked; if the current photo environment is a low-light environment, and the current is in a photo mode with the screen to fill the light, then the current first color in the colors displayed by the terminal screen is adjusted to a second color, wherein the color temperature value of the first color is bigger than the color temperature value of the second color; the photos corresponding to the second color are forms according to the photo orders that have obtained. The imaging method and terminal has the advantages of being capable of avoiding the blue purple plaques on facial skin caused by uneven brightness in low-light environment, and selfies with even skin color are obtained.

Provided is a display device comprising a liquid-crystal panel and an optical sheet member including multiple stacked optical sheets emitting light from a light source toward the liquid-crystal panel, which can alleviate unevenness in light even in the case where, for example, light with such unevenness is emitted from the optical sheet member due to warps or wrinkles generated in the optical sheet member caused by heat generated by the light source.

A diffusion sheet is provided between a liquid-crystal panel and an optical sheet member with a gap from the optical sheet member. The light emitted through the optical sheet member is diffused by the diffusion sheet and gap, and then enters the liquid-crystal panel.

The invention relates to the technical field of light emitting diodes, in particular to a light emitting diode package structure. The light emitting diode package structure includes a crystal of a light emitting diode and further comprises a base, a fixing ring, a heat dissipating assembly, a heat dissipating wire, a lens and a transparent frame. The light emitting diode package structure is provided with the heat dissipating assembly, the fixing ring and the heat dissipating wire, heat generated by working of the light emitting diode is transmitted to the heat dissipating wire through the fixing ring, then the heat is transmitted to the heat dissipating assembly through the heat dissipating wire to realize timely heat dissipation of the crystal, and therefore the influence on the stimulating effect of phosphor powder coated on the crystal is avoided; the heat dissipating assembly consists of a clamping ring, heat dissipating fins and a connecting ring assembly, and the heat can be quickly dissipated through the heat dissipating fins; the lens is arranged, so that a light source emitted by the light emitting diode can be diffused through the lens to maximize the light emitting range; and meanwhile, hemispherical setting allows for uniform distribution of light throughout the lens, and uneven illumination range is avoided.

The invention relates to a solar cell image acquisition structure, belongs to the technical field of solar cell visual inspection, and solves the problem that the illumination of the cell is uneven, the darkroom is difficult to operate and the adjustment effect is difficult to reset. The technical solution is that a diffusion plate, a light source bracket and a camera bracket are installed on thewhole bracket and have positions adjustable according to needs, the diffusion plate increases the angle adjustment and realizes balanced illumination with the light source such that the acquired imageis more highly restored, the scale of the lifting slide is used to precisely adjust the effect of the camera and the light source on image acquisition to facilitate the resetting of adjustment effect, and the telescopic plate is adhered between the light source bracket and the camera bracket to form a darkroom cavity to ensure stable light between the camera and the light source. The solar cell image acquisition structure can be easily disassembled and installed, and is convenient for the operator to operate in real time.

The invention discloses an illumination lamp with uniform illuminance. The illumination lamp is deviated from a central line of an illumination area and comprises a lamp holder, a socket, and a light emitting module; the socket is arranged at the end of the lamp holder; the light emitting module is accommodated in the lamp holder and is electrically connected with the socket; and the illumination lamp is characterized in that the light emitting module comprises at least two groups of different light-emitting diode (LED) luminous bodies of which emergent light central lines are not consistent and illumination intensities are different. Multiple groups of the LED luminous bodies with different emergent light central line angles are arranged in the lamp holder, so that the illumination range is widened, the illuminance is improved, and the phenomenon that the illumination is not uniform when an object is irritated by LED luminous body groups with single emergent light central line angles is avoided; a lens is not needed to be arranged in single LED luminous body; the illumination lamp has a simple whole structure and is convenient to install; and the intersection angles of the emergent light central lines among different groups of LED luminous bodies can be adjusted or changed according to actual requirements, so that illumination of a required area can be obtained, and the illumination lamp can be adjusted flexibly and easily.

The invention discloses an underwater-image enhancement system and enhancement method based on granular computing. Underwater illumination unevenness and noises are removed on the basis of a calculation method of non-uniform granularity, and image enhancement is realized while completeness of texture details is protected. According to the method, firstly, illuminance information of an underwater image is extracted; the illumination information is subdivided step by step according to granularity layers from coarseness to fineness, and the image is divided into a set formed by a series of particles of different sizes and illumination intensities; and a most-suitable brightness particle is positioned, and illuminance compensation is respectively carried out according to a brightness situationof each particle to obtain an underwater image of which the illumination unevenness is removed; and then noise removal is respectively carried out on each particle to realize image enhancement. According to the method, self-adaptive analysis can be carried out according to image characteristics without the need for prior illumination knowledge and manual parameter adjustment, and texture and detail information of the enhanced underwater image is clear and complete.

The invention discloses a city intelligent lamp post integrating power supply, network and control. The lamp post comprises a first lamp post main body, a second lamp post main body, a lamp arm, a fixed plate, a connecting rod, a lifting component, an operating box, a touch screen, an adjusting knob, a base, a bolt hole and a solar cell panel, wherein the base is welded at the bottom of the firstlamp post main body; the operating box is fixed to one side of the center of the first lamp post main body by virtue of a screw; the touch screen is arranged at one end of the operating box; the second lamp post main body sleeves the top of the first lamp post main body; and a first supporting plate is welded at one side of the center of the second lamp post main body. The city intelligent lamp post integrating power supply, network and control is simple in structure and convenient to operate; the height of the city intelligent lamp post can be freely adjusted so as to adapt to various environments and fields; a circumstance that the lamp post main body of the city intelligent lamp post is uniform in lighting brightness due to uniformity in ground height can be avoided, so as to bring about benefit for lighting; and the city intelligent lamp post is convenient for users.