6 results about "Color adaptation" patented technology

This invention discloses a method, system, device, and storage medium for generating camouflage images, belonging to the field of computer vision and image generation. It employs a hierarchical automatic annotation method based on a large visual language model to obtain camouflage image annotation data, guiding the process through a three-level annotation workflow: online batch processing, offline supplementation, and manual review, outputting structured results. Based on a diffusion model framework, it integrates two types of feature enhancement modules—texture prior and color adaptation—to construct a generative model. After training with annotation data, it inputs the camouflage image to be restored, constraining texture consistency and aligning global color consistency through the two modules respectively, thus completing the generation and restoration of the camouflage image. This method for generating and restoring camouflage targets, combining semantic pairing, texture prior, and color consistency, along with its accompanying dataset, can be widely applied to camouflage target image synthesis, camouflage target detection enhancement, augmented reality, and other technical directions.

This application discloses a color adaptation method and an electronic device. The electronic device has a shooting end and a display end. At the shooting end, the electronic device can capture a first original image under a first ambient color temperature, and generate and save a first image file based on the first original image. The first image file includes a first image and first metadata, which includes the first ambient color temperature, the expected white point color temperature of the first image when displayed under the first ambient color temperature, and the white point color temperature of the first image in the first image file. At the display end, the electronic device can generate and display a color-adapted first image based on a second ambient color temperature. The white point color temperature of the color-adapted first image is determined based on the aforementioned first metadata. Therefore, the electronic device can restore the image to the color temperature perceived by the human eye after color adaptation to the greatest extent possible, thereby providing users with a more realistic shooting and viewing experience.

The application discloses a kind of structure light three-dimensional measurement method based on continuous phase constraint, including constructing encoding stripe, project the encoding stripe and obtain corresponding image, project periodic stripe pattern with preset phase offset and obtain multiple images, and the phase information of each pixel is calculated by the multiple images;Determine the stripe period interval to which the pixel belongs based on the phase information, and based on the continuity of phase on space, the initial stripe order is corrected consistently, and the three-dimensional appearance of the measured object is recovered according to the corrected stripe order and phase information.The present application encodes by time domain, space domain and color domain, the present method significantly reduces the number of patterns that need to be projected, while ensuring measurement accuracy through color adaptation and phase-assisted decoding, and has stronger robustness for color surfaces.

The present application relates to a convolutional neural network-based image color fusion method, device and storage medium, applied to the technical field of image processing, comprising: realizing color adaptation of foreground and background under the double constraints of foreground mask and skin segmentation mask through a color fusion model, optimizing the color naturalness of the skin area, effectively solving the problems of rigid fusion and strange skin color in the prior art, and improving the stability of the method; The high-resolution processing strategy of "low-resolution inference + detail preservation color migration" not only avoids the problems of large video memory consumption and long time consumption of direct high-resolution inference, but also solves the problems of loss of global color information in block inference and introduction of edge abnormalities in traditional high-frequency information recovery; The detail preservation color migration model can accurately extract the color features of the low-resolution fusion result and completely retain the texture details of the high-resolution original image, realizing the dual goals of color fusion and detail preservation; Automatic processing significantly reduces time and labor costs.

The application discloses a multi-style differentiation pattern lighting system and device of a sighting telescope, and relates to the technical field of sighting telescopes. The device comprises a prism, a differentiation plate, a first LED lamp, a second LED lamp and a lens. The differentiation plate is provided with a first pattern and a second pattern in a concentric manner, and the surface of the second pattern is coated with a black light-shielding coating. The opening and closing and color switching of the two LED lamps are independently controlled, so that the free switching of the first pattern display, the second pattern display and the combined display of the two patterns can be realized, and multi-color adaptation is supported. The device ensures the light transmission and imaging effect through precise assembly of the components. The application can expand the differentiation pattern style by replacing the differentiation plate, solves the problem of fixed differentiation pattern and color of the traditional sighting telescope, adapts to different sighting scenes, improves the sighting flexibility and accuracy, and is suitable for various sighting telescope devices.

The application discloses an intelligent color-changing light source system, and relates to the technical field of LED intelligent lighting; a power management module receives a mode switching instruction issued by a micro control module, and switches the operation condition according to the load demand corresponding to color output; a driving module receives a PWM pulse signal issued by the micro control module, and adjusts the driving current of an RGBW four-channel LED array module; a color perception module is used for collecting ambient light intensity, color temperature and color distribution data in real time, and transmitting the data to the micro control module for color adaptation and calibration; a closed-loop feedback adjustment module obtains color deviation through difference calculation based on the data collected by the color perception module, in combination with preset color parameters, and transmits the color deviation to the micro control module; the micro control module generates a calibration signal and sends the calibration signal to the driving module, so as to correct the driving current of each channel of the RGBW four-channel LED array module. The application can meet the requirements of low power consumption, fast response and high color precision.