11 results about "Visible light positioning" patented technology

This application discloses a visible light positioning and communication method, apparatus, and system, belonging to the field of visible light positioning and communication. It involves driving an LED lamp to emit a light signal with a preset modulation frequency. A receiving sensor receives the spectrum, extracts the chip's native blue light spectrum, and then decodes the spectral information carried by the spectrum based on the hardware parameters of the receiving sensor to obtain digital information. Positioning and communication are then performed based on this digital information. This application's solution completely eliminates physiological flicker perceptible to the human eye by employing high-frequency modulation at a preset frequency. Simultaneously, receiving only the native blue light spectrum effectively removes the afterglow effect of phosphors, ensuring clear high-frequency signals and significantly improving decoding success rate. Adaptive decoding, combined with the receiving sensor's hardware parameters, solves the frequency offset problem caused by hardware differences between different devices, enhancing cross-device compatibility. This achieves high-precision, high-reliability visible light positioning and communication, applicable to indoor navigation, communication, and other scenarios.

The application provides a visible light positioning system and a preparation method of a silicon-based flexible photoelectric detector, and relates to the technical field of visible light positioning. The visible light positioning system comprises a fixed module with a curved surface structure, at least two silicon-based flexible photoelectric detectors, a data processing module and a positioning analysis module. The silicon-based flexible photoelectric detector comprises, from top to bottom, a front grid electrode layer, a hole transport layer, a passivation layer, an N-type monocrystalline silicon layer and a back metal electrode layer arranged in a stacked manner. The N-type monocrystalline silicon layer has a pyramid structure on both sides, and the hole transport layer, the passivation layer and the back metal electrode layer are conformally arranged with the N-type monocrystalline silicon layer. The silicon-based flexible photoelectric detector has the characteristics of flexibility, self-supporting and self-power supply, and has excellent photoelectric detection capability. The visible light positioning system has a simple structure, reduces the volume and cost, and realizes accurate positioning of the measured light source.

The application provides a binocular positioning method using a known light source arrangement, and belongs to the field of computer vision positioning. The application captures the positions of three visible light feature points of a target object in a camera pixel image during movement of a binocular camera, and an inclination angle and a roll angle obtained by a six-axis inertial sensor. A unscented Kalman filter is used to integrate data of the inertial sensor and data of the binocular camera, so that visible light positioning is realized, that is, the position of a visible light feature point of the target object in a three-dimensional space and a heading angle are accurately calculated. The application has wide applicability, good stability, and can be used for positioning at a farther distance. The stability is excellent not only in an indoor environment, but also in complex outdoor environments such as urban blocks, mountains and oceans.

This invention proposes a visible light positioning method and system based on spatiotemporal and angular feature fusion, relating to the field of indoor positioning technology. The method includes: constructing a training dataset based on an indoor positioning scene, including visible light positioning pilot maps, coordinate labels, distance labels, and angle labels; inputting the training dataset into a positioning model for training, extracting preliminary features through a feature embedding module, and then capturing the temporal dependencies of the preliminary features and enhancing spatial perception through a feature fusion module to obtain fused features; inputting the fused features into position extraction branches and angle extraction branches at different depths to obtain position information and angle information respectively; calculating a loss function until the loss converges to obtain a trained positioning model; inputting the visible light positioning pilot map of the receiver to be positioned into the trained positioning model to obtain positioning information. This achieves high-precision and robust 3D positioning, effectively solving the problems of insufficient feature mining and poor scene adaptability in traditional VLP technology.

The application discloses a kind of anti-pose interference three-dimensional visible light positioning methods based on double-branch feature decoupling.First, in indoor space, the visible light positioning system containing tilt receiving end is deployed, and system channel model is constructed;Multi-inclination state sampling is carried out to photoelectric detector, and the received signal strength characteristic of photoelectric detector under different inclination states at different space reference points is obtained;Then, the received signal strength characteristic is preprocessed, and the enhanced received signal strength characteristic is obtained, so as to obtain the tilt enhanced fingerprint database of illumination compensation;Finally, a pose estimation model based on double-branch feature decoupling is constructed, the position estimation branch of the model decouples the pure position feature from the position main feature using the pose of photoelectric detector, and the position of photoelectric detector is obtained using the pure position feature regression.The interference ability of pose on position estimation is significantly weakened, and the problem of positioning accuracy decline caused by unknown tilt state of receiving end and weak light area is solved.

The application provides a visible light positioning system and method based on occlusion detection. The application calculates the normalized signal intensity change rate of each LED lamp in the current period; a world coordinate system is constructed in combination with the right-hand rule; the robot selects the corresponding occlusion threshold model to calculate the threshold of each LED lamp in the current period according to the discrimination result of the three-axis movement direction; the normalized signal intensity change rate of each LED lamp in the current period is combined with the threshold of each LED lamp in the current period to make a judgment, so that the occlusion state of each LED lamp in the current period is obtained; the robot vehicle selects the occlusion state of each LED lamp in the current period to obtain a plurality of un-occluded LED lamps in the current period, and the indoor positioning method based on the LED lamp signal intensity is used for positioning to obtain the position of the robot in the current period. Even in the case of serious light reflection effect or very short occlusion time, the application can still effectively eliminate the occluded light signal.

The application relates to a vehicle position and attitude prediction method and system based on a fingerprint method visible light positioning, and belongs to the technical field of vehicle positioning. The method comprises the following steps: dividing fingerprint areas according to the signal coverage range of a vehicle-mounted visible light emitting device; wherein the fingerprint areas comprise multiple fingerprint position points; each fingerprint position point comprises multiple attitude angles; taking one of the attitude angles of one of the fingerprint position points as a fingerprint point; acquiring signal strength values on all the fingerprint points, establishing a fingerprint database, and preprocessing the database to obtain a standard fingerprint database; training the standard fingerprint database to construct a relationship model of the signal strength values and the relative position and attitude angle of the vehicle; acquiring real-time signal strength of a vehicle in front of the vehicle, and calculating the relative position and attitude angle of the current vehicle relative to the front vehicle according to the relationship model to complete relative positioning and attitude prediction of the vehicle. The application improves the accuracy and adaptability to complex scenes of vehicle-to-vehicle relative positioning.

This invention provides an indoor visible light positioning method and system based on clustering and deep neural networks, relating to the field of optical communication positioning technology, including a transmitter and a receiver. The received signal strength of the positioning area is used as the training set for the deep neural network. Different modulation frequencies are assigned to multiple white LEDs. The neural network is trained using the received signal strength of each LED in the training set and the actual coordinates of the photodetector. The learning algorithm combines k-means clustering and deep neural network (DNN) algorithms. The received signal strength of each LED is input into the trained neural network to obtain the photodetector's position coordinates. This invention, based on an optimized learning algorithm using neural networks, effectively reduces the amount of sampling data and improves network training speed and indoor positioning accuracy. The positioning system is unaffected by external factors such as multipath reflection and has significant practical application value.