Research on image sensor (IS)-based visible light positioning systems has attracted widespread attention. However, when the receiver is tilted or under a single LED, the positioning system can only achieve two-dimensional (2D) positioning and requires the assistance of inertial measurement units (IMU). When the LED is not captured or decoding fails, the system’s positioning error increases further. Thus, we propose a novel three-dimensional (3D) visible light positioning system based on image sensors for various environments. Specifically, (1) we use IMU to obtain the receiver’s state and calculate the receiver’s 2D position. Then, we fit the height–size curve to calculate the receiver’s height, avoiding the coordinate iteration error in traditional 3D positioning methods. (2) When no LED or decoding fails, we propose a firefly-assisted unscented particle filter (FA-UPF) algorithm to predict the receiver’s position, achieving high-precision dynamic positioning. The experimental results show that the system positioning error under a single LED is within 10 cm, and the average positioning error through FA-UPF under no light source is 6.45 cm.

Existing visible light positioning (VLP) systems often struggle to simultaneously achieve high accuracy, low complexity, and low power consumption, especially for portable applications. To address this challenge, we propose the L-PLH system, a novel VLP system that utilizes the ubiquitous ambient light sensors (ALS) and wearable devices as receivers. L-PLH system simplifies the beacon recognition process through a dual selection mechanism that optimally configures LED transmission frequencies through the ALS’s integration effect and the undersampling principle. At the receiver, the Qin interpolation method effectively handles missing data, enhancing the clarity of aliased frequency peaks after fast Fourier transform (FFT) for robust decoding. Furthermore, we employ an improved genetic algorithm to globally optimize the Lambertian model coefficients, significantly improving distance estimation accuracy. Experimental results demonstrate that the L-PLH system achieves an average positioning error of 16.9 cm while maintaining milliwatt-level power consumption. The combination of high precision, low complexity, and ultra-low power consumption makes the L-PLH system suitable for practical portable applications like smartphone-based indoor navigation.