Aiming at the nonuniformity of the received optical power and low positioning precision in the indoor visible light positioning, a received signal strength indicator (RSSI) visible light positioning method is proposed based on adaptive flower pollination quantitative light source optimization scheme combined with improved radial basis function (RBF) based neural network. The adaptive flower pollination algorithm optimizes the light intensity of the transmitter processing the received uniform optical signal using an improved RBF-based neural network RSSI positioning method, resulting in accurate and effective positioning. The kernel principal component analysis K-means+ + (KPCA-K-means+ + )clustering model is used to preprocess the received RSSI sample value. The optimal cluster number and cluster center are obtained as the number and central value of the hidden layer neurons. The genetic algorithm and least mean square (GA-LMS) model is used to optimize the parameters of the RBF neural network. According to simulation results, the received optical power ranges from -28.6 dBm to -25.1 dBm in an indoor space of 9 m×12 m×3.5 m. Moreover, the positioning error is less than 0.1 m. Therefore, the proposed improved visible light positioning method has higher positioning accuracy and stronger practicability advantages.