The range migration algorithm (RMA) based on Fourier transformation is widely applied in millimeter-wave (MMW) close-range imaging because of its few operations and small approximation. However, its interpolation stage is not effective due to the involved intensive logic controls, which limits the speed performance in a graphics processing unit (GPU) platform. Therefore, in this paper, we present an acceleration optimization method based on the hybrid GPU and central processing unit (CPU) parallel computation for implementing the RMA. The proposed method exploits the strong logic-control capability of the CPU to assist the GPU in processing the logic controls of the interpolation stage. The common positions of wavenumber-domain components to be interpolated are calculated by the CPU and stored in the constant memory for broadcast at any time. This avoids the repetitive computation consumed in a GPU-only scheme. Then the GPU is responsible for the remaining matrix-related steps and outputs the needed wavenumber-domain values. The imaging experiments verify the acceleration efficiency of the proposed method and demonstrate that the speedup ratio of our proposed method is more than 15 times of that by the CPU-only method, and more than 2 times of that by the GPU-only method.

The three-dimensional (3D) millimeter-wave (MMW) image is a big data with redundant information that not only blurs the image but also increases the computational load on the denoising procedure. To address this problem, we propose an intensity-density associative clustering method which mainly consists of two phases. Specifically, an intensity-based clustering algorithm, e.g., K-Means, is firstly applied on the amplitude of the image data and initially achieves denoising and data compression. Then, a density-based spatial clustering algorithm, e.g., DBSCAN, is used to further extract object information. Due to the label transferring from the retained amplitude, only valid image data can forward spatial information to DBSCAN, and as a result, the computational load on DBSCAN decreases. Also, a multithreaded parallel computing framework is developed to exploit the distributed multicore processing for its implementation. Therefore, the proposed method can be well-adapted for 3D MMW image data in a computational efficient way. Simulations and experimental results confirm the effectiveness of our method that has good efficiency on big MMW image data with respect to the noise suppression and object information extraction.