A Task-Driven Invertible Projection Matrix Learning Algorithm for Hyperspectral Compressed Sensing

Abstract

The high complexity of the reconstruction algorithm is the main bottleneck of the hyperspectral image (HSI) compression technology based on compressed sensing. Compressed sensing technology is an important tool for retrieving the maximum number of HSI scenes on the ground. However, the complexity of the compressed sensing algorithm is limited by the energy and hardware of spaceborne equipment. Aiming at the high complexity of compressed sensing reconstruction algorithm and low reconstruction accuracy, an equivalent model of the invertible transformation is theoretically derived by us in the paper, which can convert the complex invertible projection training model into the coupled dictionary training model. Besides, aiming at the invertible projection training model, the most competitive task-driven invertible projection matrix learning algorithm (TIPML) is proposed. In TIPML, we don’t need to directly train the complex invertible projection model, but indirectly train the invertible projection model through the training of the coupled dictionary. In order to improve the accuracy of reconstructed data, in the paper, the singular value transformation is proposed. It has been verified that the concentration of the dictionary is increased and that the expressive ability of the dictionary has not been reduced by the transformation. Besides, two-loop iterative training is established to improve the accuracy of data reconstruction. Experiments show that, compared with the traditional compressed sensing algorithm, the compressed sensing algorithm based on TIPML has higher reconstruction accuracy, and the reconstruction time is shortened by more than a hundred times. It is foreseeable that the TIPML algorithm will have a huge application prospect in the field of HSI compression.

Parameter identification method of nonuniform and under-sampled blade tip timing based on extended DFT and compressed sensing

“…Any signal can usually be represented as a linear combination of a series of basic functions [31], that is, it exhibits sparsity in a certain transform domain, and the original signal can be restored by using these sparse signals [32]. The principle of the CS method is to directly collect the sparse signal in the transform domain or when the collected data are incomplete owing to objective conditions; the original signal is restored by constructing a transformation matrix and using a small number of measurement signals [33]. The specific process of CS is shown in figure 3 [34].…”

Editorial to Special Issue “Remote Sensing Data Compression”

“…The paper "A Task-Driven Invertible Projection Matrix Learning Algorithm for Hyperspectral Compressed Sensing" by Dai, S., Liu, W., Wang, Z., and Li, K. [15] proposes a hyperspectral compressed sensing algorithm with low complexity and strong real-time performance. It is based on a task-driven invertible projection matrix learning algorithm aiming at solving the problems of long time-consuming and low reconstruction accuracy of compressed sensing-based reconstruction algorithms.…”