To address ssues such as low real-time performance and high resource consumption in existing grayscale image algorithms for airborne target feature analysis on strongly physically constrained platforms, this study proposes a multivariate statistical parameter representation approach based on mean, variance, entropy, and energy. The feasibility and data validation of this method for characterizing feature changes in continuous grayscale images of airborne targets are conducted. Experimental results demonstrate that the set of multivariate statistical parameters can effectively characterize the process of imaging field of view approaching the target aircraft, the process of AIM-9X hitting the target aircraft with flashes and smoke, and the process of target aircraft exploding and disintegrating in continuous grayscale images. The analysis confirms the feasibility of using these multivariate statistical parameters to characterize the feature changes of airborne targets in continuous grayscale images. The analytical process provides new insights for trend judgment and predictive analysis of continuous airborne target changes under stringent platform constraints.