A Study on IR Target Recognition Approach in Aerial Jamming Environment Based on Bayesian Probabilistic Model

Abstract

The use of infrared (IR) decoys as a countermeasure has become a significant and important factor that influences the performance of heat-seeking missiles. The system employed by such missiles utilizes a template matching algorithm that relies on the infrared characteristics of the target. This target feature vector is compared against the features of nearby objects using minimum distance classification criterion. One of the problems is that it is very difficult to efficiently consider every possible jamming condition. This paper confronts the issue using Bayesian methods to build a probabilistic recognition model that performs well in an aerial jamming environment. Our approach is based on simulating the partial reasoning functions of human visual cognition, where the Bayesian component is used to handle uncertainty. Dealing with ambiguity, such as distinguishing between target and decoy, requires a properly trained model. Our solution, in part, is to conduct a feature histogram analysis on a large set of data that are generated by using a simulated method. This produces a feature probability model with a mixed Gaussian distribution. The maximum likelihood estimation is performed to determine the class of the object, and as such distinguish between genuine targets and decoys. We extend this to construct a new aerial IR target recognition algorithm that relies on both prior information and our probabilistic recognition model. Our empirical analysis includes simulated aerial combat images that are generated for the purpose of testing our method. The experimental results indicate that our approach shows an improvement in performance when compared to the feature template matching approach.

Computer Image Scene and Object Information Extraction based on Bayesian Network Model

“…After determining, the conditional probability p 𝑝(𝑥 𝑖 |𝑐) determines the value of the entire posterior probability.Suppose that the number of scene class 𝑥 𝑖 adjacent to the building target in the positive sample image is p, the total number of positive samples ism,then the probability is 𝑝(𝑥 𝑖 = "𝑡𝑢𝑟𝑒"|𝑐 = "𝑡𝑢𝑟𝑒") = ( 𝑝 𝑚 ); the number of scene class 𝑥 𝑖 adjacent to the building target in the negative sample image is q, the total number of negative samples is n, then the probability 𝑝(𝑥 𝑖 = "𝑡𝑢𝑟𝑒"|𝑐 = "𝑓𝑎𝑙𝑠𝑒") = ( 𝑞 𝑛 ) . Other posterior probabilities are obtained by the complementarity rule [15].…”

Analysis of the Influence of Trace Point Step-Jump Behavior

“…Actually, the effects of flares mainly include two aspects: one is disturbing the seeker system to prevent the missile from recognizing true targets and the other is disturbing the guidance system by generating abnormal overload signals and causing the missile to become unstable. To tackle the first matter, Li et al [23] utilized the Bayesian method to build a probabilistic recognition model, which is more efficient than the feature template matching approach. Likewise, Wu et al [24] revealed the inherent structure and infrared signature of the aircraft and provided an anti-interference method after exploiting the occlusion detection.…”