Infrared target detecting, tracking and identifying system

Abstract

The invention is a kind of infrared object tracing and identifying system which includes infrared imaging, infrared image receiving, infrared image processing and image and result displaying. The infrared image is acquired through the infrared imaging device, the digital image data and output control signal are transmitted to the infrared image receiving part through digital output difference port and difference single-end circuit, the receiving part of the image uses field programmable gate array FPGA to receive 14 bits difference signal, then the data is transmitted to the infrared image processing part double digital signal processor DSP board system through token bus, carries on object detecting and tracing and identifying to the infrared image, the processing result and the original data is transmitted to the monitor through the computer bus.

Description

Technical field: [0001] The invention relates to an infrared target detection, tracking and recognition system, which is a hardware platform designed to obtain high-performance infrared target images, and to detect, track and recognize infrared image targets, and is a passive infrared detection system based on an advanced staring focal plane array. It can be widely used in advanced weapon systems, security surveillance, intelligent transportation and industrial automation detection and other fields. Background technique: [0002] With the development of infrared detector technology, thermal imaging cameras have developed from the past using unit or multiple discrete detectors plus one-dimensional or two-dimensional optical-mechanical scanners to staring imaging devices that do not require optical-mechanical scanning. The infrared thermal imaging detection system based on the staring focal plane array has greatly improved both in terms of temperature sensitivity and spatial r...

AI Technical Summary

Problems solved by technology

[0004] 1. The target has no information such as size, shape and texture, and traditional image processing methods cannot be applied;

[0005] 2. The fluctuating background makes the target signal often submerged in the noise;

[0006] 3. The amount of data is large and difficult to process in real time

[0007] Researchers at home and abroad have proposed some methods for target detection, tracking and recognition in low signal-to-noise ratio infrared images, such as three-dimensional matched filter, truncated sequential likelihood ratio detection method, dynamic programming method, high-order correlation method, wavelet analysis and neural network methods, etc., but the calculation is very large, and it is difficult to process video image sequences in real time

In addition, the shortcomings that significantly restrict the practical application of the above algorithms are mainly due to the fact that various algorithms are based on the noise distribution and even the target distribution as prior knowledge.

Although the above assumptions bring great convenience to the detection algorithm design, algorithm performance analysis and result analysis, in actual situations, most of the cases do not satisfy the assumption distribution, which inevitably introduces errors and even leads to wrong conclusions

Images