Infrared moving small target detection method of a complex scene

Abstract

The invention discloses an infrared moving small target detection method of a complex scene, which mainly comprises the following steps: 1) extracting a moving target area. 2) The image is divided into two parts: foreground and background according to the gray characteristics of the image. 3) Optical flow estimation is performed on the extracted moving target region by optical flow method, and thetarget motion vector information is extracted. 4) The extracted moving target region is morphologically filtered, the connected regions of the filtered moving target region are analyzed, and different moving target regions are identified. 5) the detection probability of the connected region is set, and the number of sample characteristic quantities to be detected in the connected region is determined. All connected domains are randomly sampled. The invention reduces the complexity of the algorithm, improves the detection accuracy rate, and effectively solves the problems of target misdetection, missed detection and mismatch caused by the large difference between the background and the target and the partial occlusion of the target.

Description

technical field [0001] The invention relates to the field of infrared detection, in particular to a method for detecting small moving infrared targets in complex scenes. Background technique [0002] The traditional detection methods of infrared moving targets include background difference, optical flow method, and frame difference method. The frame difference method is based on the time difference of pixels, and the moving area is segmented and extracted through binarization. It is not easily affected by light, but it is sensitive to environmental noise, resulting in incomplete target detection. The optical flow method estimates the motion field according to the spatiotemporal gradient of the image sequence, and detects the moving object by analyzing the changes of the motion field. The detection accuracy is high, but the calculation process is relatively complicated, and the real-time operation needs to be improved. Using the mean shift algorithm can complete the detectio...

AI Technical Summary

Problems solved by technology

[0002] The traditional detection methods of infrared moving targets include background difference, optical flow method, and frame difference method. The frame difference method is based on the time difference of pixels, and the motion area is segmented and extracted through binarization. It is not easily affected by light, but it is more sensitive to environmental noise, resulting in incomplete target detection.

The optical flow method estimates the motion field based on the spatio-temporal gradient of the image sequence, and detects the moving object by analyzing the changes of the motion field. The detection accuracy is high, but the calculation process is relatively complicated, and the real-time operation needs to be improved.

Using the mean shift algorithm can complete the detection process well in the case of edge occlusion and uneven background motion. It is a non-parametric estimation method that does not require prior knowledge, but it needs to iterate the feature quantity of each pixel value. Calculation, large amount of calculation, poor real-time performance

[0003] In summary, the above algorithm can achieve better detection results in a high SNR environment, but in a complex background, it is susceptible to ground background interference, such as illumination changes, background disturbances, shadows, and the number of targets and the speed of movement have differences. Randomness makes it difficult to balance the accuracy and real-time performance of existing infrared target detection algorithms

When the target is partially occluded and the ratio of the target to the background is quite different, existing algorithms are prone to target loss and mismatching, resulting in reduced detection accuracy

Images