A dataset for infrared image dim-small aircraft target detection and tracking under ground / air background

Dim-small target detection and tracking in infrared images is the main research content for long-range precision strike, aerospace defense confrontation, battlefield intelligence and reconnaissance. However, the simulation infrared data is not perfect and measured data lacks of samples in areas of infrared target detection and recognition. In response to this situation, we focus dim-small target detection and tracking of low altitude flying target, and provide a group of data for one or multiple fixed-wing UAV targets via outfield recording and post data processing. The data acquisition scenario covers sky background and complex field background. Dataset includes 22 image sequences, 30 trajectories, 16177 frames and 16944 targets. Each target correspond a label location in the image, and each image sequence correspond a label file. This dataset can serve researches on infrared target characteristics, dim-small object detection and precision guidance. Dataset in detail: http://www.csdata.org/p/387/.