研究目的
To propose a local adaptive contrast measure for robust infrared small target detection using gray and variance di?erence.
研究成果
The proposed method achieves promising target enhancement and background suppression performance on complicated real IR images. It outperforms baseline methods in terms of detection rate and false alarm rate.
研究不足
When a target is so far away from the imaging system that it only occupies 2–3 pixels in an image, the temporal cues in multiple frames should be used to extract targets. The method is not very e?cient due to the use of a sliding window to check all possible locations in an image.
1：Experimental Design and Method Selection:
The study employs a size-adaptive gray-level target enhancement process followed by an improved multiscale variance di?erence method for target enhancement and cloud clutter removal.
2：Sample Selection and Data Sources:
Two infrared image sequences with di?erent backgrounds were collected for testing.
3：List of Experimental Equipment and Materials:
Not explicitly mentioned.
4：Experimental Procedures and Operational Workflow:
The method involves extracting image patches with three windows from an IR image, calculating the maximum contrast measure, calculating the variance di?erence, multiplying the multiscale gray di?erence map with the multiscale variance di?erence map, and using adaptive-threshold segmentation to extract candidate targets.
5：Data Analysis Methods:
The performance is evaluated using Signal to Clutter Ratio Gain (SCRG), Background Suppression Factor (BSF), and Receiver Operating Characteristic (ROC) curves.
独家科研数据包，助您复现前沿成果，加速创新突破
获取完整内容
