Dim and Small Target Detection Method via Gradient Features Guided Local Contrast

Small and dim target detection is a longstanding challenge in computer vision because of conditions, such as target scale variations and strong clutter. This article provides an innovative and efficient algorithm for detecting small targets. By utilizing a novel approach, our algorithm achieves superior performance in the presence of challenging environmental conditions, it suppresses the background and enhances the target via gradient features guided local contrast (GFLC). To begin, we leverage the gradient properties of the image to mitigate the background noise. Subsequently, local contrast features are utilized to accentuate the target area in the original image. The fusion map is then computed by combining the above features. Finally, the targets are efficiently extracted from the fusion map via segmentation. The findings indicate that the algorithm we presented achieves outstanding accuracy in detecting targets in images with intricate backgrounds and low contrast, and it effectively suppresses background noise.