昏暗背景下视频图像对比度低,通常的检测算法很难实现对运动目标的检测。提出了一种基于视频增强的昏暗背景下目标检测方法,首先通过直方图均衡与时空混合高斯滤波相结合的方法进行视频增强,然后对增强后的视频用传统检测方法进行目标检测。实验表明该方法在昏暗背景下能较好地检测出运动目标,具有较强的鲁棒性。
The contrast of images in the video with caliginous background is low, general methods are difficuh to detect the target in caliginous background. This paper presents a method for the detection of moving targets in caliginous background based on video enhancement. We first use histogram equalization and spatio-temporal gaussian filtering to enhance the quality of the video. After video enhancement, we use the conventional method to detect the moving target. Results on real image sequences illustrate the efficiency of the proposed method in any caliginous background.