基于群智感知的街景变化检测方法

he images and spatiotemporal contextual information contained in mobile crowdsensing data can be used to detect changes in street view images, but crowdsensing data are usually low-quality and non-standard. In order to accurately detect the changes in the street view, this paper mainly solves the problem caused by low-quality datum which have been collected from different shooting perspectives. First, for the problem of large parallax, the image registration method is used to initially align the images and extract the registration feature points; then, the region of interest is extracted from the image based on the distribution of the registration feature points; third, aiming at the error detection content of the difference image, a screening method based on area and multi-feature points is proposed to remove the error detection region; finally, the complete changing object is extracted by combining edge detection and superpixel segmentation algorithm. Compared with MDFNet method, when the image pairs change, the F1-measure value and error rate of our method are 55.8% and 10.8%, and they have increased by 6% and decreased by 24% respectively. When there are no changes, the error rate of our method is only 2.8% and it is reduced by about 28%.