Research On Environmental Modeling Technology For Auto-parking System

For its enormous market demand, Auto-parking system has come to be a hot research topic in Intelligent Vehicle research area recently. Environmental modeling for parking spaces is one of the key technologies of Auto-parking system. To develop the HQ3 Auto-parking system, this thesis presented a new method of environmental modeling technology for parking spaces based on the image mosaic technology assisted with the ultrasonic information. The main work and innovations of this thesis can be concluded as follows:1. Considering the characteristics of the parking spaces image, two pre-processing technologies were presented to improve the results of image mosaicing:firstly, the Adaptive Non-maximal Suppression method (ANMS) was introduced in choosing corners, which improving the distribute characteristic of the corners and the accuracy of the image matching; secondly, the Inverse Perspective Mapping(IMP) is introduced to transform the images, which partially eliminate the perspective effects of the original images and then successfully solve the difficulty of image mosaic for two images with too different view angles.2. To mosaic the images of parking space, image registration techniques were studied deeply. As the result, an improved RANSAC method and a voting method based on the parameters'histogram were presented, which effectively improved the accuracy of the registration parameter's estimation from the corrupted matching points. The experiments on real images proved that this method was simple and effective.3. Synthetically utilizing the above-mentioned research results, and combining with the ultrasonic information, a parking spaces environmental modeling system based on human-computer interaction was developed, which ensured that the development of "Hongqi HQ3" Auto-parking system went on wheels.