Image Semantic Segmentation Algorithm Based On Superpixels And Conditional Random Fields

As the key to build intelligent vision system,the computer vision has always been the focus of attention of researchers.Image semantic segmentation is one of the most important basic issues,and its research results have been widely used in many fields,highlighting important academic value and practical significance.In recent years,the development of deep learning has achieved very constructive breakthroughs in the field of computer vision.Although existing image semantic segmentation methods based on deep learning can extract high-level semantic features of images,there are still the problem of lacking image details such as image edges and textures.Based on the existing deep learning model,an improved image semantic segmentation method based on superpixels and conditional random fields is proposed.Firstly,this paper uses the existing feature extraction model based on deep learning to obtain rough semantic segmentation results,including high-level semantic information of the image but lacking details of the image.At the same time,the superpixel segmentation algorithm is applied to obtain superpixels that carries more low-level information.Secondly,due to the lack of image details in rough segmentation results,the segmentation of the edge of the image is inaccurate.In this paper,an boundary optimization algorithm is proposed to optimize the edge segmentation accuracy of the rough results.The edge segmentation effect in the rough results is preliminarily optimized using superpixels.Finally,the use of superpixels for local boundary optimization can improve the segmentation accuracy,but the final segmentation result lacks accurate boundary information and structural information due to the insufficient use of other details.In order to further improve the segmentation accuracy,the fully connected conditional random field is used to constrain the pixels with similar color and spatial position,and make full use of the local texture features,global context information and smooth priors to further optimize the semantic segmentation results of the image.In order to measure the performance of the improved method proposed in this paper,the experiments on the improved method and two other state-of-the-art methods are carried out on the benchmark dataset PASCAL VOC 2012 and the famous urban scenery dataset Cityscapes.Experimental results show that compared with other image semantic segmentation methods,the improved method presented in this paper has achieved the best results on both datasets,and has improved both in pixel accuracy and segmentation accuracy.The experimental data proves that the improved method proposed in this paper not only can effectively extract the high-level semantic information of the image,but also can retain more detailed information,while it has strong robustness.The proposed method is expected to be applied to the field with high accuracy requirement.