Instance segmentation generates pixel - level segmentation masks for each object based on image classification, which iscurrently one of the popular research?topics and challenging tasks in computer vision. To address the problems of poor segmentationaccuracy and robustness of current algorithms,we propose an?
improved SOLOV2 algorithm. Firstly,FCN ( Fully Convolutional Networksfor Semantic Segmentation) is used as the overall framework,and ResNext is adopted?
as the backbone network,which can effectivelyimprove the accuracy of the network without raising the number of network parameters and computational effort. Secondly,a modifiedNAS-FPN ( Neural Architecture Search Feature Pyramid Network) is used as the feature pyramid network structure,which is a structurethat?
allows the search and combination of feature maps in the FPN,so that the network can re - search and fuse the already extractedfeature maps,as a solution to the problem that the network cannot fully perceive the feature maps and thus the network accuracy is nothigh. Finally, the whole segmentation network model is obtained by adjusting the hyperparameters. The experimental analysis andcomparison on the COCO2017 dataset and the BDD100K dataset shows that the improved SOLOV2 instance segmentation algorithmachieves 41. 8% accuracy,which improves the network accuracy by 2. 1% while taking into account the real - time performance. It isproved through experiments that the improved algorithm can adapt to a variety of traffic scenes and can complete the detection and segmentation of traffic scene targets.