Redirigiendo al acceso original de articulo en 23 segundos...
ARTÍCULO
TITULO

Weakly-Supervised Image Semantic Segmentation Based on Superpixel Region Merging

Resumen

In this paper, we propose a semantic segmentation method based on superpixel region merging and convolutional neural network (CNN), referred to as regional merging neural network (RMNN). Image annotation has always been an important role in weakly-supervised semantic segmentation. Most methods use manual labeling. In this paper, super-pixels with similar features are combined using the relationship between each pixel after super-pixel segmentation to form a plurality of super-pixel blocks. Rough predictions are generated by the fully convolutional networks (FCN) so that certain super-pixel blocks will be labeled. We perceive and find other positive areas in an iterative way through the marked areas. This reduces the feature extraction vector and reduces the data dimension due to super-pixels. The algorithm not only uses superpixel merging to narrow down the target’s range but also compensates for the lack of weakly-supervised semantic segmentation at the pixel level. In the training of the network, we use the method of region merging to improve the accuracy of contour recognition. Our extensive experiments demonstrated the effectiveness of the proposed method with the PASCAL VOC 2012 dataset. In particular, evaluation results show that the mean intersection over union (mIoU) score of our method reaches as high as 44.6%. Because the cavity convolution is in the pooled downsampling operation, it does not degrade the network’s receptive field, thereby ensuring the accuracy of image semantic segmentation. The findings of this work thus open the door to leveraging the dilated convolution to improve the recognition accuracy of small objects.

Palabras claves

 Artículos similares

       
 
Yuting Chen, Pengjun Zhao, Yi Lin, Yushi Sun, Rui Chen, Ling Yu and Yu Liu    
Precise identification of spatial unit functional features in the city is a pre-condition for urban planning and policy-making. However, inferring unknown attributes of urban spatial units from data mining of spatial interaction remains a challenge in ge... ver más

 
Ai-Sheng Wang, Zhang-Cai Yin and Shen Ying    
The possibility of moving objects accessing different types of points of interest (POIs) at specific times is not always the same, so quantitative time geography research needs to consider the actual POI semantic information, including POI attributes and... ver más

 
Xuejing Xie, Yongyang Xu, Bin Feng and Wenjun Wu    
The classification of urban functional areas is important for understanding the characteristics of urban areas and optimizing the utilization of urban land resources. Existing related methods have improved accuracy. However, they neglect cognitive differ... ver más

 
Zhixin Li, Song Ji, Dazhao Fan, Zhen Yan, Fengyi Wang and Ren Wang    
Accurate building geometry information is crucial for urban planning in constrained spaces, fueling the growing demand for large-scale, high-precision 3D city modeling. Traditional methods like oblique photogrammetry and LiDAR prove time consuming and ex... ver más

 
Kegong Shi, Jinjin Yan and Jinquan Yang    
Reasonable semantic partition of indoor areas can improve space utilization, optimize property management, and enhance safety and convenience. Existing algorithms for such partitions have drawbacks, such as the inability to consider semantics, slow conve... ver más