There are two types of methods for image segmentation.One is traditional image processing methods,which are sensitive to details and boundaries,yet fail to recognize semantic information.The other is deep learning met...There are two types of methods for image segmentation.One is traditional image processing methods,which are sensitive to details and boundaries,yet fail to recognize semantic information.The other is deep learning methods,which can locate and identify different objects,but boundary identifications are not accurate enough.Both of them cannot generate entire segmentation information.In order to obtain accurate edge detection and semantic information,an Adaptive Boundary and Semantic Composite Segmentation method(ABSCS)is proposed.This method can precisely semantic segment individual objects in large-size aerial images with limited GPU performances.It includes adaptively dividing and modifying the aerial images with the proposed principles and methods,using the deep learning method to semantic segment and preprocess the small divided pieces,using three traditional methods to segment and preprocess original-size aerial images,adaptively selecting traditional results tomodify the boundaries of individual objects in deep learning results,and combining the results of different objects.Individual object semantic segmentation experiments are conducted by using the AeroScapes dataset,and their results are analyzed qualitatively and quantitatively.The experimental results demonstrate that the proposed method can achieve more promising object boundaries than the original deep learning method.This work also demonstrates the advantages of the proposed method in applications of point cloud semantic segmentation and image inpainting.展开更多
In this paper, I analyze pictorial representations of the Buddhist story of Mulian rescuing his mother in China, Japan, and Korea in the pre-modern and early modern periods. I have collected several pictorial versions...In this paper, I analyze pictorial representations of the Buddhist story of Mulian rescuing his mother in China, Japan, and Korea in the pre-modern and early modern periods. I have collected several pictorial versions of the Mulian story in these countries, and comparison shows close proximity of several such works. All of them are related to the narrative texts that represent elaboration of the originally scriptural story （it originated in the apocryphal Buddhist scripture that circulated in China） in vernacular languages. Images of the Mulian story in the countries of East Asia had diverse nature： they could appear as separate scenes in devotional religious paintings, multi-scene handscrolls, and illustrations in the manuscripts and editions. I argue that the subject of Mulian rescuing his mother was of primary importance in the popularization of Buddhist ideas among different layers of society. The related images were used for both storytelling and reading practices and helped different audiences to comprehend the Mulian story.展开更多
基金funded in part by the Equipment Pre-Research Foundation of China,Grant No.61400010203in part by the Independent Project of the State Key Laboratory of Virtual Reality Technology and Systems.
文摘There are two types of methods for image segmentation.One is traditional image processing methods,which are sensitive to details and boundaries,yet fail to recognize semantic information.The other is deep learning methods,which can locate and identify different objects,but boundary identifications are not accurate enough.Both of them cannot generate entire segmentation information.In order to obtain accurate edge detection and semantic information,an Adaptive Boundary and Semantic Composite Segmentation method(ABSCS)is proposed.This method can precisely semantic segment individual objects in large-size aerial images with limited GPU performances.It includes adaptively dividing and modifying the aerial images with the proposed principles and methods,using the deep learning method to semantic segment and preprocess the small divided pieces,using three traditional methods to segment and preprocess original-size aerial images,adaptively selecting traditional results tomodify the boundaries of individual objects in deep learning results,and combining the results of different objects.Individual object semantic segmentation experiments are conducted by using the AeroScapes dataset,and their results are analyzed qualitatively and quantitatively.The experimental results demonstrate that the proposed method can achieve more promising object boundaries than the original deep learning method.This work also demonstrates the advantages of the proposed method in applications of point cloud semantic segmentation and image inpainting.
文摘In this paper, I analyze pictorial representations of the Buddhist story of Mulian rescuing his mother in China, Japan, and Korea in the pre-modern and early modern periods. I have collected several pictorial versions of the Mulian story in these countries, and comparison shows close proximity of several such works. All of them are related to the narrative texts that represent elaboration of the originally scriptural story （it originated in the apocryphal Buddhist scripture that circulated in China） in vernacular languages. Images of the Mulian story in the countries of East Asia had diverse nature： they could appear as separate scenes in devotional religious paintings, multi-scene handscrolls, and illustrations in the manuscripts and editions. I argue that the subject of Mulian rescuing his mother was of primary importance in the popularization of Buddhist ideas among different layers of society. The related images were used for both storytelling and reading practices and helped different audiences to comprehend the Mulian story.
