目前基于学习的多视图三维重建研究已经取得了显著成果,但依然存在特征提取不完全和成本代价体之间相关性差的问题,从而导致重建精度不高。针对这一问题,设计了一种级联网络PAA-MVSNet。为了获得输入图像更加完整和准确的特征信息,该模...目前基于学习的多视图三维重建研究已经取得了显著成果,但依然存在特征提取不完全和成本代价体之间相关性差的问题,从而导致重建精度不高。针对这一问题,设计了一种级联网络PAA-MVSNet。为了获得输入图像更加完整和准确的特征信息,该模型采用了“自顶向下”的特征提取方法,在不同尺度上进行特征提取,并将这些特征进行拼接,最后输出3个不同尺度的特征层;此外,引入改进的SE注意力模块优化三维代价体正则化过程,增强了代价体成本体积之间的相关性,提高了重建的精度和完整性。在DTU数据集上和基准网络CasMVSNet相比,该模型的准确性误差和完整性误差指标分别降低了5%和1.4%,且相较于其他模型均有不同程度提升。此外Tanks and Temples数据集上的实验结果表明,该模型有很好的泛化性。提出的基于路径聚合的特征提取模块和注意力优化代价体正则化模块均取得了效果,在重建精度上相比于其他模型都有一定的提升,验证了该模型的有效性。展开更多
An approach to addressing the stereo correspondence problem is presented using genetic algorithms (GAs) to obtain a dense disparity map. Different from previous methods, this approach casts the stereo matching as a mu...An approach to addressing the stereo correspondence problem is presented using genetic algorithms (GAs) to obtain a dense disparity map. Different from previous methods, this approach casts the stereo matching as a multi-extrema optimization problem such that finding the fittest solution from a set of potential disparity maps. Among a wide variety of optimization techniques, GAs are proven to be potentially effective methods for the global optimization problems with large search space. With this idea, each disparity map is viewed as an individual and the disparity values are encoded as chromosomes, so each individual has lots of chromosomes in the approach. Then, several matching constraints are formulated into an objective function, and GAs are used to search the global optimal solution for the problem. Furthermore, the coarse-to-fine strategy has been embedded in the approach so as to reduce the matching ambiguity and the time consumption. Finally, experimental results on synthetic and real images show the performance of the work.展开更多
Propeller blade width measurement has been extensively studied in the past using direct and indirect methods, and it plays a great role in determining the quality of the finished products. It has surveyed that previou...Propeller blade width measurement has been extensively studied in the past using direct and indirect methods, and it plays a great role in determining the quality of the finished products. It has surveyed that previous techniques are usually time-consuming and erroneous due to a large number of points to be processed in blade width measurement. This paper proposes a new method of measuring blade width using two images acquired from different viewpoints of the same blade. And a new feature points matching approach for propeller blade image is proposed in stereo vision measurement. Based on these, pixel coordinates of contour points of the blade in two images are extracted and converted to real world coordinates by image algorithm and binocular stereo machine vision theory. Then, from the real world coordinates, the blade width at any position can be determined by simple geometrical method.展开更多
Aiming at the shortcoming that certain existing blockingmatching algorithrns, such as full search, three-step search, and dia- mond search algorithms, usually can not keep a good balance between high acoaracy and low ...Aiming at the shortcoming that certain existing blockingmatching algorithrns, such as full search, three-step search, and dia- mond search algorithms, usually can not keep a good balance between high acoaracy and low computational complexity, a block-maching motion estimation algorithm based on two-step search is proposed in this paper. According to the fact that the gray values of adjacent pixels will not vary fast, the algorithm employs an interlaced search pattem in the search window to estimate the motion vector of the objectblock. Simulation and actual experiments demanstrate that the proposed algmithm greatly outperforms the well-known three-step search and dianond search algoritlam, no matter the motion vector is large or small. Comparedc with the full search algorithm, the proposed one achieves similar peffomance but requires much less computation, therefore, the algorithm is well qualified for real-time video image processing.展开更多
文摘目前基于学习的多视图三维重建研究已经取得了显著成果,但依然存在特征提取不完全和成本代价体之间相关性差的问题,从而导致重建精度不高。针对这一问题,设计了一种级联网络PAA-MVSNet。为了获得输入图像更加完整和准确的特征信息,该模型采用了“自顶向下”的特征提取方法,在不同尺度上进行特征提取,并将这些特征进行拼接,最后输出3个不同尺度的特征层;此外,引入改进的SE注意力模块优化三维代价体正则化过程,增强了代价体成本体积之间的相关性,提高了重建的精度和完整性。在DTU数据集上和基准网络CasMVSNet相比,该模型的准确性误差和完整性误差指标分别降低了5%和1.4%,且相较于其他模型均有不同程度提升。此外Tanks and Temples数据集上的实验结果表明,该模型有很好的泛化性。提出的基于路径聚合的特征提取模块和注意力优化代价体正则化模块均取得了效果,在重建精度上相比于其他模型都有一定的提升,验证了该模型的有效性。
文摘An approach to addressing the stereo correspondence problem is presented using genetic algorithms (GAs) to obtain a dense disparity map. Different from previous methods, this approach casts the stereo matching as a multi-extrema optimization problem such that finding the fittest solution from a set of potential disparity maps. Among a wide variety of optimization techniques, GAs are proven to be potentially effective methods for the global optimization problems with large search space. With this idea, each disparity map is viewed as an individual and the disparity values are encoded as chromosomes, so each individual has lots of chromosomes in the approach. Then, several matching constraints are formulated into an objective function, and GAs are used to search the global optimal solution for the problem. Furthermore, the coarse-to-fine strategy has been embedded in the approach so as to reduce the matching ambiguity and the time consumption. Finally, experimental results on synthetic and real images show the performance of the work.
基金Supported by the Natural Science Foundation of China (50975133)the Innovative Foundation for Ph.D of the Jiangsu Province, China (2010-227)
文摘Propeller blade width measurement has been extensively studied in the past using direct and indirect methods, and it plays a great role in determining the quality of the finished products. It has surveyed that previous techniques are usually time-consuming and erroneous due to a large number of points to be processed in blade width measurement. This paper proposes a new method of measuring blade width using two images acquired from different viewpoints of the same blade. And a new feature points matching approach for propeller blade image is proposed in stereo vision measurement. Based on these, pixel coordinates of contour points of the blade in two images are extracted and converted to real world coordinates by image algorithm and binocular stereo machine vision theory. Then, from the real world coordinates, the blade width at any position can be determined by simple geometrical method.
基金supported by the Lab Open Fund of Beijing Microchemical Research Institute(P2008026EB)
文摘Aiming at the shortcoming that certain existing blockingmatching algorithrns, such as full search, three-step search, and dia- mond search algorithms, usually can not keep a good balance between high acoaracy and low computational complexity, a block-maching motion estimation algorithm based on two-step search is proposed in this paper. According to the fact that the gray values of adjacent pixels will not vary fast, the algorithm employs an interlaced search pattem in the search window to estimate the motion vector of the objectblock. Simulation and actual experiments demanstrate that the proposed algmithm greatly outperforms the well-known three-step search and dianond search algoritlam, no matter the motion vector is large or small. Comparedc with the full search algorithm, the proposed one achieves similar peffomance but requires much less computation, therefore, the algorithm is well qualified for real-time video image processing.
