Dense Stereo Matching Algorithm Based on Image Segmentation

Ruihao, 马瑞浩 Ma; Feng, 朱枫 Zhu; Qingxiao, 吴清潇 Wu; Rongrong, 鲁荣荣 Lu; Jingyang, 魏景阳 Wei

doi:10.3788/aos201939.0315001

Cited by 5 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many researchers have conducted extensive and in-depth research on these algorithms. For instance, Ma et al [42] proposed an algorithm based on image segmentation in which the image was segmented by simple linear iterative clusters. An image test with the Middlebury dataset showed that the mismatch rate of the whole region was 5.275%, the mismatch rate of shaded regions was 7.370%, and the mismatch rate of unshaded regions was 2.315%; the comprehensive average mismatch rate was 4.990%.…”

Section: Overview Of Stereo Vision Matchingmentioning

confidence: 99%

Coal Mine Rescue Robots Based on Binocular Vision: A Review of the State of the Art

Zhai

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Rescue work after a coal mine accident is fraught with challenges and dangers. Considering the safety of rescue workers and the urgency of a rescue mission, it is necessary to use coal mine rescue robots to perform the tasks of environmental detection and rescue. As a key part of the robot sensing system, a visual sensor can provide much information about a scene. Among vision sensor types, binocular vision has the advantages of being noncontact and passive, and it is the key technology for a robot to acquire obstacle information and reconstruct a three-dimensional scene. Therefore, coal mine rescue robots based on binocular vision have become a popular research topic in the field of mine safety. First, the research status of camera calibration and stereo vision matching for binocular vision is systematically introduced in this paper. Second, the latest research progress on coal mine rescue robots based on binocular vision is reviewed from the perspective of technological applications and development. Finally, the technical challenges and future development trends of binocular vision in coal mine rescue robots are described. INDEX TERMS Coal mine rescue robots, binocular vision, camera calibration, stereo vision matching.

show abstract

Section: Overview Of Stereo Vision Matchingmentioning

confidence: 99%

Coal Mine Rescue Robots Based on Binocular Vision: A Review of the State of the Art

Zhai

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

Research on Automatic Detection Method of Part Shape Based on Projection Optics and Image Processing

Sun

Wang

et al. 2019

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

Block Adjustment of Large-scale Domestic Optical Satellite Remote Sensing Imagery without GCP in Antarctic

Wang

Xiang

et al. 2020

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Aiming to the difficult area of surveying and mapping, such as Antarctic, it is difficult to guarantee favourable observation condition for traditional mapping methods. Large-scale block adjustment (BA) without ground control point (GCP) is carried out by using domestic high-resolution satellite remote sensing imagery. The key technologies of BA model construction based on virtual control point (VCP), gross error detection and elimination, and robust and fast method of large-scale BA are studied in this paper. On this basis, the experimental analysis and validation of 13pairs (39 images) of ZY-3 satellite imagery in Antarctic are carried out. The results show that the sparse matrix technology can effectively reduce the memory requirement. The combined matrix block and GPU parallel technology can solve the problem of large-scale BA computational efficiency. In addition, after BA, the maximum residual is 3.920 pixel, the root mean square error (RMSE) is 0.169 pixel in the X (flight) direction, the maximum residual error is 5.933 pixel, and the RMSE is 0.191 pixel in the Y (scan) direction. The proposed method has certain accuracy and stability in large-scale BA without GCP using high-resolution satellite remote sensing imagery in Antarctica. The relative positioning accuracy can reach sub-pixel level, which can meet the requirements of cartographic splicing.

show abstract

Dense Stereo Matching Algorithm Based on Image Segmentation

Cited by 5 publications

References 0 publications

Coal Mine Rescue Robots Based on Binocular Vision: A Review of the State of the Art

Coal Mine Rescue Robots Based on Binocular Vision: A Review of the State of the Art

Research on Automatic Detection Method of Part Shape Based on Projection Optics and Image Processing

Block Adjustment of Large-scale Domestic Optical Satellite Remote Sensing Imagery without GCP in Antarctic

Contact Info

Product

Resources

About