TY - GEN
T1 - MTStereo 2.0
T2 - 19th International Conference on Computer Analysis of Images and Patterns, CAIP 2021
AU - Brandt, Rafaël
AU - Strisciuglio, Nicola
AU - Petkov, Nicolai
N1 - Funding Information:
This work was partially funded by the EU H2020 program, under the Bot2020 (grant No. 688007).
Publisher Copyright:
© 2021, Springer Nature Switzerland AG.
PY - 2021
Y1 - 2021
N2 - Efficient yet accurate extraction of depth from stereo image pairs is required by systems with low power resources, such as robotics and embedded systems. State-of-the-art stereo matching methods based on convolutional neural networks require intensive computations on GPUs and are difficult to deploy on embedded systems. In this paper, we propose MTStereo2.0, an improved version of the MTStereo stereo matching method, which includes a more robust context-driven cost function, better detection of incorrect matches and the computation of disparity at pixel level. MTStereo provides accurate sparse and semi-dense depth estimation and does not require intensive GPU computations. We tested it on several benchmark data sets, namely KITTI 2015, Driving, FlyingThings3D, Middlebury 2014, Monkaa and the TrimBot2020 garden data sets, and achieved competitive accuracy. The code is available at https://github.com/rbrandt1/MaxTreeS.
AB - Efficient yet accurate extraction of depth from stereo image pairs is required by systems with low power resources, such as robotics and embedded systems. State-of-the-art stereo matching methods based on convolutional neural networks require intensive computations on GPUs and are difficult to deploy on embedded systems. In this paper, we propose MTStereo2.0, an improved version of the MTStereo stereo matching method, which includes a more robust context-driven cost function, better detection of incorrect matches and the computation of disparity at pixel level. MTStereo provides accurate sparse and semi-dense depth estimation and does not require intensive GPU computations. We tested it on several benchmark data sets, namely KITTI 2015, Driving, FlyingThings3D, Middlebury 2014, Monkaa and the TrimBot2020 garden data sets, and achieved competitive accuracy. The code is available at https://github.com/rbrandt1/MaxTreeS.
KW - Max-Tree
KW - Stereo matching
UR - http://www.scopus.com/inward/record.url?scp=85119375173&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-89128-2_11
DO - 10.1007/978-3-030-89128-2_11
M3 - Conference contribution
AN - SCOPUS:85119375173
SN - 978-3-030-89127-5
T3 - Lecture Notes in Computer Science
SP - 110
EP - 119
BT - Computer Analysis of Images and Patterns - 19th International Conference, CAIP 2021, Proceedings
A2 - Tsapatsoulis, Nicolas
A2 - Panayides, Andreas
A2 - Theocharides, Theo
A2 - Lanitis, Andreas
A2 - Lanitis, Andreas
A2 - Pattichis, Constantinos
A2 - Pattichis, Constantinos
A2 - Vento, Mario
PB - Springer
Y2 - 28 September 2021 through 30 September 2021
ER -