Learning-Based Template Matching for Robot Arm Grasping

Le, Minh-Tri; Lien, Jenn-Jier James

doi:10.1109/smc52423.2021.9659240

Cited by 2 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the first stage of the proposed model, the object position is estimated using a learning-based template-matching algorithm. In detail, the learning-based templatematching algorithm is enhanced from our previous work Le and Lien (2021). In that work, based on the density of the high similarity scores of the measurement process, the confused similarity scores (note that confused matching scores are defined here as high similarity scores between template image and wrong targets) were detected and removed during the matching process.…”

Section: Introductionmentioning

confidence: 99%

Robot arm grasping using learning-based template matching and self-rotation learning network

Lien

2022

Int J Adv Manuf Technol

Self Cite

View full text Add to dashboard Cite

Applying deep neural network models to robot-arm grasping tasks requires the laborious and time-consuming annotation of a large number of representative examples in the training process. Accordingly, this work proposes a two-stage grasping model, in which the first stage employs learningbased template matching (LTM) algorithm for estimating the object position, and a self-rotation learning (SRL) network is then proposed to estimate the rotation angle of the grasping objects in the second stage. The LTM algorithm measures similarity between the feature maps of the search and template images which are extracted by a pre-trained model. While the SRL network performs the automatic rotation and labelling of the input data for training purposes. Therefore, the proposed model does not consume an expensive human-annotation process. The experimental results show that the proposed model obtains 92.6% when testing on 2400 pairs of the template and target images. Moreover, in performing practical grasping tasks on a NVidia Jetson TX2 developer kit, the proposed model achieves a higher accuracy (88.5%) than other grasping approaches on a split of Cornell-grasp dataset.

show abstract

Section: Introductionmentioning

confidence: 99%

Robot arm grasping using learning-based template matching and self-rotation learning network

Lien

2022

Int J Adv Manuf Technol

Self Cite

View full text Add to dashboard Cite

show abstract

Robot Arm Grasping Using Learning-Based Template Matching and Self-Rotation Learning Network

Lien²

2022

Preprint

View full text Add to dashboard Cite

Applying deep neural network models to robot-arm grasping tasks requires the laborious and time-consuming annotation of a large number of representative examples in the training process. Accordingly, this work proposes a two-stage grasping model, in which the first stage employs learning-based template matching (LTM) algorithm for estimating the object position, and a self-rotation learning (SRL) network is then proposed to estimate the rotation angle of the grasping objects in the second stage. The LTM algorithm measures similarity between the feature maps of the search and template images which are extracted by a pre-trained model. While the SRL network performs the automatic rotation and labelling of the input data for training purposes. Therefore, the proposed model does not consume an expensive human-annotation process. The experimental results show that the proposed model obtains 92.6% when testing on 2400 pairs of the template and target images. Moreover, in performing practical grasping tasks on a NVidia Jetson TX2 developer kit, the proposed model achieves a higher accuracy (88.5%) than other grasping approaches on a split of Cornell-grasp dataset.

show abstract

Learning-Based Template Matching for Robot Arm Grasping

Cited by 2 publications

References 15 publications

Robot arm grasping using learning-based template matching and self-rotation learning network

Robot arm grasping using learning-based template matching and self-rotation learning network

Robot Arm Grasping Using Learning-Based Template Matching and Self-Rotation Learning Network

Contact Info

Product

Resources

About