Exploiting Trademark Databases for Robotic Object Fetching

Song, Joshua; Kurniawati, Hanna

doi:10.1109/icra.2019.8793829

Cited by 4 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Still, it is not suitable for the keypoints detection since we need to label the semantic keypoints accurately, which is a challenging task for real images. To overcome this problem, some researchers have used synthesizing datasets [5][6][7] and produced ground truth labels [8,9]. Some researchers use unlabeled data [10,11] in object detection, but the methods are not applicable to our keypoints detection problem.…”

Section: Introductionmentioning

confidence: 99%

Texture-Less Shiny Objects Grasping in a Single RGB Image Using Synthetic Training Data

et al. 2022

View full text Add to dashboard Cite

In the industrial domain, estimating the pose of texture-less shiny parts is challenging but worthwhile. In this study, it is impractical to utilize texture information to obtain the pose because the features are likely to be affected by the surrounding objects. In addition, the colors of the metal parts are similar, making object segmentation challenging. This study proposes dividing the entire process into three steps: object detection, feature extraction, and pose estimation. We use the Mask-RCNN to detect objects and HRNet to extract the corresponding features. For metal parts of different shapes, different keypoints were chosen accordingly. Conventional contour-based methods are inapplicable to parts containing planar surfaces because the objects occlude each other in clustered environments. In this case, we used dense discrete points along the edges as semantic keypoints for metal parts containing planar elements. We chose skeleton points as semantic keypoints for parts containing cylindrical components. Subsequently, we combined the localization of semantic keypoints and the corresponding CAD model information to estimate the 6D pose of an individual object in sight. The implementation of deep learning approaches requires massive training datasets and intensive labeling. Thus, we propose a method to generate training datasets and automatically label them. Experiments show that the algorithm based on synthetic data performs well in a natural environment, despite not utilizing real scenario images for training.

show abstract

Section: Introductionmentioning

confidence: 99%

Texture-Less Shiny Objects Grasping in a Single RGB Image Using Synthetic Training Data

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Deep learning methods are known to be robust, but their implementations are based on huge amounts of training data, and require intensive manual work for labeling the datasets. To overcome this limitation, it is desirable to have approaches for synthesizing datasets for training [3]- [6] and producing label data [7] [23].…”

Section: Introductionmentioning

confidence: 99%

Pose Estimation for Texture-less Shiny Objects in a Single RGB Image Using Synthetic Training Data

Chen¹,

Jiang²,

Zhang³

et al. 2019

Preprint

View full text Add to dashboard Cite

In the industrial domain, the pose estimation of multiple texture-less shiny parts is a valuable but challenging task. In this particular scenario, it is impractical to utilize keypoints or other texture information because most of them are not actual features of the target but the reflections of surroundings. Moreover, the similarity of color also poses a challenge in segmentation. In this article, we propose to divide the pose estimation process into three stages: object detection, features detection and pose optimization. A convolutional neural network was utilized to perform object detection. Concerning the reliability of surface texture, we leveraged the contour information for estimating pose. Since conventional contourbased methods are inapplicable to clustered metal parts due to the difficulties in segmentation, we use the dense discrete points along the metal part edges as semantic keypoints for contour detection. Afterward, we exploit both keypoint information and CAD model to calculate the 6D pose of each object in view. A typical implementation of deep learning methods not only requires a large amount of training data, but also relies on intensive human labor for labeling the datasets. Therefore, we propose an approach to generate datasets and label them automatically. Despite not using any real-world photos for training, a series of experiments showed that the algorithm built on synthetic data perform well in the real environment.

show abstract

“…Their final evaluation obtained better results using object detection frameworks based on two stages than frameworks based on one stage and segmentation networks. Song & Kurniawati [29] also compared the same types of object detection frameworks (two-stage and one-stage). They also evaluated a training base composition with only synthetic data, real data, and synthetic data.…”

Section: Logo Detectionmentioning

confidence: 99%

Method for Automatic Detection of Stamps in Scanned Documents Using Deep Learning and Synthetic Data Generation by Instance Augmentation

VALENTE¹

View full text Add to dashboard Cite

Scanned documents in business environments have replaced large volumes of papers. Authorized professionals use stamps to certify critical information in these documents. Many companies need to verify the adequate stamping of incoming and outgoing documents. In most inspection situations, people perform a visual inspection to identify stamps. Therefore, manual stamp checking is tiring, susceptible to errors, and inefficient in terms of time spent and expected results.Errors in manual checking for stamps can lead to fines from regulatory bodies, interruption of operations, and even compromise workflows and financial transactions. This work proposes two methods that combined can address this problem, by fully automating stamp detection in real-world scanned documents.The developed methods can handle datasets containing many small sample-sized types of stamps, multiples overlaps, different combinations per page, and missing data. The first method proposes a deep network architecture designed from the relationship between the problems identified in real-world stamps and the challenges and solutions of the object detection task pointed out in the literature.The second method proposes a novel instance augmentation pipeline of stamp datasets from real data to investigate whether it is possible to detect stamp types with insufficient samples. We evaluate the hyperparameters of the instance augmentation approach and the obtained results through a Deep Explainability method. We achieve state-of-the-art results for the stamp detection task by successfully combining these two methods, achieving 97.3% of precision and 93.2% of recall.

show abstract

Exploiting Trademark Databases for Robotic Object Fetching

Cited by 4 publications

References 20 publications

Texture-Less Shiny Objects Grasping in a Single RGB Image Using Synthetic Training Data

Texture-Less Shiny Objects Grasping in a Single RGB Image Using Synthetic Training Data

Pose Estimation for Texture-less Shiny Objects in a Single RGB Image Using Synthetic Training Data

Method for Automatic Detection of Stamps in Scanned Documents Using Deep Learning and Synthetic Data Generation by Instance Augmentation

Contact Info

Product

Resources

About