SALT: A Semi-automatic Labeling Tool for RGB-D Video Sequences

Stumpf, Dennis; Krauß, Stephan; Reis, Gerd; Wasenmüller, Oliver; Stricker, Didier

doi:10.48550/arxiv.2102.10820

Cited by 4 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both datasets use the Kinect Azure RGB-D camera. The annotation of the data was done manually, assisted by some semi-automatic functionalities of our annotation tool, such as the transfer of bounding box proposals between subsequent frames [21]. Table 1 summarizes the attributes of the two datasets.…”

Section: Datasetsmentioning

confidence: 99%

Time-of-Flight Depth Sensing for Automotive Safety and Smart Building Applications: The VIZTA Project

Rambach,

Mirbach,

Anisimov

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Time-of-Flight (ToF) can be an advantageous sensing modality for several indoor applications, used alone or in combination with other sensors such as RGB cameras. As part of the research project VIZTA (Vision, Identification, with Z-sensing Technologies and key Applications), we developed methods using Machine Learning algorithms with ToF depth measurements as inputs to address two key areas of applications, in-car cabin monitoring (person detection and segmentation) and smart building monitoring ( person counting and anomaly detection). In this article, we discuss the entire research approach followed in VIZTA, from setting up the experimental environments for collecting data and creating the VIZTA public datasets, to developing Deep Learning algorithms tailored to ToF data, used either in 2D depth map or 3D point cloud format. We discuss the advantages and challenges of using ToF-data, as well as the lessons learned during the evaluation and benchmarking of our methods.

show abstract

Section: Datasetsmentioning

confidence: 99%

Time-of-Flight Depth Sensing for Automotive Safety and Smart Building Applications: The VIZTA Project

Rambach,

Mirbach,

Anisimov

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…SALT [12] proposes to use a GrabCut based approach to speed up labeling of RGB-D data. Similarly, their method does not require object or environment models.…”

Section: B 3d Annotationmentioning

confidence: 99%

3D Annotation Of Arbitrary Objects In The Wild

Blomqvist¹,

Hietala²

2021

Preprint

View full text Add to dashboard Cite

Recent years have produced a variety of learning based methods in the context of computer vision and robotics. Most of the recently proposed methods are based on deep learning, which require very large amounts of data compared to traditional methods. The performance of the deep learning methods are largely dependent on the data distribution they were trained on, and it is important to use data from the robot's actual operating domain during training. Therefore, it is not possible to rely on pre-built, generic datasets when deploying robots in real environments, creating a need for efficient data collection and annotation in the specific operating conditions the robots will operate in. The challenge is then: how do we reduce the cost of obtaining such datasets to a point where we can easily deploy our robots in new conditions, environments and to support new sensors? As an answer to this question, we propose a data annotation pipeline based on SLAM, 3D reconstruction, and 3D-to-2D geometry. The pipeline allows creating 3D and 2D bounding boxes, along with per-pixel annotations of arbitrary objects without needing accurate 3D models of the objects prior to data collection and annotation. Our results showcase almost 90% Intersection-over-Union (IoU) agreement on both semantic segmentation and 2D bounding box detection across a variety of objects and scenes, while speeding up the annotation process by several orders of magnitude compared to traditional manual annotation.

show abstract

“…Stumpf et al [20] describe the layout of images with 3D bounding boxes using an RGB-D camera. Images were labeled using the information about the current depth-map of the frame.…”

Section: Related Workmentioning

confidence: 99%

DeepScanner: a Robotic System for Automated 2D Object Dataset Collection with Annotations

Ilin¹,

Kalinov²,

Karpyshev³

et al. 2021

Preprint

View full text Add to dashboard Cite

In the proposed study, we describe the possibility of automated dataset collection using an articulated robot. The proposed technology reduces the number of pixel errors on a polygonal dataset and the time spent on manual labeling of 2D objects. The paper describes a novel automatic dataset collection and annotation system, and compares the results of automated and manual dataset labeling. Our approach increases the speed of data labeling 240-fold, and improves the accuracy compared to manual labeling 13-fold. We also present a comparison of metrics for training a neural network on a manually annotated and an automatically collected dataset.Index terms -Dataset collection, automated data annotation, image segmentation, industrial robot.

show abstract

SALT: A Semi-automatic Labeling Tool for RGB-D Video Sequences

Cited by 4 publications

References 22 publications

Time-of-Flight Depth Sensing for Automotive Safety and Smart Building Applications: The VIZTA Project

Time-of-Flight Depth Sensing for Automotive Safety and Smart Building Applications: The VIZTA Project

3D Annotation Of Arbitrary Objects In The Wild

DeepScanner: a Robotic System for Automated 2D Object Dataset Collection with Annotations

Contact Info

Product

Resources

About