scholarly journals Semantic Mapping with Low-Density Point-Clouds for Service Robots in Indoor Environments

2020 ◽  
Vol 10 (20) ◽  
pp. 7154
Author(s):  
Carlos Medina Sánchez ◽  
Matteo Zella ◽  
Jesús Capitán ◽  
Pedro J. Marrón
Keyword(s):  
Deep Learning ◽  
Point Clouds ◽  
Physical Structure ◽  
Service Robots ◽  
Low Density ◽  
Indoor Environments ◽  
Density Point ◽  
Detection Of Objects ◽  
The One ◽  
Indoor Scenarios

The advancements in the robotic field have made it possible for service robots to increasingly become part of everyday indoor scenarios. Their ability to operate and reach defined goals depends on the perception and understanding of their surrounding environment. Detecting and positioning objects as well as people in an accurate semantic map are, therefore, essential tasks that a robot needs to carry out. In this work, we walk an alternative path to build semantic maps of indoor scenarios. Instead of relying on high-density sensory input, like the one provided by an RGB-D camera, and resource-intensive processing algorithms, like the ones based on deep learning, we investigate the use of low-density point-clouds provided by 3D LiDARs together with a set of practical segmentation methods for the detection of objects. By focusing on the physical structure of the objects of interest, it is possible to remove complex training phases and exploit sensors with lower resolution but wider Field of View (FoV). Our evaluation shows that our approach can achieve comparable (if not better) performance in object labeling and positioning with a significant decrease in processing time than established approaches based on deep learning methods. As a side-effect of using low-density point-clouds, we also better support people privacy as the lower resolution inherently prevents the use of techniques like face recognition.

scholarly journals Classification of Point Clouds for Indoor Components Using Few Labeled Samples

2020 ◽  
Vol 12 (14) ◽  
pp. 2181
Author(s):  
Hangbin Wu ◽  
Huimin Yang ◽  
Shengyu Huang ◽  
Doudou Zeng ◽  
Chun Liu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Point Cloud ◽  
Point Clouds ◽  
Neighborhood Search ◽  
Learning Methods ◽  
Semantic Classification ◽  
Cloud Classification ◽  
Mixed Features ◽  
Indoor Scenarios ◽  
Point Cloud Classification

The existing deep learning methods for point cloud classification are trained using abundant labeled samples and used to test only a few samples. However, classification tasks are diverse, and not all tasks have enough labeled samples for training. In this paper, a novel point cloud classification method for indoor components using few labeled samples is proposed to solve the problem of the requirement for abundant labeled samples for training with deep learning classification methods. This method is composed of four parts: mixing samples, feature extraction, dimensionality reduction, and semantic classification. First, the few labeled point clouds are mixed with unlabeled point clouds. Next, the mixed high-dimensional features are extracted using a deep learning framework. Subsequently, a nonlinear manifold learning method is used to embed the mixed features into a low-dimensional space. Finally, the few labeled point clouds in each cluster are identified, and semantic labels are provided for unlabeled point clouds in the same cluster by a neighborhood search strategy. The validity and versatility of the proposed method were validated by different experiments and compared with three state-of-the-art deep learning methods. Our method uses fewer than 30 labeled point clouds to achieve an accuracy that is 1.89–19.67% greater than existing methods. More importantly, the experimental results suggest that this method is not only suitable for single-attribute indoor scenarios but also for comprehensive complex indoor scenarios.

scholarly journals AUTOMATICALLY DETERMINING SCALE WITHIN UNSTRUCTURED POINT CLOUDS

2016 ◽  
Vol XLI-B3 ◽  
pp. 617-624
Author(s):  
Jayren Kadamen ◽  
George Sithole
Keyword(s):  
Three Dimensional ◽  
Point Clouds ◽  
Indoor Navigation ◽  
Indoor Environments ◽  
Terrestrial Lidar ◽  
Detection Of Objects ◽  
The Difference ◽  
Computationally Intensive ◽  
Three Dimensional Models ◽  
General Size

Three dimensional models obtained from imagery have an arbitrary scale and therefore have to be scaled. Automatically scaling these models requires the detection of objects in these models which can be computationally intensive. Real-time object detection may pose problems for applications such as indoor navigation. This investigation poses the idea that relational cues, specifically height ratios, within indoor environments may offer an easier means to obtain scales for models created using imagery. The investigation aimed to show two things, (a) that the size of objects, especially the height off ground is consistent within an environment, and (b) that based on this consistency, objects can be identified and their general size used to scale a model. To test the idea a hypothesis is first tested on a terrestrial lidar scan of an indoor environment. Later as a proof of concept the same test is applied to a model created using imagery. The most notable finding was that the detection of objects can be more readily done by studying the ratio between the dimensions of objects that have their dimensions defined by human physiology. For example the dimensions of desks and chairs are related to the height of an average person. In the test, the difference between generalised and actual dimensions of objects were assessed. A maximum difference of 3.96% (2.93<i>cm</i>) was observed from automated scaling. By analysing the ratio between the heights (distance from the floor) of the tops of objects in a room, identification was also achieved.

scholarly journals AUTOMATICALLY DETERMINING SCALE WITHIN UNSTRUCTURED POINT CLOUDS

2016 ◽  
Vol XLI-B3 ◽  
pp. 617-624
Author(s):  
Jayren Kadamen ◽  
George Sithole
Keyword(s):  
Three Dimensional ◽  
Point Clouds ◽  
Indoor Navigation ◽  
Indoor Environments ◽  
Terrestrial Lidar ◽  
Detection Of Objects ◽  
The Difference ◽  
Computationally Intensive ◽  
Three Dimensional Models ◽  
General Size

Three dimensional models obtained from imagery have an arbitrary scale and therefore have to be scaled. Automatically scaling these models requires the detection of objects in these models which can be computationally intensive. Real-time object detection may pose problems for applications such as indoor navigation. This investigation poses the idea that relational cues, specifically height ratios, within indoor environments may offer an easier means to obtain scales for models created using imagery. The investigation aimed to show two things, (a) that the size of objects, especially the height off ground is consistent within an environment, and (b) that based on this consistency, objects can be identified and their general size used to scale a model. To test the idea a hypothesis is first tested on a terrestrial lidar scan of an indoor environment. Later as a proof of concept the same test is applied to a model created using imagery. The most notable finding was that the detection of objects can be more readily done by studying the ratio between the dimensions of objects that have their dimensions defined by human physiology. For example the dimensions of desks and chairs are related to the height of an average person. In the test, the difference between generalised and actual dimensions of objects were assessed. A maximum difference of 3.96% (2.93<i>cm</i>) was observed from automated scaling. By analysing the ratio between the heights (distance from the floor) of the tops of objects in a room, identification was also achieved.

scholarly journals REGISTRATION OPTIMIZATION OF MOBILE HANDHELD SCANNER POINT CLOUDS WITH STATIC SCANS

2021 ◽  
Vol XLIII-B2-2021 ◽  
pp. 289-296
Author(s):  
V. Alteirac ◽  
H. Macher ◽  
T. Landes
Keyword(s):  
Point Clouds ◽  
Ease Of Use ◽  
Mobile Systems ◽  
Acquisition Time ◽  
Indoor Environments ◽  
Mobile System ◽  
Minimum Number ◽  
The One ◽  
Time Required ◽  
Handheld Scanner

Abstract. In recent years, 3D acquisition methods involving different types of scanners have undergone a phenomenal technological growth. Nowadays, mobile acquisition devices are popular because of their ease of use and their fairly competitive cost. Static scanners provide higher accuracy and more detail, but the acquisition time required with these systems is higher than with mobile systems. Mobile scanners are known for their high acquisition speed but lower point density and accuracy. Until now, the choice of the type of system to use was dependent on the geometry of the study area and the required accuracy. This research aims to find a way to optimize the survey by finding a compromise between the two types of devices, in order to take advantage of both systems for the same acquisition campaign. The first objective is to study the minimum number of static positions required for respecting the required accuracy. A solution is also proposed for compensating the drift of the mobile device. Secondly, the pertinence to use static stations for the principal loop and mobile system for adjoining rooms is investigated. The datasets chosen allow, on the one side, to quantify the limits of the mobile system for the acquisition of indoor buildings and, on the other side, to give recommendations regarding the configuration of static stations as a reference for mobile point clouds. Based on these experiments, a methodology is proposed for indoor environments to combine the use of the two acquisition systems and thus to save time in the field while still providing a good registration quality.

scholarly journals Multi-Dimensional Underwater Point Cloud Detection Based on Deep Learning

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 884
Author(s):  
Chia-Ming Tsai ◽  
Yi-Horng Lai ◽  
Yung-Da Sun ◽  
Yu-Jen Chung ◽  
Jau-Woei Perng
Keyword(s):  
Deep Learning ◽  
Point Cloud ◽  
Three Dimensional ◽  
Point Clouds ◽  
Training Data ◽  
Network Architectures ◽  
Point Cloud Data ◽  
Data Types ◽  
Raw Data ◽  
Cloud Data

Numerous sensors can obtain images or point cloud data on land, however, the rapid attenuation of electromagnetic signals and the lack of light in water have been observed to restrict sensing functions. This study expands the utilization of two- and three-dimensional detection technologies in underwater applications to detect abandoned tires. A three-dimensional acoustic sensor, the BV5000, is used in this study to collect underwater point cloud data. Some pre-processing steps are proposed to remove noise and the seabed from raw data. Point clouds are then processed to obtain two data types: a 2D image and a 3D point cloud. Deep learning methods with different dimensions are used to train the models. In the two-dimensional method, the point cloud is transferred into a bird’s eye view image. The Faster R-CNN and YOLOv3 network architectures are used to detect tires. Meanwhile, in the three-dimensional method, the point cloud associated with a tire is cut out from the raw data and is used as training data. The PointNet and PointConv network architectures are then used for tire classification. The results show that both approaches provide good accuracy.

scholarly journals Towards footwear manufacturing 4.0: shoe sole robotic grasping in assembling operations

2021 ◽  
Author(s):  
Guillermo Oliver ◽  
Pablo Gil ◽  
Jose F. Gomez ◽  
Fernando Torres
Keyword(s):  
Industry 4.0 ◽  
Laser Scanner ◽  
Point Clouds ◽  
Average Score ◽  
Low Density ◽  
Contour Extraction ◽  
Shoe Industry ◽  
Simulated Environment ◽  
Dense Point ◽  
Different Shapes

AbstractIn this paper, we present a robotic workcell for task automation in footwear manufacturing such as sole digitization, glue dispensing, and sole manipulation from different places within the factory plant. We aim to make progress towards shoe industry 4.0. To achieve it, we have implemented a novel sole grasping method, compatible with soles of different shapes, sizes, and materials, by exploiting the particular characteristics of these objects. Our proposal is able to work well with low density point clouds from a single RGBD camera and also with dense point clouds obtained from a laser scanner digitizer. The method computes antipodal grasping points from visual data in both cases and it does not require a previous recognition of sole. It relies on sole contour extraction using concave hulls and measuring the curvature on contour areas. Our method was tested both in a simulated environment and in real conditions of manufacturing at INESCOP facilities, processing 20 soles with different sizes and characteristics. Grasps were performed in two different configurations, obtaining an average score of 97.5% of successful real grasps for soles without heel made with materials of low or medium flexibility. In both cases, the grasping method was tested without carrying out tactile control throughout the task.

scholarly journals Low-Density Insulation Blocks and Hardboards from Amaranth (Amaranthus cruentus) Stems, a New Perspective for Building Applications

Coatings ◽  
2021 ◽  
Vol 11 (3) ◽  
pp. 349
Author(s):  
Philippe Evon ◽  
Guyonne de Langalerie ◽  
Laurent Labonne ◽  
Othmane Merah ◽  
Thierry Talou ◽  
...  
Keyword(s):  
Aerial Part ◽  
Low Density ◽  
Renewable Materials ◽  
Fractionation Process ◽  
Amaranthus Cruentus ◽  
Cosmetic Industry ◽  
New Perspective ◽  
The One ◽  
Promising Source ◽  
Amaranth Oil

Nowadays, amaranth appears as a promising source of squalene of vegetable origin. Amaranth oil is indeed one of the most concentrated vegetable oils in squalene, i.e., up to 6% (w/w). This triterpene is highly appreciated in cosmetology, especially for the formulation of moisturizing creams. It is almost exclusively extracted from the liver of sharks, causing their overfishing. Thus, providing a squalene of renewable origin is a major challenge for the cosmetic industry. The amaranth plant has thus experienced renewed interest in recent years. In addition to the seeds, a stem is also produced during cultivation. Representing up to 80% (w/w) of the plant aerial part, it is composed of a ligneous fraction, the bark, on its periphery, and a pith in its middle. In this study, a fractionation process was developed to separate bark and pith. These two fractions were then used to produce renewable materials for building applications. On the one hand, the bark was used to produce hardboards, with the deoiled seeds acting as natural binder. Such boards are a viable alternative to commercial wood-based panels. On the other hand, the pith was transformed into cohesive and machinable low-density insulation blocks revealing a low thermal conductivity value.

scholarly journals A Systematic Deep Learning Based Overhead Tracking and Counting System Using RGB-D Remote Cameras

2021 ◽  
Vol 11 (12) ◽  
pp. 5503
Author(s):  
Munkhjargal Gochoo ◽  
Syeda Amna Rizwan ◽  
Yazeed Yasin Ghadi ◽  
Ahmad Jalal ◽  
Kibum Kim
Keyword(s):  
Deep Learning ◽  
Human Head ◽  
Point Clouds ◽  
Head Tracking ◽  
Complex Environments ◽  
People Tracking ◽  
Practical Applications ◽  
Remote Cameras ◽  
Video Frames ◽  
Benchmark Datasets

Automatic head tracking and counting using depth imagery has various practical applications in security, logistics, queue management, space utilization and visitor counting. However, no currently available system can clearly distinguish between a human head and other objects in order to track and count people accurately. For this reason, we propose a novel system that can track people by monitoring their heads and shoulders in complex environments and also count the number of people entering and exiting the scene. Our system is split into six phases; at first, preprocessing is done by converting videos of a scene into frames and removing the background from the video frames. Second, heads are detected using Hough Circular Gradient Transform, and shoulders are detected by HOG based symmetry methods. Third, three robust features, namely, fused joint HOG-LBP, Energy based Point clouds and Fused intra-inter trajectories are extracted. Fourth, the Apriori-Association is implemented to select the best features. Fifth, deep learning is used for accurate people tracking. Finally, heads are counted using Cross-line judgment. The system was tested on three benchmark datasets: the PCDS dataset, the MICC people counting dataset and the GOTPD dataset and counting accuracy of 98.40%, 98%, and 99% respectively was achieved. Our system obtained remarkable results.

Sign in / Sign up

Export Citation Format

Share Document