Real-Time Fully Incremental Scene Understanding on Mobile Platforms

Wald, Johanna; Tateno, Keisuke; Sturm, Jürgen; Navab, Nassir; Tombari, Federico

doi:10.1109/lra.2018.2852782

Cited by 28 publications

(18 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is capable of generating three-dimensional mesh data from the screen geometry [16]. The method of deducing standing human bodies from single images using the calibration models is presented in the previous works [17].…”

Section: Related Workmentioning

confidence: 99%

Blockchain-based Learning for Health Screening with Digital Anthropometry from Body Images

Choudhury

Khanna

et al. 2021

Preprint

View full text Add to dashboard Cite

Anthropoid images encode reliable biometric information in abundance. Recent research on image-based screening drives this effort to investigate the feasibility of interpreting the inherent nutritional state from multidimensional human body images. However, anthropometric databases are becoming increasingly essential and grow in parallel to achieve efficient system designs. This paper presents a novel imaging-based strategy in an augmented environment to quantify the human anthropometric features with blockchain-based learning to generate a diagnosis report. It includes evaluating the attributes such as height, weight, forearm, wrist, waist, Mid-Upper Arm Circumference (MUAC), Knee, Feet, head length from an image using the Augmented Reality and Blockchain-based Transfer Learning for diagnostic accuracy. We developed a novel skeleton known as FETTLE to determine the role of body measures for assessing nutritional conditions and body weight from human body images. It forms an instantly applicable technique aimed at evaluating children’s growth patterns all through their initial ages. FETTLE app can also be operated on bedridden people as a screening mechanism to spot their risk of pressure ulcers and undernutrition, followed by a more structured examination. Our approach is superior in accuracy measures with consortium blockchain-based learning context with privacy-preserved medical data sharing and high-end user experience and interaction. Our framework is proved to gain about 97.26% validation accuracy on anthropoid images.

show abstract

Section: Related Workmentioning

confidence: 99%

Blockchain-based Learning for Health Screening with Digital Anthropometry from Body Images

Choudhury

Khanna

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In the third stage, posttreatment is carried out to further remove non-tobacco plant areas. There are also many other existing approaches in the area of scene understanding [9], [10], [11], [12], [13], [14], [15], [16], [17]. However, most of them are not designed for the UAVs nor optimized for detection and localization tasks during flying on the air.…”

Section: Scene Understanding For Uavsmentioning

confidence: 99%

Scan From the Sky: A Path Planning Method with Perception Optimization for UAVs

Yuan¹,

Ota²,

Zhao³

2021

Preprint

View full text Add to dashboard Cite

Unmanned aerial vehicles (UAVs) are frequently adopted in disaster management. The vision they provided is extremelyvaluable for rescuers. However, they face severe problems in their stability in actual disaster scenarios, as the images captured by theon-board sensors cannot consistently give enough information for deep learning models to make accurate decisions. In many cases,UAVs have to capture multiple images from different views to output final recognition results. In this paper, we desire to formulate the flypath task for UAVs, considering the actual perception needs. A new convolutional neural network (CNN) model is proposed to detectand localize the objects, such as the buildings, as well as an optimization method to find the optimal flying path to accutately recognizeas many as possible objects with a minimum time cost. The simulation results demonstrate that the proposed method is effective andefficient, and can well address the actual scene understanding and path planning problems for UAVs in the real world.

show abstract

“…Understanding Scene understanding methods based on RGB-D data generally rely on volumetric or surfel-based SLAM to reconstruct the 3D geometry of the scene while fusing semantic segments extracted via Random Forests [29,30] or CNNs [13,15]. Other works such as SLAM++ [24] or Fusion++ [12] operate on an object level and create semantic scene graphs for SLAM and loop closure.…”

Section: Rgb-d Scenementioning

confidence: 99%

RIO: 3D Object Instance Re-Localization in Changing Indoor Environments

Wald

Avetisyan

Navab

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

Self Cite

View full text Add to dashboard Cite

Figure 1: 3D object instance re-localization benchmark: we want to robustly estimate the 6DoF pose (T1, T2, ...Tn) of changed rigid object instances from a segmented source to a target scan taken at a later point in time. AbstractIn this work, we introduce the task of 3D object instance re-localization (RIO): given one or multiple objects in an RGB-D scan, we want to estimate their corresponding 6DoF poses in another 3D scan of the same environment taken at a later point in time. We consider RIO a particularly important task in 3D vision since it enables a wide range of practical applications, including AI-assistants or robots that are asked to find a specific object in a 3D scene. To address this problem, we first introduce 3RScan, a novel dataset and benchmark, which features 1482 RGB-D scans of 478 environments across multiple time steps. Each scene includes several objects whose positions change over time, together with ground truth annotations of object instances and their respective 6DoF mappings among re-scans. Automatically finding 6DoF object poses leads to a particular challenging feature matching task due to varying partial observations and changes in the surrounding context. To this end, we introduce a new data-driven approach that efficiently finds matching features using a fully-convolutional 3D correspondence network operating on multiple spatial scales. Combined with a 6DoF pose optimization, our method outperforms state-of-the-art baselines on our newly-established benchmark, achieving an accuracy of 30.58%.

show abstract

Real-Time Fully Incremental Scene Understanding on Mobile Platforms

Cited by 28 publications

References 25 publications

Blockchain-based Learning for Health Screening with Digital Anthropometry from Body Images

Blockchain-based Learning for Health Screening with Digital Anthropometry from Body Images

Scan From the Sky: A Path Planning Method with Perception Optimization for UAVs

RIO: 3D Object Instance Re-Localization in Changing Indoor Environments

Contact Info

Product

Resources

About