Computer-Aided Depth Video Stream Masking Framework for Human Body Segmentation in Depth Sensor Images

Ryselis, Karolis; Blažauskas, Tomas; Damaševičius, Robertas; Maskeliūnas, Rytis

doi:10.3390/s22093531

Cited by 9 publications

(6 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the contrary, if the CD value is large, the classification performance of the model must poor. In order to further verify the effectiveness of the proposed method, we compare with PCN [33], Fold-ingNet [31], AtlasNet [21], TopNet [23] and SA-Net…”

Section: Implementation Detailsmentioning

confidence: 99%

“…Pierdicca [18] uses an improved DGCNN for semantic segmentation of com-plex, highly variable 3D point cloud historical building models to accelerate the identification of historical building elements. Karolis et al [21] proposed using computer-aided technology for depth video stream masking and training with convolutional neural networks to obtain more accurate human body segmentation results. This framework has good accuracy and real-time performance in human body segmentation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Point Cloud Completion Based on Nonlocal Neural Networks with Adaptive Sampling

Xing,

Wang,

Wang

et al. 2024

ITC

View full text Add to dashboard Cite

Raw point clouds are usually sparse and incomplete, inevitably containing outliers or noise from 3D sensors. In this paper, an improved SA-Net based on an encoder-decoder structure is proposed to make it more robust in predicting complete point clouds. The encoder of the original SA-Net network is very sensitive to noise in the feature extraction process. Therefore, we use PointASNL as the encoder, which weights around the initial sampling points through the AS module (Adaptive Sampling Module) and adaptively adjusts the weight of the sampling points to effectively alleviate the bias effect of outliers. In order to fully mine the feature information of point clouds, it captures the neighborhood and long-distance dependencies of sampling points through the LNL module (Local-NonLocal Module), providing more accurate information for point cloud processing. Then, we use the encoder to extract local geometric features of the incomplete point cloud at different resolutions.Then, an attention mechanism is introduced to transfer the extracted features to a decoder. The decoder gradually refines the local features to achieve a more realistic effect. Experiments on the ShapeNet data set show that the improved point cloud completion network achieves the goal and reduces the average chamfer distance by 3.50% compared to SA-Net.

show abstract

Section: Implementation Detailsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Point Cloud Completion Based on Nonlocal Neural Networks with Adaptive Sampling

Xing,

Wang,

Wang

et al. 2024

ITC

View full text Add to dashboard Cite

show abstract

“…Smart sensors and computer vision can use deep learning technology to implement posture estimation and motion recognition [ 7 , 8 , 9 , 10 , 11 ], such as smart watches, wristbands, wearable sensors, and high-definition cameras. Inspired by the application of artificial intelligence technology in image recognition and data analysis, the introduction of machine learning into the motion state analysis of moving skiers will help to obtain more accurate and realistic ski technical action features and the motion performance of mobile personnel [ 12 ].…”

Section: Introductionmentioning

confidence: 99%

Optically Non-Contact Cross-Country Skiing Action Recognition Based on Key-Point Collaborative Estimation and Motion Feature Extraction

et al. 2023

Sensors

View full text Add to dashboard Cite

Technical motion recognition in cross-country skiing can effectively help athletes to improve their skiing movements and optimize their skiing strategies. The non-contact acquisition method of the visual sensor has a bright future in ski training. The changing posture of the athletes, the environment of the ski resort, and the limited field of view have posed great challenges for motion recognition. To improve the applicability of monocular optical sensor-based motion recognition in skiing, we propose a monocular posture detection method based on cooperative detection and feature extraction. Our method uses four feature layers of different sizes to simultaneously detect human posture and key points and takes the position deviation loss and rotation compensation loss of key points as the loss function to implement the three-dimensional estimation of key points. Then, according to the typical characteristics of cross-country skiing movement stages and major sub-movements, the key points are divided and the features are extracted to implement the ski movement recognition. The experimental results show that our method is 90% accurate for cross-country skiing movements, which is equivalent to the recognition method based on wearable sensors. Therefore, our algorithm has application value in the scientific training of cross-country skiing.

show abstract

“…In recent years, with the rise of new deep learning techniques, semantic segmentation has been successfully applied to several challenging fields, for instance: autonomous driving, medical imaging, augmented reality, and remote sensing, to mention a few [ 5 ]. Some important semantic segmentation research has specific applications, such as that proposed in [ 6 ], which presents a framework to create foreground–background masks from depth images for human body segmentation. In [ 7 ], a fully connected VGG16 neural network was proposed for real-time path finding intended to help visually impaired or blind people.…”

Section: Introductionmentioning

confidence: 99%

FASSVid: Fast and Accurate Semantic Segmentation for Video Sequences

Portillo-Portillo

Olivares-Mercado

Alvarado

et al. 2022

Entropy

View full text Add to dashboard Cite

Most of the methods for real-time semantic segmentation do not take into account temporal information when working with video sequences. This is counter-intuitive in real-world scenarios where the main application of such methods is, precisely, being able to process frame sequences as quickly and accurately as possible. In this paper, we address this problem by exploiting the temporal information provided by previous frames of the video stream. Our method leverages a previous input frame as well as the previous output of the network to enhance the prediction accuracy of the current input frame. We develop a module that obtains feature maps rich in change information. Additionally, we incorporate the previous output of the network into all the decoder stages as a way of increasing the attention given to relevant features. Finally, to properly train and evaluate our methods, we introduce CityscapesVid, a dataset specifically designed to benchmark semantic video segmentation networks. Our proposed network, entitled FASSVid improves the mIoU accuracy performance over a standard non-sequential baseline model. Moreover, FASSVid obtains state-of-the-art inference speed and competitive mIoU results compared to other state-of-the-art lightweight networks, with significantly lower number of computations. Specifically, we obtain 71% of mIoU in our CityscapesVid dataset, running at 114.9 FPS on a single NVIDIA GTX 1080Ti and 31 FPS on the NVIDIA Jetson Nano embedded board with images of size 1024×2048 and 512×1024, respectively.

show abstract

Computer-Aided Depth Video Stream Masking Framework for Human Body Segmentation in Depth Sensor Images

Cited by 9 publications

References 28 publications

Point Cloud Completion Based on Nonlocal Neural Networks with Adaptive Sampling

Point Cloud Completion Based on Nonlocal Neural Networks with Adaptive Sampling

Optically Non-Contact Cross-Country Skiing Action Recognition Based on Key-Point Collaborative Estimation and Motion Feature Extraction

FASSVid: Fast and Accurate Semantic Segmentation for Video Sequences

Contact Info

Product

Resources

About