DeepSegment: Segmentation of motion capture data using deep convolutional neural network

Yasin, Hashim; Hayat, Saqib

doi:10.1016/j.imavis.2021.104147

Cited by 6 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Deep learning models have seen significant success in a wide range of applications in recent years. In fact, different deep learning methods have been introduced for image and motion segmentation [10][11][12][13], detection [14][15][16], tracking [17,18] and classification [19,20]. Due to the success of deep learning methods, CNN models have also been used in the literature to provide relevant information on the number of people present on the stage.…”

Section: Related Workmentioning

confidence: 99%

New End-to-End Strategy Based on DeepLabv3+ Semantic Segmentation for Human Head Detection

Chouai

Doležel

Štursa

et al. 2021

Sensors

View full text Add to dashboard Cite

In the field of computer vision, object detection consists of automatically finding objects in images by giving their positions. The most common fields of application are safety systems (pedestrian detection, identification of behavior) and control systems. Another important application is head/person detection, which is the primary material for road safety, rescue, surveillance, etc. In this study, we developed a new approach based on two parallel Deeplapv3+ to improve the performance of the person detection system. For the implementation of our semantic segmentation model, a working methodology with two types of ground truths extracted from the bounding boxes given by the original ground truths was established. The approach has been implemented in our two private datasets as well as in a public dataset. To show the performance of the proposed system, a comparative analysis was carried out on two deep learning semantic segmentation state-of-art models: SegNet and U-Net. By achieving 99.14% of global accuracy, the result demonstrated that the developed strategy could be an efficient way to build a deep neural network model for semantic segmentation. This strategy can be used, not only for the detection of the human head but also be applied in several semantic segmentation applications.

show abstract

Section: Related Workmentioning

confidence: 99%

New End-to-End Strategy Based on DeepLabv3+ Semantic Segmentation for Human Head Detection

Chouai

Doležel

Štursa

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…The k d-tree-based neighborhood searches are extended further on 2D synthetic landmarks as well as 2D skeletons extracted from RGB images [ 17 , 23 ]. Yasin et al [ 24 ] use k d-tree for the search and then retrieval of

-nearest neighbors (

NNs) which are employed further for human action classification and segmentation. The Surface Area Heuristic (SAH) k d-tree [ 19 , 20 , 21 ] have been constructed on GPUs in which the Surface Area Heuristic is calculated at each node to find the splitting plane axes instead of a median point.…”

Section: Related Workmentioning

confidence: 99%

An Effective and Efficient Approach for 3D Recovery of Human Motion Capture Data

Yasin

Ghani

Krüger

2023

Sensors

Self Cite

View full text Add to dashboard Cite

In this work, we propose a novel data-driven approach to recover missing or corrupted motion capture data, either in the form of 3D skeleton joints or 3D marker trajectories. We construct a knowledge-base that contains prior existing knowledge, which helps us to make it possible to infer missing or corrupted information of the motion capture data. We then build a kd-tree in parallel fashion on the GPU for fast search and retrieval of this already available knowledge in the form of nearest neighbors from the knowledge-base efficiently. We exploit the concept of histograms to organize the data and use an off-the-shelf radix sort algorithm to sort the keys within a single processor of GPU. We query the motion missing joints or markers, and as a result, we fetch a fixed number of nearest neighbors for the given input query motion. We employ an objective function with multiple error terms that substantially recover 3D joints or marker trajectories in parallel on the GPU. We perform comprehensive experiments to evaluate our approach quantitatively and qualitatively on publicly available motion capture datasets, namely CMU and HDM05. From the results, it is observed that the recovery of boxing, jumptwist, run, martial arts, salsa, and acrobatic motion sequences works best, while the recovery of motion sequences of kicking and jumping results in slightly larger errors. However, on average, our approach executes outstanding results. Generally, our approach outperforms all the competing state-of-the-art methods in the most test cases with different action sequences and executes reliable results with minimal errors and without any user interaction.

show abstract

“…Based on the action of different dimensionless shown in equation (8), fðRÞ is the movement differences during a complete set of Tai Chi Chuan training, which can be obtained on the basis of the △R get students Tai Chi Chuan exercise of and time integral; calculation process is shown as follows:…”

Section: : ð5þmentioning

confidence: 99%

“…Jiménez-Martín et al [4] studied the influence of three different modalities Tai Chi Chuan to people body of clinical cases and found that most common forms used in the research design associated with TCC correspond to those linked to the sports modality of this activity, while the forms associated with the therapeutic modality are scarcely present. Domestic and foreign relevant scholars [5][6][7][8][9][10]…”

Section: Introductionmentioning

confidence: 99%

Application of Fine Motion Capture Method for Tai Chi Chuan Assistant Training

2022

Journal of Sensors

View full text Add to dashboard Cite

Tai Chi Chuan is an important part of Chinese wushu and is the product of the Chinese civilization; it contains abundant philosophy sense. Tai Chi Chuan has experienced a long historical process of development; in the process of development and change numerous for brief, to the rough, now widely process of Tai Chi Chuan for its style is easy to learn and has a strong role of strengthening the body while widely popular among the people of all ages. The existing Tai Chi Chuan training methods have not satisfied people’s pursuit of spiritual life that has more and more high request, therefore urgently needs to study new and efficient Tai Chi Chuan training method. In this paper, the characteristics and development history of the Tai Chi Chuan development were analyzed. In order to overcome difficulties in training, at present, the research on application of AI technology with fine motion capture method auxiliary taijiquan training is aimed at, which can further improve the social mass to understand Tai Chi Chuan, and guide people to exercise more scientifically, improve the body quality, training effect, and enrich the spiritual and cultural life.

show abstract

DeepSegment: Segmentation of motion capture data using deep convolutional neural network

Cited by 6 publications

References 11 publications

New End-to-End Strategy Based on DeepLabv3+ Semantic Segmentation for Human Head Detection

New End-to-End Strategy Based on DeepLabv3+ Semantic Segmentation for Human Head Detection

An Effective and Efficient Approach for 3D Recovery of Human Motion Capture Data

Application of Fine Motion Capture Method for Tai Chi Chuan Assistant Training

Contact Info

Product

Resources

About