Ridge body parts features for human pose estimation and recognition from RGB-D video data

Jalal, Ahmad; Kim, Yeonho; Kim, Daijin

doi:10.1109/icccnt.2014.6963015

Cited by 93 publications

(39 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By proposing the body surface context features, human action recognition is robust to translations and rotations. As with Jalal's work in [10], Song's work [12] still depends on static scenes with an embedded sensing infrastructure. Current activity recognitions in such lifelogging settings usually assume there is only one actor in the scene and how these solutions can scale up to more realistic and challenging settings such as outdoors are difficult.…”

Section: In-situ Visual Lifeloggingmentioning

confidence: 99%

“…This means that human activities can be captured through sensors such as video cameras installed in the local infrastructure, therefore the recording is highly dependent on instrumented environments, such as PlaceLab (MIT) [8]. Typical use of video sensors for in-situ sensing also includes works as reported in [9,10,11,12] and [13] . Jalal et al [11] proposed a depth video-based activity recognition system for smart spaces based on feature transformation and HMM recognition.…”

Section: In-situ Visual Lifeloggingmentioning

confidence: 99%

See 1 more Smart Citation

Computer Vision for Lifelogging

Wang

Sun

Smeaton

et al. 2018

Computer Vision for Assistive Healthcare

View full text Add to dashboard Cite

show abstract

Section: In-situ Visual Lifeloggingmentioning

confidence: 99%

Section: In-situ Visual Lifeloggingmentioning

confidence: 99%

Computer Vision for Lifelogging

Wang

Sun

Smeaton

et al. 2018

Computer Vision for Assistive Healthcare

View full text Add to dashboard Cite

show abstract

“…where, P(O | h l ) denoted the probability of likelihood of the h activity HMM among different number of activities [26][27][28]. Fig.…”

Section: Modified Hidden Markov Model (M-hmm)mentioning

confidence: 99%

Depth Images-based Human Detection, Tracking and Activity Recognition Using Spatiotemporal Features and Modified HMM

Kamal¹,

Jalal²,

Kim³

2016

Journal of Electrical Engineering and Technology

Self Cite

103

View full text Add to dashboard Cite

-Human activity recognition using depth information is an emerging and challenging technology in computer vision due to its considerable attention by many practical applications such as smart home/office system, personal health care and 3D video games. This paper presents a novel framework of 3D human body detection, tracking and recognition from depth video sequences using spatiotemporal features and modified HMM. To detect human silhouette, raw depth data is examined to extract human silhouette by considering spatial continuity and constraints of human motion information. While, frame differentiation is used to track human movements. Features extraction mechanism consists of spatial depth shape features and temporal joints features are used to improve classification performance. Both of these features are fused together to recognize different activities using the modified hidden Markov model (M-HMM). The proposed approach is evaluated on two challenging depth video datasets. Moreover, our system has significant abilities to handle subject's body parts rotation and body parts missing which provide major contributions in human activity recognition.

show abstract

“…It determines the color in the image can appear most color number or the maximum gray level in the gray image. Image content understanding depth estimation method is mainly through classifying every scene in the image block, and then for each category of scenery with respective applicable method to estimate the depth of their information [23][24][25][26][27].…”

Section: The Intensity and Depth Pixels Problemmentioning

confidence: 99%

A Novel Face Recognition Algorithm based on the Deep Convolution Neural Network and Key Points Detection Jointed Local Binary Pattern Methodology

Huang¹,

Zhang²

2017

Journal of Electrical Engineering and Technology

View full text Add to dashboard Cite

-This paper presents a novel face recognition algorithm based on the deep convolution neural network and key point detection jointed local binary pattern methodology to enhance the accuracy of face recognition. We firstly propose the modified face key feature point location detection method to enhance the traditional localization algorithm to better pre-process the original face images. We put forward the grey information and the color information with combination of a composite model of local information. Then, we optimize the multi-layer network structure deep learning algorithm using the Fisher criterion as reference to adjust the network structure more accurately. Furthermore, we modify the local binary pattern texture description operator and combine it with the neural network to overcome drawbacks that deep neural network could not learn to face image and the local characteristics. Simulation results demonstrate that the proposed algorithm obtains stronger robustness and feasibility compared with the other state-of-the-art algorithms. The proposed algorithm also provides the novel paradigm for the application of deep learning in the field of face recognition which sets the milestone for further research.

show abstract

Ridge body parts features for human pose estimation and recognition from RGB-D video data

Cited by 93 publications

References 22 publications

Computer Vision for Lifelogging

Computer Vision for Lifelogging

Depth Images-based Human Detection, Tracking and Activity Recognition Using Spatiotemporal Features and Modified HMM

A Novel Face Recognition Algorithm based on the Deep Convolution Neural Network and Key Points Detection Jointed Local Binary Pattern Methodology

Contact Info

Product

Resources

About