Human Action Segmentation Based on a Streaming Uniform Entropy Slice Method

Peng, Cheng; Lo, Sio-Long; Huang, Jie; Tsoi, Ah Chung

doi:10.1109/access.2017.2788943

Cited by 7 publications

(7 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With a careful comparison between the original image and uncertainty map in the figure, we can find that our trained model mostly has high confidence in the interior parts of the images, but low confidence around the image edge. This finding is confirmed in other literature studies which show that capturing sharp discontinuous optical flow occurred on motion boundary, which is a subset of image edges, is challenging [21], [36]- [38].…”

Section: B Uncertainty Estimation and Interpretationsupporting

confidence: 87%

Fast Uncertainty Estimation for Deep Learning Based Optical Flow

Lee

Capuano

Harvard

et al. 2020

2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

We present a novel approach to reduce the processing time required to derive the estimation uncertainty map in deep learning-based optical flow determination methods. Without uncertainty aware reasoning, the optical flow model, especially when it is used for mission critical fields such as robotics and aerospace, can cause catastrophic failures. Although several approaches such as the ones based on Bayesian neural networks have been proposed to handle this issue, they are computationally expensive. Thus, to speed up the processing time, our approach applies a generative model, which is trained by input images and an uncertainty map derived through a Bayesian approach. By using synthetically generated images of spacecraft, we demonstrate that the trained generative model can produce the uncertainty map 100∼700 times faster than the conventional uncertainty estimation method used for training the generative model itself. We also show that the quality of uncertainty map derived by the generative model is close to that of the original uncertainty map. By applying the proposed approach, the deep learning model operated in real-time can avoid disastrous failures by considering the uncertainty as well as achieving better performance removing uncertain portions of the prediction result.

show abstract

Section: B Uncertainty Estimation and Interpretationsupporting

confidence: 87%

Fast Uncertainty Estimation for Deep Learning Based Optical Flow

Lee

Capuano

Harvard

et al. 2020

2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

show abstract

“…Object recognition [46] Object Tracking [10] Video classification [47] Behavior analysis [48] Gait analysis [49] Background subtraction [50] Event recognition [51] Action segmentation [52] Scene understanding [53] 11) ACTION SEGMENTATION Video segmentation is a technique of dividing a video sequence into different sets of continuous frames similar to specific criteria. We observe that performing action segmentation before doing action recognition gives better recognition performance [52]. A challenging problem in human action understanding is to recognize a sequence of continuous actions, which is generally a segment.…”

Section: Human Action Recognition [6][41][42]mentioning

confidence: 99%

Video Processing Using Deep Learning Techniques: A Systematic Literature Review

et al. 2021

View full text Add to dashboard Cite

Studies show lots of advanced research on various data types such as image, speech, and text using deep learning techniques, but nowadays, research on video processing is also an emerging field of computer vision. Several surveys are present on video processing using computer vision deep learning techniques, targeting specific functionality such as anomaly detection, crowd analysis, activity monitoring, etc. However, a combined study is still unexplored. This paper aims to present a Systematic Literature Review (SLR) on video processing using deep learning to investigate the applications, functionalities, techniques, datasets, issues, and challenges by formulating the relevant research questions (RQs). This systematic mapping includes 93 research articles from reputed databases published between 2011 and 2020. We categorize the deep learning technique for video processing as CNN, DNN, and RNN based. We observe the significant advancements in video processing between 2017 and 2020, primarily due to the advent of AlexNet, ResNet, and LSTM based deep learning techniques. The prominent fields of video processing research are observed as human action recognition, crowd anomaly detection, and behavior analysis. This SLR is a helpful guide for the researchers to explore the recent literature, available datasets, and existing deep learning techniques for video processing.

show abstract

“…is process helps to improve the performance of the activity recognition system. erefore, in the literature, the authors of [31][32][33][34][35][36] utilized the latest methods to segment the human body from the video frames. Similarly, for the feature extraction, di erent latest methodologies have been employed which help the classi ers to accurately classify the human activities (as the work ow shown in Figure 1) [37][38][39][40][41][42].…”

Section: Related Workmentioning

confidence: 99%

Human Activity Recognition Using Gaussian Mixture Hidden Conditional Random Fields

Ṣiddiqi

Alruwaili

Ali

et al. 2019

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In healthcare, the analysis of patients’ activities is one of the important factors that offer adequate information to provide better services for managing their illnesses well. Most of the human activity recognition (HAR) systems are completely reliant on recognition module/stage. The inspiration behind the recognition stage is the lack of enhancement in the learning method. In this study, we have proposed the usage of the hidden conditional random fields (HCRFs) for the human activity recognition problem. Moreover, we contend that the existing HCRF model is inadequate by independence assumptions, which may reduce classification accuracy. Therefore, we utilized a new algorithm to relax the assumption, allowing our model to use full-covariance distribution. Also, in this work, we proved that computation wise our method has very much lower complexity against the existing methods. For the experiments, we used four publicly available standard datasets to show the performance. We utilized a 10-fold cross-validation scheme to train, assess, and compare the proposed model with the conditional learning method, hidden Markov model (HMM), and existing HCRF model which can only use diagonal-covariance Gaussian distributions. From the experiments, it is obvious that the proposed model showed a substantial improvement with p value ≤0.2 regarding the classification accuracy.

show abstract

Human Action Segmentation Based on a Streaming Uniform Entropy Slice Method

Cited by 7 publications

References 55 publications

Fast Uncertainty Estimation for Deep Learning Based Optical Flow

Fast Uncertainty Estimation for Deep Learning Based Optical Flow

Video Processing Using Deep Learning Techniques: A Systematic Literature Review

Human Activity Recognition Using Gaussian Mixture Hidden Conditional Random Fields

Contact Info

Product

Resources

About