Deep Learning Based 2D Human Pose Estimation: A Survey

A review of deep learning techniques for 2D and 3D human pose estimation

Handwritten character recognition has been profoundly studied for many years in the field of pattern recognition. Due to its vast practical applications and financial implications, handwritten character recognition is still an important research area. In this research, the Handwritten Ethiopian Character Recognition (HECR) dataset has been prepared to train the model. The images in the HECR dataset were organized with more than one color pen RGB main spaces that have been size normalized to 28 × 28 pixels. The dataset is a combination of scripts (Fidel in Ethiopia), numerical representations, punctuations, tonal symbols, combining symbols, and special characters. These scripts have been used to write ancient histories, science, and arts of Ethiopia and Eritrea. In this study, a hybrid model of two super classifiers: Convolutional Neural Network (CNN) and eXtreme Gradient Boosting (XGBoost) is proposed for classification. In this integrated model, CNN works as a trainable automatic feature extractor from the raw images and XGBoost takes the extracted features as an input for recognition and classification. The output error rates of the hybrid model and CNN with a fully connected layer are compared. A 0.4630 and 0.1612 error rates are achieved in classifying the handwritten testing dataset images, respectively. Thus XGBoost as a classifier performs a better result than the traditional fully connected layer.

/pdf/a-new-hybrid-convolutional-neural-network-and-extreme-3vnuhsb7ww.pdf

A New Hybrid Convolutional Neural Network and eXtreme Gradient Boosting Classifier for Recognizing Handwritten Ethiopian Characters

Estimation of the human pose from a monocular camera has been an emerging research topic in the computer vision community with many applications. Recently, benefited from the deep learning technologies, a significant amount of research efforts have greatly advanced the monocular human pose estimation both in 2D and 3D areas. Although there have been some works to summarize the different approaches, it still remains challenging for researchers to have an in-depth view of how these approaches work. In this paper, we provide a comprehensive and holistic 2D-to-3D perspective to tackle this problem. We categorize the mainstream and milestone approaches since the year 2014 under unified frameworks. By systematically summarizing the differences and connections between these approaches, we further analyze the solutions for challenging cases, such as the lack of data, the inherent ambiguity between 2D and 3D, and the complex multi-person scenarios. We also summarize the pose representation styles, benchmarks, evaluation metrics, and the quantitative performance of popular approaches. Finally, we discuss the challenges and give deep thinking of promising directions for future research. We believe this survey will provide the readers with a deep and insightful understanding of monocular human pose estimation.

Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective.

Estimation of the human pose from a monocular camera has been an emerging research topic in the computer vision community with many applications. Recently, benefiting from the deep learning technologies, a significant amount of research efforts have advanced the monocular human pose estimation both in 2D and 3D areas. Although there have been some works to summarize different approaches, it still remains challenging for researchers to have an in-depth view of how these approaches work from 2D to 3D. In this article, we provide a comprehensive and holistic 2D-to-3D perspective to tackle this problem. First, we comprehensively summarize the 2D and 3D representations of human body. Then, we summarize the mainstream and milestone approaches for these human body presentations since the year 2014 under unified frameworks. Especially, we provide insightful analyses for the intrinsic connections and methods evolution from 2D to 3D pose estimation. Furthermore, we analyze the solutions for challenging cases, such as the lack of data, the inherent ambiguity between 2D and 3D, and the complex multi-person scenarios. Next, we summarize the benchmarks, evaluation metrics, and the quantitative performance of popular approaches. Finally, we discuss the challenges and give deep thinking of promising directions for future research. We believe this survey will provide the readers (researchers, engineers, developers, etc.) with a deep and insightful understanding of monocular human pose estimation. 

/pdf/recent-advances-of-monocular-2d-and-3d-human-pose-estimation-3u9y9vg7.pdf

Recent Advances of Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective

Human pose estimation localizes body keypoints to accurately recognizing the postures of individuals given an image. This step is a crucial prerequisite to multiple tasks of computer vision which include human action recognition, human tracking, human-computer interaction, gaming, sign languages, and video surveillance. Therefore, we present this survey article to fill the knowledge gap and shed light on the researches of 2D human pose estimation. A brief introduction is followed by classifying it as a single or multi-person pose estimation based on the number of people needed to be tracked. Then gradually the approaches used in human pose estimation are described before listing some applications and also flaws facing in pose estimation. Following that, a center of attention is given on briefly discussing researches with a significant effect on human pose estimation and examine the novelty, motivation, architecture, the procedures (working principles) of each model together with its practical application and drawbacks, datasets implemented, as well as the evaluation metrics used to evaluate the model. This review is presented as a baseline for newcomers and guides researchers to discover new models by observing the procedure and architecture flaws of existing researches.

/pdf/the-progress-of-human-pose-estimation-a-survey-and-taxonomy-43r9ovz4xt.pdf

The Progress of Human Pose Estimation: A Survey and Taxonomy of Models Applied in 2D Human Pose Estimation

Ethiopie, or Geez is a Semitic language that has been spoken in the horn of Africa, in the history of Ethiopia, but now days it is only used as the language of liturgy in the Ethiopian and Eritrean Orthodox Tewahdo Church. Many of history, science and arts of Ethiopia have been documented by this language and almost all are found in the church. In this paper a Ge'ez Optical Character Recognition (OCR) using Convolutional Neural Network and a feed forward Multi-Layer perceptron are proposed. In order to apply these approaches two steps have done. Firstly, a Multi-Layer Perceptron neural network has developed to compare four widely used Ethiopic typefaces such as Ethiopian Jiret, Ebrima, Nyala and Abyssinica SIL. Images of 26 Ge'ez script written from these typefaces were given to the neural network for training and then scanned documents was given again as an input to check which of these typeface characters are recognized and classified. As a result, characters written in Ethiopian Jiret typeface has recognized very well. In the second part, using Ethiopian Jiret typeface many images of strings have been generated in using a standard python codec registry, then these images have used as an input to the Convolutional Neural Network and Multi-Layer Perceptron comparison. The results are promising and provide a better direction to the future work.

Halefom Tekle Weldegebriel

Papers

The Progress of Human Pose Estimation: A Survey and Taxonomy of Models Applied in 2D Human Pose Estimation

A New Hybrid Convolutional Neural Network and eXtreme Gradient Boosting Classifier for Recognizing Handwritten Ethiopian Characters

Deep learning for Ethiopian Ge'ez script optical character recognision