Visual Feature Learning on Video Object and Human Action Detection: A Systematic Review

Abstract

Video object and human action detection are applied in many fields, such as video surveillance, face recognition, etc. Video object detection includes object classification and object location within the frame. Human action recognition is the detection of human actions. Usually, video detection is more challenging than image detection, since video frames are often more blurry than images. Moreover, video detection often has other difficulties, such as video defocus, motion blur, part occlusion, etc. Nowadays, the video detection technology is able to implement real-time detection, or high-accurate detection of blurry video frames. In this paper, various video object and human action detection approaches are reviewed and discussed, many of them have performed state-of-the-art results. We mainly review and discuss the classic video detection methods with supervised learning. In addition, the frequently-used video object detection and human action recognition datasets are reviewed. Finally, a summarization of the video detection is represented, e.g., the video object and human action detection methods could be classified into frame-by-frame (frame-based) detection, extracting-key-frame detection and using-temporal-information detection; the methods of utilizing temporal information of adjacent video frames are mainly the optical flow method, Long Short-Term Memory and convolution among adjacent frames.

Tackling Explicit Material from Online Video Conferencing Software for Education Using Deep Attention Neural Architectures

“…It aims to maximize the second term of the Discriminator cost function - after all, only this term can affect the Discriminator's cost function to increase it. Therefore, the following will apply to the Generator [ 8 ]: where the negative sign at the beginning has now been removed as the Generator tries by minimizing its cost function to increase that of the Discriminator, while all other sizes are as before. Because the first term of the equation depends only on the training data set, the above Generator cost function is declared as negative of the Discriminator cost function [ 22 , 23 ]: …”

“…It is continuous and differentiable and does not increase too fast. The proposed model introduces a normalization term that imposes a penalty when the norm of some of the output derivatives of Discriminator concerning its input is greater than 1 so that [ 21 ] and so, the cost functions that the two neural networks try to minimize will be [ 8 , 21 , 22 ]: …”

“…For our problem, these graphs show the flow of information between the attention steps and the corresponding transformations that follow. The most common of the proposed transformations are [ 8 , 22 , 23 ]: …”

“…Li et al [ 8 ] studied numerous motion classification algorithms, concentrating on video using classifiers, mostly frame-based. They divided the basic processes into three main categories: the first was frame-by-frame recognition, the second was extracting sequences, and the third was temporal-information monitoring, which used the LSTM structure or the optical flow approach to remove training data between sequences.…”

Vision-Based Module for Herding with a Sheepdog Robot

“…As the proposed module is deployed in real-time environments, it is based on one-stage detectors. The considered state-of-the-art algorithms [ 72 ] based on one stage are You Only Look Once (YOLO) in different versions (YOLOv1, YOLOv2, YOLOv3, YOLOv4, YOLOv5) and Single-Shot MultiBox Detector (SSD). SSD has improved versions such as Deconvolutional SSD (DSSD) that includes large-scale context in object detection, Rainbow SSD (RSSD) that concatenates different feature maps using deconvolution and batch normalisation [ 73 ], and Feature-fusion SSD (FSSD) that balances semantic and positional information using bilinear interpolation to resize feature maps to the same size to be subsequently concatenated [ 74 ].…”