Deep learning tools for the measurement of animal behavior in neuroscience

MW Mathis, A Mathis - Current opinion in neurobiology, 2020 - Elsevier
Highlights•Deep neural networks are shattering performance benchmarks in computer
vision for various tasks.•Using modern deep learning approaches (DNNs) in the lab is a …

Deep neural network concepts for background subtraction: A systematic review and comparative evaluation

T Bouwmans, S Javed, M Sultana, SK Jung - Neural Networks, 2019 - Elsevier
Conventional neural networks have been demonstrated to be a powerful framework for
background subtraction in video acquired by static cameras. Indeed, the well-known Self …

[PDF][PDF] 人运动的视觉分析综述

王亮, 胡卫明, 谭铁牛 - 2002 - cbsr.ia.ac.cn
摘要目前, 人运动的视觉分析是计算机视觉领域中最活跃的研究主题之一, 其核心是利用计算机
视觉技术从图像序列中检测, 跟踪, 识别人并对其行为进行理解与描述, 它在虚拟现实, 视觉监控 …

[PDF][PDF] 视觉跟踪技术综述

侯志强, 韩崇昭 - 自动化学报, 2006 - researchgate.net
摘要视觉跟踪问题是当前计算机视觉领域中的热点问题, 本文对这一问题进行了详细的介绍.
首先, 对视觉跟踪技术在视频监视, 图像压缩和三维重构等三个主要方面的应用进行了论述 …

A survey on deep learning technique for video segmentation

T Zhou, F Porikli, DJ Crandall… - IEEE transactions on …, 2022 - ieeexplore.ieee.org
Video segmentation—partitioning video frames into multiple segments or objects—plays a
critical role in a broad range of practical applications, from enhancing visual effects in movie …

Vnect: Real-time 3d human pose estimation with a single rgb camera

D Mehta, S Sridhar, O Sotnychenko, H Rhodin… - Acm transactions on …, 2017 - dl.acm.org
We present the first real-time method to capture the full global 3D skeletal pose of a human
in a stable, temporally consistent manner using a single RGB camera. Our method combines …

Monocular 3d human pose estimation in the wild using improved cnn supervision

D Mehta, H Rhodin, D Casas, P Fua… - … conference on 3D …, 2017 - ieeexplore.ieee.org
We propose a CNN-based approach for 3D human body pose estimation from single RGB
images that addresses the issue of limited generalizability of models trained solely on the …

Background subtraction in real applications: Challenges, current models and future directions

B Garcia-Garcia, T Bouwmans, AJR Silva - Computer Science Review, 2020 - Elsevier
Computer vision applications based on videos often require the detection of moving objects
in their first step. Background subtraction is then applied in order to separate the background …

A review on human activity recognition using vision‐based method

S Zhang, Z Wei, J Nie, L Huang… - Journal of healthcare …, 2017 - Wiley Online Library
Human activity recognition (HAR) aims to recognize activities from a series of observations
on the actions of subjects and the environmental conditions. The vision‐based HAR …

Visual tracking: An experimental survey

AWM Smeulders, DM Chu, R Cucchiara… - IEEE transactions on …, 2013 - ieeexplore.ieee.org
There is a large variety of trackers, which have been proposed in the literature during the
last two decades with some mixed success. Object tracking in realistic scenarios is a difficult …