Open AccessPosted Content
OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
Reads0
Chats0
TLDR
OpenPose is released, the first open-source realtime system for multi-person 2D pose detection, including body, foot, hand, and facial keypoints, and the first combined body and foot keypoint detector, based on an internal annotated foot dataset.Abstract:
Realtime multi-person 2D pose estimation is a key component in enabling machines to have an understanding of people in images and videos. In this work, we present a realtime approach to detect the 2D pose of multiple people in an image. The proposed method uses a nonparametric representation, which we refer to as Part Affinity Fields (PAFs), to learn to associate body parts with individuals in the image. This bottom-up system achieves high accuracy and realtime performance, regardless of the number of people in the image. In previous work, PAFs and body part location estimation were refined simultaneously across training stages. We demonstrate that a PAF-only refinement rather than both PAF and body part location refinement results in a substantial increase in both runtime performance and accuracy. We also present the first combined body and foot keypoint detector, based on an internal annotated foot dataset that we have publicly released. We show that the combined detector not only reduces the inference time compared to running them sequentially, but also maintains the accuracy of each component individually. This work has culminated in the release of OpenPose, the first open-source realtime system for multi-person 2D pose detection, including body, foot, hand, and facial keypoints.read more
Citations
More filters
Proceedings ArticleDOI
Down to the Last Detail: Virtual Try-on with Fine-grained Details
TL;DR: A Tree-Block (tree dilated fusion block) to replace standard ResNet-block to address the long-range translation and rich-details generation, and a multi-stage framework to synthesize person images, where fine-grained details can be well preserved.
Posted Content
Foley Music: Learning to Generate Music from Videos.
TL;DR: Foley Music as discussed by the authors uses body keypoints from videos and MIDI events from audio recordings to synthesize plausible music for a silent video clip about people playing musical instruments, which can be converted to realistic music using an off-the-shelf music synthesizer tool.
Journal ArticleDOI
Exploiting visual cues for safe and flexible cyber-physical production systems:
Syed Osama Bin Islam,Waqas Akbar Lughmani,Waqar S. Qureshi,Waqar S. Qureshi,Azfar Khalid,M.A. Mariscal,Susana García-Herrero +6 more
TL;DR: An ontology-based approach to solve industrial scenarios for safety applications in cyber-physical production systems and multiple scenarios are tested for simultaneous detection and prioritization to enhance the learning surface of the intelligent production system with the goal to automate safety-based decisions.
Posted Content
Locality Aware Appearance Metric for Multi-Target Multi-Camera Tracking.
TL;DR: It is argued that the mismatch between the local matching procedure in tracking and the global nature of re-ID appearance features may compromise MTMCT performance, and introduces locality aware appearance metric (LAAM), which is a trained metric for single camera tracking and an inter-camera metric for multi-camera tracking.
Proceedings ArticleDOI
Admittance control for collaborative dual-arm manipulation
Sonny Tarbouriech,Benjamin Navarro,Philippe Fraisse,André Crosnier,Andrea Cherubini,Damien Sallé +5 more
TL;DR: This work proposes a kinematic control strategy for dual-arm robotic platforms physically collaborating with human operators based on admittance control at improving the performance of object transportation tasks by acting on two levels: estimating and compensating gravity effects on one side and considering human intention in the cooperative task space on the other.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Book ChapterDOI
Microsoft COCO: Common Objects in Context
Tsung-Yi Lin,Michael Maire,Serge Belongie,James Hays,Pietro Perona,Deva Ramanan,Piotr Dollár,C. Lawrence Zitnick +7 more
TL;DR: A new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding by gathering images of complex everyday scenes containing common objects in their natural context.
Proceedings ArticleDOI
Densely Connected Convolutional Networks
TL;DR: DenseNet as mentioned in this paper proposes to connect each layer to every other layer in a feed-forward fashion, which can alleviate the vanishing gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters.